A pressure correction method, device, equipment and storage medium

Abstract

The application discloses a pressure correction method, device, equipment and storage medium. The method comprises the following steps: obtaining historical material data of a roller press, establishing a pressure prediction model according to the historical material data; obtaining to-be-tested material data, determining a predicted steady-state pressure according to the to-be-tested material data and the pressure prediction model; and performing pressure correction of the roller press according to the predicted steady-state pressure. The historical material data of the roller press is obtained, a pressure prediction model is established based on a big data statistical regression modeling method, the steady-state pressure of the next batch can be predicted according to the steady-state pressure of the last batch, then the corresponding target pressure increment is determined according to the target steady-state speed set by a user, finally, the difference between the predicted steady-state pressure and the target pressure increment is taken as a target correction pressure, the pressure correction is realized, the problem of material scrapping caused by slow pressure adjustment is solved, the pressure can be effectively and quickly adjusted, the pressure adjustment efficiency is improved, the appearance of out-of-specification materials is reduced, and the production quality is ensured.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a pressure correction method, apparatus, device, and storage medium. Background Technology

[0002] Roller presses, also known as calenders, double-roll mills, rolling mills, extrusion mills, and roller mills, can replace the energy-intensive and inefficient ball mill pre-grinding system, and reduce steel consumption and noise.

[0003] In the rolling process, materials need to be extruded and ground to specified specifications using a controlled roller press. Because different batches of material have different characteristics, their pressure requirements also differ. Before entering the roller press, it's sometimes impossible to directly measure the incoming material characteristics, resulting in a lack of crucial feedforward information. If the initial pressure during production is inaccurate, relying solely on feedback from the material's specifications after extrusion and grinding can easily lead to slow pressure adjustment, causing a significant amount of material to exceed specifications and become scrap. Summary of the Invention

[0004] This invention provides a pressure correction method, apparatus, equipment, and storage medium to quickly correct the initial pressure when a roller press is grinding materials, thereby ensuring the working efficiency of the roller press.

[0005] According to one aspect of the present invention, a pressure correction method is provided, the method comprising:

[0006] Obtain historical material data of the roller press, and establish a pressure prediction model based on the historical material data. The pressure prediction model includes the correspondence between material data and steady-state pressure.

[0007] Acquire data on the material to be tested, and determine the predicted steady-state pressure based on the data and the pressure prediction model;

[0008] Pressure correction for the roller press is performed based on the predicted steady-state pressure.

[0009] Optionally, historical material data of the roller press can be obtained, including: obtaining production-related data of the roller press within a specified time range, wherein the production-related data includes steady-state pressure, material head specifications, target specifications, and initial pressure; determining the production batch corresponding to each production-related data, generating data groups based on the production batch and production-related data, wherein the data groups include production-related data of the same production batch; and using each data group as historical material data.

[0010] Optionally, a pressure prediction model is established based on historical material data, including: building the network structure of a multiple regression model and determining the model parameters corresponding to the network structure, wherein the model parameters include the intercept term, the change in thickness deviation corresponding to a unit steady-state pressure difference, and the change in thickness deviation corresponding to a unit pressure relief; training the model parameters based on historical material data and determining the training error function using the least squares method; when the training error function is less than a preset threshold, the corresponding model parameters are used as the target model parameters; and a pressure prediction model is established based on the target model parameters.

[0011] Optionally, the data of the material to be tested can be obtained, including: determining the current production batch and obtaining the current feed head specification and target feed head specification corresponding to the current production batch; obtaining the previous steady-state pressure and previous initial pressure corresponding to the previous batch based on the current production batch; and using the current feed head specification, target feed head specification, previous steady-state pressure and previous initial pressure as the data of the material to be tested.

[0012] Optionally, the predicted steady-state pressure is determined based on the data of the material to be measured and the pressure prediction model, including: calculating the difference between the previous steady-state pressure and the previous initial pressure to determine the pressure relief change value; and inputting the current feed head specification, the target feed head specification, the previous steady-state pressure and the pressure relief change value into the pressure prediction model to obtain the output predicted steady-state pressure.

[0013] Optionally, the pressure correction of the roller press is performed based on the predicted steady-state pressure, including: obtaining the target steady-state speed, determining the target pressure increment based on the target steady-state speed; using the difference between the predicted steady-state pressure and the target pressure increment as the target correction pressure; and performing pressure correction of the roller press based on the target correction pressure.

[0014] Optionally, determining the target pressure increment based on the target steady-state velocity includes: obtaining a pressure increment list, wherein the pressure increment list includes the pressure increment corresponding to the velocity change; obtaining the current velocity of the roller press, calculating the difference between the current velocity and the target steady-state velocity as the target velocity change; and matching the target velocity change with the pressure increment list to obtain the target pressure increment corresponding to the target velocity change.

[0015] According to another aspect of the present invention, a pressure correction device is provided, the device comprising:

[0016] The pressure prediction model building module is used to acquire historical material data of the roller press and build a pressure prediction model based on the historical material data. The pressure prediction model includes the correspondence between material data and steady-state pressure.

[0017] The predictive steady-state pressure determination module is used to acquire data on the material to be measured and determine the predicted steady-state pressure based on the data on the material to be measured and the pressure prediction model.

[0018] The roller press pressure correction module is used to correct the pressure of the roller press based on the predicted steady-state pressure.

[0019] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0020] At least one processor; and

[0021] A memory communicatively connected to the at least one processor; wherein,

[0022] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform a pressure correction method according to any embodiment of the present invention.

[0023] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement a pressure correction method according to any embodiment of the present invention.

[0024] The technical solution of this invention acquires historical material data from the roller press and establishes a pressure prediction model based on big data statistical regression modeling. It can predict the steady-state pressure of the next batch based on the steady-state pressure of the previous batch, and then determine the corresponding target pressure increment based on the target steady-state speed set by the user. Finally, the difference between the predicted steady-state pressure and the target pressure increment is used as the target correction pressure, thereby realizing pressure correction and solving the problem of material scrap caused by slow pressure adjustment. It can effectively and quickly adjust the pressure, improve the pressure adjustment efficiency, reduce the occurrence of out-of-specification materials, and ensure production quality.

[0025] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0026] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0027] Figure 1 This is a flowchart of a pressure correction method provided in Embodiment 1 of the present invention;

[0028] Figure 2This is a flowchart of another pressure correction method provided in Embodiment 2 of the present invention;

[0029] Figure 3 This is a schematic diagram of a pressure correction device according to Embodiment 3 of the present invention;

[0030] Figure 4 This is a schematic diagram of the structure of an electronic device that implements a pressure correction method according to an embodiment of the present invention. Detailed Implementation

[0031] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0032] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0033] Example 1

[0034] Figure 1 The flowchart of a pressure correction method is provided in Embodiment 1 of the present invention. This embodiment is applicable to the case of a roller press extruding and grinding materials. The method can be executed by a pressure correction device, which can be implemented in hardware and / or software and can be configured in a computer controller. Figure 1 As shown, the method includes:

[0035] S110. Obtain historical material data of the roller press and establish a pressure prediction model based on the historical material data.

[0036] A roller press is a grinding equipment used to extrude and grind materials to a specified specification. It is also known as a calender, double-roll mill, rolling mill, extrusion mill, or roller mill. A roller press consists of two opposing, synchronously rotating extrusion rollers. During operation, material is fed from above the rollers and continuously drawn into the space between them, where it is pulverized under high pressure. During the roller press grinding process, equipment parameters, such as pressure, need to be preset according to the properties of the raw material. When the properties of the raw material change, the roller press equipment parameters need to be adjusted in a timely manner to ensure stable production and equipment safety. Historical material data refers to the historical data of material grinding in the roller press, including the steady-state pressure of each batch of material during continuous production, the first specification data of each batch of material during the initial batch production, and the initial pressure at that time. It is known that the same pressure has different extrusion and grinding effects at different speeds; the faster the speed, the greater the pressure required to achieve the same extrusion and grinding effect. Therefore, after a batch of material is produced, the pressure needs to be released to meet the low-speed production requirements of the next batch.

[0037] Specifically, a pressure prediction model can be established based on the acquired historical material data. The pressure prediction model includes the correspondence between material data and steady-state pressure. Through the pressure prediction model, the next steady-state pressure can be predicted based on the previous steady-state pressure, thereby realizing pressure correction.

[0038] Optionally, historical material data of the roller press can be obtained, including: obtaining production-related data of the roller press within a specified time range, wherein the production-related data includes steady-state pressure, material head specifications, target specifications, and initial pressure; determining the production batch corresponding to each production-related data, generating data groups based on the production batch and production-related data, wherein the data groups include production-related data of the same production batch; and using each data group as historical material data.

[0039] Specifically, the specified time range can be set according to user needs. When acquiring data, the controller can obtain continuous production-related data from multiple batches of the roller press within the specified time range. The controller refers to the computer controller that performs pressure correction. Production-related data includes steady-state pressure, material head specifications, target specifications, and initial pressure. It should be noted that pressure is a crucial parameter for the stable operation of the roller press and directly affects its extrusion effect. However, the extrusion pressure of the roller press cannot be too high or too low. Excessive pressure will cause significant wear on the roller surface, while insufficient pressure will affect the extrusion effect. Steady-state pressure refers to the pressure corresponding to the roller press during stable operation. Material head specifications refer to the initial size information of the material. Target specifications refer to the grinding size information set by the user. The roller press can grind the material according to the user-set target specifications to achieve the target material head specifications. Initial pressure is the pressure corresponding to the material just entering the roller press. Furthermore, the controller will determine the production batch corresponding to each production-related data, and then group the production-related data of the same production batch into the same data group so that a pressure prediction model can be built in the form of data grouping. Grouping by production batch is to better establish the relationship between the previous batch of data and the next batch of data during model training, thereby enabling stress prediction.

[0040] Optionally, a pressure prediction model is established based on historical material data, including: building the network structure of a multiple regression model and determining the model parameters corresponding to the network structure, wherein the model parameters include the intercept term, the change in thickness deviation corresponding to a unit steady-state pressure difference, and the change in thickness deviation corresponding to a unit pressure relief; training the model parameters based on historical material data and determining the training error function using the least squares method; when the training error function is less than a preset threshold, the corresponding model parameters are used as the target model parameters; and a pressure prediction model is established based on the target model parameters.

[0041] Specifically, the network structure of the multiple regression model is represented by the following formula (1):

[0042] Y 料头 -Y 目标 =k0+k1*(P 下一稳态压力 -P 上一稳态压力 )+k2*ΔP 泄压 (1)

[0043] Among them, Y 料头 Indicates the material head specification, Y 目标 P represents the target specification. 上一稳态压力 P represents the steady-state pressure of the previous batch. 下一稳态压力 Indicates the steady-state pressure of the next batch, ΔP 泄压This represents the pressure relief amount, i.e., the change between the initial pressure and the steady-state pressure. k0, k1, and k2 are model parameters. k0 represents the intercept term; k1 represents the change in thickness deviation corresponding to a unit steady-state pressure difference, i.e., the change in thickness deviation when the steady-state pressure difference between two rolls is 1 unit; and k2 represents the change in thickness deviation corresponding to a unit pressure relief, i.e., the change in thickness deviation when 1 unit of pressure is relieved. The model parameters can be trained based on historical material data. During training, the least squares method is used for fitting, and the training error function is determined. When the training error function is less than a preset threshold, the model training is complete. At this point, a pressure prediction model can be established based on the corresponding target model parameters.

[0044] S120. Obtain the data of the material to be tested, and determine the predicted steady-state pressure based on the data of the material to be tested and the pressure prediction model.

[0045] Optionally, the data of the material to be tested can be obtained, including: determining the current production batch and obtaining the current feed head specification and target feed head specification corresponding to the current production batch; obtaining the previous steady-state pressure and previous initial pressure corresponding to the previous batch based on the current production batch; and using the current feed head specification, target feed head specification, previous steady-state pressure and previous initial pressure as the data of the material to be tested.

[0046] Specifically, since the pressure prediction model predicts the next batch of data based on the previous batch of data, when performing steady-state pressure prediction, it is necessary to determine the current production batch, then obtain the current feed head specification and target feed head specification corresponding to the current production batch, and obtain the previous steady-state pressure and previous initial pressure corresponding to the previous batch. Then, the current feed head specification, target feed head specification, previous steady-state pressure, and previous initial pressure are used as the data of the material to be measured.

[0047] Optionally, the predicted steady-state pressure is determined based on the data of the material to be measured and the pressure prediction model, including: calculating the difference between the previous steady-state pressure and the previous initial pressure to determine the pressure relief change value; and inputting the current feed head specification, the target feed head specification, the previous steady-state pressure and the pressure relief change value into the pressure prediction model to obtain the output predicted steady-state pressure.

[0048] Specifically, the pressure relief change value is the difference between the previous steady-state pressure and the previous initial pressure. After determining the pressure relief change value, the current feed head specification, target feed head specification, previous steady-state pressure, and pressure relief change value are input into the pressure prediction model to obtain the predicted steady-state pressure output by the model.

[0049] S130. Adjust the pressure of the roller press according to the predicted steady-state pressure.

[0050] Specifically, the predicted steady-state pressure output by the model is the predicted value of the steady-state pressure for the next batch. The initial pressure is adjusted based on the predicted steady-state pressure. The initial pressure is quickly corrected by the roller press control method based on big data statistical regression modeling.

[0051] The technical solution of this invention acquires historical material data from the roller press and establishes a pressure prediction model based on big data statistical regression modeling. It can predict the steady-state pressure of the next batch based on the steady-state pressure of the previous batch, and then determine the corresponding target pressure increment based on the target steady-state speed set by the user. Finally, the difference between the predicted steady-state pressure and the target pressure increment is used as the target correction pressure, thereby realizing pressure correction and solving the problem of material scrap caused by slow pressure adjustment. It can effectively and quickly adjust the pressure, improve the pressure adjustment efficiency, reduce the occurrence of out-of-specification materials, and ensure production quality.

[0052] Example 2

[0053] Figure 2 This is a flowchart of a pressure correction method provided in Embodiment 2 of the present invention. This embodiment adds a specific process for pressure correction of the roller press based on the predicted steady-state pressure, building upon Embodiment 1. For example... Figure 2 As shown, the method includes:

[0054] S210. Obtain historical material data of the roller press and establish a pressure prediction model based on the historical material data. The pressure prediction model includes the correspondence between material data and steady-state pressure.

[0055] Optionally, historical material data of the roller press can be obtained, including: obtaining production-related data of the roller press within a specified time range, wherein the production-related data includes steady-state pressure, material head specifications, target specifications, and initial pressure; determining the production batch corresponding to each production-related data, generating data groups based on the production batch and production-related data, wherein the data groups include production-related data of the same production batch; and using each data group as historical material data.

[0056] Optionally, a pressure prediction model is established based on historical material data, including: building the network structure of a multiple regression model and determining the model parameters corresponding to the network structure, wherein the model parameters include the intercept term, the change in thickness deviation corresponding to a unit steady-state pressure difference, and the change in thickness deviation corresponding to a unit pressure relief; training the model parameters based on historical material data and determining the training error function using the least squares method; when the training error function is less than a preset threshold, the corresponding model parameters are used as the target model parameters; and a pressure prediction model is established based on the target model parameters.

[0057] S220. Obtain the data of the material to be tested, and determine the predicted steady-state pressure based on the data of the material to be tested and the pressure prediction model.

[0058] Optionally, the data of the material to be tested can be obtained, including: determining the current production batch and obtaining the current feed head specification and target feed head specification corresponding to the current production batch; obtaining the previous steady-state pressure and previous initial pressure corresponding to the previous batch based on the current production batch; and using the current feed head specification, target feed head specification, previous steady-state pressure and previous initial pressure as the data of the material to be tested.

[0059] Optionally, the predicted steady-state pressure is determined based on the data of the material to be measured and the pressure prediction model, including: calculating the difference between the previous steady-state pressure and the previous initial pressure to determine the pressure relief change value; and inputting the current feed head specification, the target feed head specification, the previous steady-state pressure and the pressure relief change value into the pressure prediction model to obtain the output predicted steady-state pressure.

[0060] S230. Obtain the target steady-state velocity and determine the target pressure increment based on the target steady-state velocity.

[0061] Optionally, determining the target pressure increment based on the target steady-state velocity includes: obtaining a pressure increment list, wherein the pressure increment list includes the pressure increment corresponding to the velocity change; obtaining the current velocity of the roller press, calculating the difference between the current velocity and the target steady-state velocity as the target velocity change; and matching the target velocity change with the pressure increment list to obtain the target pressure increment corresponding to the target velocity change.

[0062] Specifically, the pressure increment list is a list set by the user based on manual experience and historical data. It includes the pressure increment corresponding to each speed change, and the pressure increment can be positive or negative. Since the motor speed of the roller press may not return to zero after processing a batch of material due to inertia, it is also necessary to determine the current speed of the roller press and then calculate the difference between the current speed and the target steady-state speed to determine the target speed change. The pressure increment list can be used to match the target speed change, thus determining the pressure increment when the speed changes from the current speed to the target steady-state speed, i.e., the target pressure increment.

[0063] S240. The difference between the predicted steady-state pressure and the target pressure increment is used as the target correction pressure.

[0064] S250, Adjust the pressure of the roller press according to the target adjustment pressure.

[0065] Specifically, based on the predicted steady-state pressure from the model, the pressure increment during the acceleration process can be used to quickly correct the initial pressure during material production. Specifically, the target correction pressure can be determined by calculating the difference between the predicted steady-state pressure and the target pressure increment. The target correction pressure is the corrected pressure, and the controller ultimately achieves pressure correction through the target correction pressure.

[0066] The technical solution of this invention acquires historical material data from the roller press and establishes a pressure prediction model based on big data statistical regression modeling. It can predict the steady-state pressure of the next batch based on the steady-state pressure of the previous batch, and then determine the corresponding target pressure increment based on the target steady-state speed set by the user. Finally, the difference between the predicted steady-state pressure and the target pressure increment is used as the target correction pressure, thereby realizing pressure correction and solving the problem of material scrap caused by slow pressure adjustment. It can effectively and quickly adjust the pressure, improve the pressure adjustment efficiency, reduce the occurrence of out-of-specification materials, and ensure production quality.

[0067] Example 3

[0068] Figure 3 This is a schematic diagram of a pressure correction device provided in Embodiment 3 of the present invention. Figure 3 As shown, the device includes:

[0069] The pressure prediction model building module 310 is used to acquire historical material data of the roller press and build a pressure prediction model based on the historical material data. The pressure prediction model includes the correspondence between material data and steady-state pressure.

[0070] The predictive steady-state pressure determination module 320 is used to acquire data of the material to be measured and determine the predicted steady-state pressure based on the data of the material to be measured and the pressure prediction model.

[0071] The roller press pressure correction module 330 is used to correct the pressure of the roller press based on the predicted steady-state pressure.

[0072] Optionally, the pressure prediction model establishment module 310 specifically includes: a historical material data acquisition unit, used to: acquire production-related data of the roller press within a specified time range, wherein the production-related data includes steady-state pressure, material head specifications, target specifications, and initial pressure; determine the production batch corresponding to each production-related data, generate data groups based on the production batch and production-related data, wherein the data groups include production-related data of the same production batch; and use each data group as historical material data.

[0073] Optionally, the pressure prediction model building module 310 specifically includes: a pressure prediction model building unit, used for: building the network structure of a multiple regression model and determining the model parameters corresponding to the network structure, wherein the model parameters include the intercept term, the thickness deviation change corresponding to a unit steady-state pressure difference, and the thickness deviation change corresponding to a unit pressure relief; training the model parameters based on historical material data and determining the training error function using the least squares method; when the training error function is less than a preset threshold, using the corresponding model parameters as the target model parameters; and building a pressure prediction model based on the target model parameters.

[0074] Optionally, the steady-state pressure prediction module 320 specifically includes: a material data acquisition unit, used to: determine the current production batch and acquire the current feed head specification and target feed head specification corresponding to the current production batch; acquire the previous steady-state pressure and previous initial pressure corresponding to the previous batch based on the current production batch; and use the current feed head specification, target feed head specification, previous steady-state pressure, and previous initial pressure as the material data to be tested.

[0075] Optionally, the steady-state pressure prediction module 320 specifically includes: a steady-state pressure prediction unit, used to: calculate the difference between the previous steady-state pressure and the previous initial pressure to determine the pressure relief change value; input the current feed head specification, the target feed head specification, the previous steady-state pressure and the pressure relief change value into the pressure prediction model to obtain the output predicted steady-state pressure.

[0076] Optionally, the roller press pressure correction module 330 specifically includes: a target pressure increment determination unit, used to: obtain the target steady-state velocity and determine the target pressure increment based on the target steady-state velocity; a target correction pressure calculation unit, used to: use the difference between the predicted steady-state pressure and the target pressure increment as the target correction pressure; and a pressure correction unit, used to: perform pressure correction of the roller press based on the target correction pressure.

[0077] Optionally, the target pressure increment determination unit is specifically used to: obtain a pressure increment list, wherein the pressure increment list includes pressure increments corresponding to steady-state velocities; and match the target steady-state velocity with the pressure increment list to obtain the target pressure increment corresponding to the target steady-state velocity.

[0078] The technical solution of this invention acquires historical material data from the roller press and establishes a pressure prediction model based on big data statistical regression modeling. It can predict the steady-state pressure of the next batch based on the steady-state pressure of the previous batch, and then determine the corresponding target pressure increment based on the target steady-state speed set by the user. Finally, the difference between the predicted steady-state pressure and the target pressure increment is used as the target correction pressure, thereby realizing pressure correction and solving the problem of material scrap caused by slow pressure adjustment. It can effectively and quickly adjust the pressure, improve the pressure adjustment efficiency, reduce the occurrence of out-of-specification materials, and ensure production quality.

[0079] The pressure correction device provided in this embodiment of the invention can execute a pressure correction method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0080] Example 4

[0081] Figure 4A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0082] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0083] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0084] Processor 11 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, central processing unit (CPU), graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as a pressure correction method. That is: acquiring historical material data of the roller press, establishing a pressure prediction model based on the historical material data, wherein the pressure prediction model includes the correspondence between material data and steady-state pressure; acquiring the material data to be measured, determining the predicted steady-state pressure based on the material data to be measured and the pressure prediction model; and performing pressure correction of the roller press based on the predicted steady-state pressure.

[0085] In some embodiments, a stress correction method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or mounted on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of a stress correction method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform a stress correction method by any other suitable means (e.g., by means of firmware).

[0086] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0087] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0088] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0089] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0090] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0091] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0092] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0093] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A pressure correction method, characterized by, The method comprises the following steps: obtaining historical material data of the roller press, and establishing a pressure prediction model according to the historical material data, wherein the pressure prediction model comprises a corresponding relationship between material data and steady-state pressure; obtaining to-be-tested material data, and determining a predicted steady-state pressure according to the to-be-tested material data and the pressure prediction model; performing pressure correction of the roller press according to the predicted steady-state pressure; wherein the establishment of the pressure prediction model according to the historical material data comprises: building a network structure of a multiple regression model, and determining model parameters corresponding to the network structure, wherein the model parameters comprise an intercept term, a thickness deviation change corresponding to a unit steady-state pressure difference, and a thickness deviation change corresponding to a unit pressure relief; training the model parameters according to the historical material data, and determining a training error function by using a least squares method; when the training error function is less than a preset threshold, the corresponding model parameters are taken as target model parameters; establishing a pressure prediction model according to the target model parameters.

2. The method of claim 1, wherein, The obtaining of the historical material data of the roller press comprises: obtaining production-related data of the roller press within a specified time range, wherein the production-related data comprises a steady-state pressure, a head specification, a target specification, and an initial pressure; determining production batches corresponding to each of the production-related data, and generating data groups according to the production batches and the production-related data, wherein the data groups comprise production-related data of the same production batch; each of the data groups is taken as the historical material data.

3. The method of claim 1, wherein, The obtaining of the to-be-tested material data comprises: determining a current production batch, and obtaining a current head specification and a target head specification corresponding to the current production batch; obtaining a previous steady-state pressure and a previous initial pressure corresponding to a previous batch according to the current production batch; the current head specification, the target head specification, the previous steady-state pressure, and the previous initial pressure are taken as the to-be-tested material data.

4. The method of claim 3, wherein, The determination of the predicted steady-state pressure according to the to-be-tested material data and the pressure prediction model comprises: calculating a difference between the previous steady-state pressure and the previous initial pressure to determine a pressure relief change value; inputting the current head specification, the target head specification, the previous steady-state pressure, and the pressure relief change value into the pressure prediction model to obtain an output predicted steady-state pressure.

5. The method of claim 1, wherein, The pressure correction of the roller press according to the predicted steady-state pressure comprises: obtaining a target steady-state speed, and determining a target pressure increment according to the target steady-state speed; taking a difference between the predicted steady-state pressure and the target pressure increment as a target correction pressure; performing pressure correction of the roller press according to the target correction pressure.

6. The method of claim 5, wherein, The determination of the target pressure increment according to the target steady-state speed comprises: obtaining a pressure increment list, wherein the pressure increment list comprises a pressure increment corresponding to a speed change amount; obtaining a current speed of the roller press, and calculating a difference between the current speed and the target steady-state speed as a target speed change amount; matching the target speed change amount through the pressure increment list to obtain a target pressure increment corresponding to the target speed change amount.

7. A pressure correction device, characterized by The method comprises the following steps: The pressure prediction model establishing module is configured to acquire historical material data of the roller press, and establish a pressure prediction model according to the historical material data, wherein the pressure prediction model comprises a corresponding relationship between material data and steady-state pressure. The predicted steady-state pressure determining module is configured to acquire to-be-measured material data, and determine a predicted steady-state pressure according to the to-be-measured material data and the pressure prediction model. The roller press pressure correcting module is configured to correct the pressure of the roller press according to the predicted steady-state pressure. The pressure prediction model establishing module specifically comprises a pressure prediction model establishing unit configured to build a network structure of a multiple regression model, and determine model parameters corresponding to the network structure, wherein the model parameters comprise an intercept term, a thickness deviation change amount corresponding to a unit steady-state pressure difference, and a thickness deviation change amount corresponding to a unit pressure relief. The model parameters are trained according to the historical material data, and a training error function is determined by using a least square method. When the training error function is less than a preset threshold, the corresponding model parameters are taken as target model parameters. The pressure prediction model is established according to the target model parameters.

8. An electronic device, comprising: The electronic device comprises: at least one processor; and a memory connected with the at least one processor in communication; wherein the memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the method in any one of claims 1-6.

9. A computer storage medium, characterized in that The computer storage medium stores computer instructions, and the computer instructions are used to enable the processor to implement the method in any one of claims 1-6 when executed.

Images