Sintering end point control method, system and device, electronic equipment and storage medium

Abstract

The invention provides a sintering end point control method, system and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining sintering operation data, and extracting a plurality of thermal state parameters and corresponding sintering speeds of a target time window based on the sintering operation data, obtaining a screening coefficient according to the variable quantity of the thermal state parameters and the variable quantity of the sintering speed of the target time window, screening the thermal state parameters based on the screening coefficient to obtain a set of thermal state characteristics, and splicing the set of thermal state characteristics based on a time sequence to obtain a thermal state characteristic matrix, fusing the thermal state feature matrix based on a time sequence based on a preset convolutional neural network to obtain a fused feature matrix, inputting the fused feature matrix into a preset sintering end point control model to obtain a sintering speed adjustment amount, and adjusting the current sintering speed based on the sintering speed adjustment amount to control the sintering end point. The method solves the technical problem that the stability of the sintering end point cannot be controlled.

Description

Technical Field

[0001] The present application relates to the technical field of steel smelting, and in particular to a sintering endpoint control method, system, device, electronic equipment and storage medium. Background Art

[0002] Sintering is an important raw material preparation process in the steel production process. Through a series of complex physical and chemical reactions, iron ore raw materials are smelted into sintered ore with high mechanical strength, good air permeability, suitable composition and qualified particle size for subsequent blast furnace ironmaking. The complexity of the sintering process is reflected in the fact that it involves many physical and chemical reactions, the system has many internal parameters and the coupling between the parameters is strong, and it has strong nonlinearity and large time lag. Therefore, the optimization control of the sintering production process is still highly dependent on operators.

[0003] The stability of the sintering thermal state comprehensively reflects the matching degree between the sintering raw material conditions and the process control parameters. Controlling the stability of the sintering thermal state is the key to controlling the stability of the entire sintering production process. The sintering endpoint is an important indicator for judging the stability of the sintering thermal state. It is also an important process parameter that affects the output and performance of sintered ore during the sintering production process. Controlling the suitability and stability of the sintering endpoint is an important goal of intelligent sintering. However, due to the complexity of the sintering process, the sintering endpoint is currently mainly controlled by the operator adjusting the sintering machine speed. Due to the different judgment abilities, personal experiences and operating habits of different operators, coupled with the daily shift system of the sintering plant and the variability of sintering conditions, it is difficult to ensure that the sintering endpoint is continuously controlled within a stable and appropriate range. Summary of the invention

[0004] In view of the shortcomings of the related technologies mentioned above, the present application provides a sintering endpoint control method, system, device, electronic device and storage medium to solve the technical problem of being unable to control the stability of the sintering endpoint.

[0005] The present application provides a sintering endpoint control method, which includes: acquiring sintering operation data, extracting multiple thermal state parameters and corresponding sintering speeds in a target time window based on the sintering operation data; obtaining a screening coefficient according to the change amount of the thermal state parameters in the target time window and the change amount of the sintering speed, and screening the thermal state parameters based on the screening coefficient to obtain a set of thermal state characteristics; splicing the set of thermal state characteristics based on time series to obtain a thermal state characteristic matrix, and fusing the thermal state characteristic matrix based on time series based on a preset convolutional neural network to obtain a fused characteristic matrix; inputting the fused characteristic matrix into a preset sintering endpoint control model to obtain a sintering speed adjustment amount, and adjusting the current sintering speed based on the sintering speed adjustment amount to control the sintering endpoint.

[0006] In one embodiment of the present application, a screening coefficient is obtained according to the change of the thermal state parameter and the change of the sintering speed in the target time window, and the thermal state parameters are screened based on the screening coefficient to obtain a set of thermal state characteristics, including: obtaining a parameter change sequence and a speed change sequence based on multiple thermal state parameters and corresponding sintering speeds in the target time window, and the parameter change sequence and the speed change sequence are arranged based on a time series; calculating the screening coefficient corresponding to each item of the parameter change sequence and the speed change sequence, and filtering the set of thermal state characteristics from the parameter change sequence and the speed change sequence based on the screening coefficient.

[0007] In one embodiment of the present application, the set of thermal state features is spliced ​​based on time series to obtain a thermal state feature matrix, and the thermal state feature matrix is ​​fused based on time series based on a preset convolutional neural network to obtain a fused feature matrix, including: splicing the set of thermal state features based on time series to obtain a thermal state feature matrix, the number of rows of the thermal state feature matrix is ​​the number of the thermal state features, and the number of columns of the thermal state feature matrix is ​​the size of the target time window; inputting the thermal state feature matrix into a preset convolutional neural network to fuse the feature matrix, the number of rows of the fused feature matrix is ​​the number of the fused features, the number of columns of the fused feature matrix is ​​the size of the target time window, and the fused features include parameter features and speed features.

[0008] In one embodiment of the present application, before the fused feature matrix is ​​input into a preset sintering endpoint control model to obtain the sintering speed adjustment amount, it also includes: acquiring sintering history data, extracting multiple thermal state parameters and corresponding sintering speeds of multiple historical time windows based on the sintering history data; obtaining a corresponding fused feature matrix based on the multiple thermal state parameters and corresponding sintering speeds of each historical time window; using the fused feature matrix as a training data set, using the sintering speed corresponding to each row of the fused feature matrix as a training label, and inputting the training data set and training labels into a preset model for training to obtain a sintering endpoint control model.

[0009] In one embodiment of the present application, the sintering endpoint control method also includes: at every preset update time, re-extracting multiple historical time windows based on the sintering historical data, and obtaining a corresponding fusion feature matrix based on multiple thermal state parameters and corresponding sintering speeds in each historical time window; training the sintering endpoint control model according to the fusion feature matrix corresponding to the historical time window to update the sintering endpoint control model.

[0010] In one embodiment of the present application, extracting multiple thermal state parameters and corresponding sintering speeds of a target time window based on the sintering operation data includes: detecting a mutation time point from the sintering operation data based on a differential method, the mutation time point being a time point when a change in the sintering speed exceeds a preset change; determining a target time window based on the mutation time point, and extracting multiple thermal state parameters and corresponding sintering speeds of the target time window.

[0011] An embodiment of the present application also provides a sintering endpoint control system, the system comprising a data acquisition module, an intelligent algorithm module and an industrial control module; the data acquisition module comprises multiple sensors, a data acquisition unit and a data transmission unit, the sensors are used to collect thermal state parameters during the sintering operation, the data acquisition unit is used to connect and receive and store the thermal state parameters collected by each sensor, and the data transmission unit is used to transmit the thermal state parameters to the intelligent algorithm module; the intelligent algorithm module is used to input the thermal state parameters into a sintering endpoint control model to obtain a sintering speed adjustment amount, and send the sintering speed adjustment amount to the industrial control module; the industrial control module is used to train and update the sintering endpoint control model in the intelligent algorithm module, and is also used to control the current sintering speed during the sintering operation based on the sintering speed adjustment amount to control the sintering endpoint.

[0012] An embodiment of the present application also provides a sintering endpoint control device, which includes: a data input module, used to obtain sintering operation data, and extract multiple thermal state parameters and corresponding sintering speeds in a target time window based on the sintering operation data; a coefficient calculation module, used to obtain a screening coefficient according to the change in the thermal state parameters and the change in the sintering speed in the target time window, and screen the thermal state parameters based on the screening coefficient to obtain a set of thermal state features; a feature fusion module, used to splice the set of thermal state features based on time series to obtain a thermal state feature matrix, and fuse the thermal state feature matrix based on time series based on a preset convolutional neural network to obtain a fused feature matrix; a model training module, used to input the fused feature matrix into a preset sintering endpoint control model to obtain a sintering speed adjustment amount, and adjust the current sintering speed based on the sintering speed adjustment amount to control the sintering endpoint.

[0013] An embodiment of the present application provides an electronic device, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the electronic device implements the sintering endpoint control method described in any one of the above embodiments.

[0014] An embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor of a computer, the computer is enabled to execute the sintering endpoint control method as described in any one of the above embodiments.

[0015] Beneficial effects of the present application: The embodiments of the present application provide a sintering endpoint control method, system, device, electronic device and storage medium, the method comprising acquiring sintering operation data, extracting multiple thermal state parameters and corresponding sintering speeds of a target time window based on the sintering operation data, obtaining a screening coefficient according to the change in the thermal state parameters and the change in the sintering speed of the target time window, screening the thermal state parameters based on the screening coefficient to obtain a set of thermal state characteristics, splicing the set of thermal state characteristics based on time series to obtain a thermal state characteristic matrix, fusing the thermal state characteristic matrix based on time series based on a preset convolutional neural network to obtain a fused characteristic matrix, inputting the fused characteristic matrix into a preset sintering endpoint control model to obtain a sintering speed adjustment amount, adjusting the current sintering speed based on the sintering speed adjustment amount to control the sintering endpoint, screening out thermal state characteristics with a higher correlation coefficient through this method, and fusing the thermal state characteristics based on time series, thereby obtaining a sintering speed adjustment amount based on the fused characteristic matrix, so as to control the sintering speed based on the current working conditions, thereby controlling the sintering endpoint within a stable range.

[0016] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is a schematic diagram of an implementation environment of a sintering endpoint control method shown in an exemplary embodiment of the present application;

[0018] Figure 2 is a flow chart of a sintering endpoint control method shown in an exemplary embodiment of the present application;

[0019] Figure 3 is a flow chart of intelligent control of sintering endpoint shown in an exemplary embodiment of the present application;

[0020] Figure 4 is a schematic diagram of sintering endpoint control model training shown in an exemplary embodiment of the present application;

[0021] Figure 5 is a block diagram of a sintering endpoint control device shown in an exemplary embodiment of the present application;

[0022] Figure 6 It is a structural schematic diagram of an electronic device shown in an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0023] The following describes the embodiments of the present application through specific examples, and those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. The present application can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0024] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present application, and thus the drawings only show components related to the present application rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed at will, and the component layout may also be more complicated.

[0025] It should be noted that in this application, "first", "second", etc. are only used to distinguish similar objects, and are not used to limit the order or precedence of similar objects. The variations of "including", "having", etc. described above indicate that the scope covered by the subject of the word is not exclusive except for the examples shown by the word.

[0026] It is understood that the various numbers, step numbers, and other reference numerals recorded in this application are distinguished for the convenience of description and are not intended to limit the scope of this application. The size of the reference numerals in this application does not mean the order of execution. The execution order of each process should be determined by its function and internal logic.

[0027] In the following description, a large number of details are discussed to provide a more thorough explanation of the embodiments of the present application. However, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of the present application difficult to understand.

[0028] The embodiments of the present application respectively provide a sintering endpoint control method, a sintering endpoint control device, an electronic device, a computer-readable storage medium, and a computer program product, which will be described in detail below.

[0029] See also Figure 1 , Figure 1 It is a schematic diagram of an implementation environment of a sintering endpoint control method shown as an exemplary embodiment of the present application.

[0030] like Figure 1As shown, the implementation environment may include a data acquisition module 101, an intelligent algorithm module 102 and an industrial control module 103, wherein the data acquisition module 101 includes a plurality of sensors, a data acquisition unit, a data transmission unit and a controller or processor, wherein the sensor is used to measure and detect various physical quantities or environmental parameters in the working condition, the data acquisition unit is used to connect and receive the data generated by the sensor, and the data acquisition unit may be a dedicated data acquisition card, a data acquisition device or an embedded device, which is responsible for converting the analog signal of the sensor into a digital signal, and performing data acquisition and storage. The data transmission unit is used to transmit the collected data to the intelligent algorithm module at the back end for processing, and common data transmission units include wired connections (such as Ethernet or serial ports), wireless connections (such as Wi-Fi, Bluetooth or Zigbee) or mobile networks (such as 2G / 3G / 4G / 5G). The controller or processor is the core control unit of the data acquisition module 101, which is responsible for controlling the data acquisition module 101 to perform data acquisition, data transmission and data storage. The controller may be a microprocessor, a microcontroller, a single-chip microcomputer or an embedded system, such as a PLC or DCS.

[0031] In one embodiment of the present application, the data acquisition module 101 further includes a storage device and a power management unit. The storage device is used to store the collected data. The storage device may be a solid-state memory (such as a flash memory, an SD card, or a solid-state hard disk), a hard disk drive, or a cloud storage service, etc. The power management unit is used to provide a stable power supply for the data acquisition module 101, and may include a battery, a power adapter, a power management chip, etc., to ensure the normal operation of the data acquisition module.

[0032] In one embodiment of the present application, a sintering endpoint control model is built into the intelligent algorithm module 102, which is used to process the collected thermal state parameters to obtain a fusion feature matrix and input it into the model to obtain a sintering speed adjustment amount.

[0033] See also Figure 3 , Figure 3It is a sintering endpoint intelligent control flow chart shown in an exemplary embodiment of the present application. In one embodiment of the present application, the sintering endpoint intelligent control process in the intelligent algorithm module 102 includes: extracting data corresponding to the moment when the sintering machine speed is adjusted from the sintering history data, constructing a sintering machine speed adjustment sample set based on the extracted data, determining a time window, and counting the changes of each thermal state parameter in the sintering machine speed adjustment sample set in the time window, calculating the Pearson correlation coefficient between the changes of each thermal state parameter in the time window and the sintering machine speed adjustment amount, screening out thermal state features with high correlation coefficients, constructing a two-dimensional convolutional neural network, fusing the information of the thermal state features from the time and feature space dimensions to obtain thermal state feature fusion information, and establishing a mapping relationship between the thermal state feature fusion information and the sintering machine speed adjustment amount, thereby controlling the sintering machine speed based on the mapping relationship.

[0034] In one embodiment of the present application, the industrial control module 103 includes a back-end unit and a front-end unit, wherein the back-end unit is used to manage the sintering endpoint control model in the intelligent algorithm module 102, control model training, model optimization, anomaly detection and fault handling, and adjust the current sintering speed based on the sintering speed adjustment amount obtained by the model. The front-end unit is used to display a user interface to the user, and is used to display visual information of data analysis results and model predictions, mainly including data visualization, real-time monitoring, reports and statistics, user interaction, alarms and warnings, etc.

[0035] In one embodiment of the present application, the implementation environment also includes a data service module, which is used to uniformly manage the collected data. It can be managed using a relational database (such as MySQL or Oracle) or a non-relational database (such as MongoDB or Redis), etc., and is selected according to specific data storage and query requirements. The data service module also provides a load balancer for balancing the request load of the data service module, ensuring load balancing of each server and service, and improving the performance and reliability of the system.

[0036] In one embodiment of the present application, a sintering endpoint control system includes a data acquisition module, an intelligent algorithm module and an industrial control module; the data acquisition module includes multiple sensors, a data acquisition unit and a data transmission unit, the sensor is used to collect thermal state parameters during the sintering operation, the data acquisition unit is used to connect and receive and store the thermal state parameters collected by each sensor, and the data transmission unit is used to transmit the thermal state parameters to the intelligent algorithm module; the intelligent algorithm module is used to input the thermal state parameters into the sintering endpoint control model, obtain the sintering speed adjustment amount, and send the sintering speed adjustment amount to the industrial control module; the industrial control module is used to train and update the sintering endpoint control model in the intelligent algorithm module, and is also used to control the current sintering speed during the sintering operation based on the sintering speed adjustment amount to control the sintering endpoint.

[0037] See also Figure 2 , Figure 2 is a flow chart of a sintering endpoint control method shown in an exemplary embodiment of the present application. The method can be applied to Figure 1 The implementation environment shown is as follows. The method may also be applicable to other exemplary implementation environments and be specifically executed by devices in other implementation environments. This embodiment does not limit the implementation environment to which the method is applicable.

[0038] like Figure 2 As shown, in an exemplary embodiment, the sintering endpoint control method includes at least steps S210 to S240, which are described in detail as follows:

[0039] Step S210, acquiring sintering operation data, and extracting a plurality of thermal state parameters and corresponding sintering speeds in a target time window based on the sintering operation data.

[0040] In one embodiment of the present application, extracting multiple thermal state parameters and corresponding sintering speeds of a target time window based on sintering operation data includes: detecting a mutation time point from the sintering operation data based on a differential method, the mutation time point being a time point when a change in the sintering speed exceeds a preset change; determining a target time window at the mutation time point, and extracting multiple thermal state parameters and corresponding sintering speeds of the target time window.

[0041] In one embodiment of the present application, the operating data of the sintering machine is obtained as the sintering operating data, including thermal state parameters such as the sintering speed and the exhaust temperature of each wind box of the sintering machine, the large flue temperature, the sintering temperature rising point and the sintering temperature inflection point.

[0042] In one embodiment of the present application, in order to obtain the sudden change time point of the sintering speed, the difference method is used to calculate the difference between adjacent data points of the sintering speed timing signal in the time dimension to detect the sudden change time point. When the change in the sintering speed at a certain time point exceeds the time point of the preset change, it is considered that the sintering speed at this time point has been adjusted, that is, this time point is used as the sudden change time point.

[0043] Step S220, obtaining a screening coefficient according to the variation of the thermal state parameters and the variation of the sintering speed in the target time window, and screening the thermal state parameters based on the screening coefficient to obtain a set of thermal state characteristics.

[0044] In one embodiment of the present application, a screening coefficient is obtained according to the change in the thermal state parameters and the change in the sintering speed in the target time window, and the thermal state parameters are screened based on the screening coefficient to obtain a set of thermal state characteristics, including: obtaining a parameter change sequence and a speed change sequence based on multiple thermal state parameters and corresponding sintering speeds in the target time window, and the parameter change sequence and the speed change sequence are arranged based on a time series; calculating the screening coefficient corresponding to each item in the parameter change sequence and the speed change sequence, and filtering out a set of thermal state characteristics from the parameter change sequence and the speed change sequence based on the screening coefficient.

[0045] In one embodiment of the present application, the target time window is set to w, and the change amount of the thermal state parameter and the change amount of the sintering speed within the time range of the mutation time point t and tw are calculated respectively. The screening coefficients of the change amount of each thermal state parameter within the target time window w and the change amount of the sintering speed are calculated respectively. In this embodiment, the screening coefficient is the Pearson correlation coefficient. The calculation method is as follows:

[0046]

[0047] In formula (1), r represents the screening coefficient, X represents the parameter change sequence within the target time window w, and Y represents the speed change sequence within the target time window w.

[0048] Assume that the set R = {|r1|,|r2|,...,|r n |}, where r i The Pearson correlation coefficient corresponding to the i-th item in the parameter change sequence and the speed change sequence within the target time window w is represented. Based on the Pearson correlation coefficient, the first m (m<n) thermal state parameters in the R set are screened out as the set of thermal state features.

[0049] Step S230, splicing the set of thermal state features based on time series to obtain a thermal state feature matrix, and fusing the thermal state feature matrix based on time series based on a preset convolutional neural network to obtain a fused feature matrix.

[0050] In one embodiment of the present application, a set of thermal state features is spliced ​​based on time series to obtain a thermal state feature matrix, and the thermal state feature matrix is ​​fused based on time series based on a preset convolutional neural network to obtain a fused feature matrix, including: splicing a set of thermal state features based on time series to obtain a thermal state feature matrix, the number of rows of the thermal state feature matrix is ​​the number of thermal state features, and the number of columns of the thermal state feature matrix is ​​the size of a target time window; the thermal state feature matrix is ​​input into a preset convolutional neural network to fuse the feature matrix, the number of rows of the fused feature matrix is ​​the number of fused features, the number of columns of the fused feature matrix is ​​the size of the target time window, and the fused features include parameter features and speed features.

[0051] In one embodiment of the present application, the time series signals of each thermal state feature are spliced ​​in the time dimension. Assuming that the number of features in the set of thermal state features is C, the window size of the time dimension is T, and the size of the thermal state feature matrix after feature splicing is C×T. The spliced ​​thermal state feature matrix is ​​fully fused from the time and feature dimensions through a preset two-dimensional convolutional neural network model. For the preset two-dimensional convolutional neural network, the input is the thermal state feature matrix X, the preset parameter matrix W of the convolution kernel, and the fused feature Y after fusion, which is as follows:

[0052]

[0053] In formula (2), X is a thermal state feature matrix with a shape of (C, T), whose feature dimension is C and time dimension is T, W is a preset parameter matrix with a convolution kernel with a shape of (k, k), i is the index of the feature dimension, and j is the index of the time dimension.

[0054] In one embodiment of the present application, the fused features are passed through a fully connected network or other regression network model to establish a mapping relationship between the fused features and the sintering speed adjustment amount.

[0055] See also Figure 4 , Figure 4 is a schematic diagram of sintering endpoint control model training shown in an exemplary embodiment of the present application, such as Figure 4 As shown, the thermal state characteristics including the sintering machine speed setting value, the sintering temperature rise point and the large flue temperature are fused based on a two-dimensional convolutional neural network and input into the preset model to obtain the sintering speed adjustment amount.

[0056] Step S240, inputting the fused feature matrix into a preset sintering endpoint control model to obtain a sintering speed adjustment amount, and adjusting the current sintering speed based on the sintering speed adjustment amount to control the sintering endpoint.

[0057] In one embodiment of the present application, before the fused feature matrix is ​​input into the preset sintering endpoint control model to obtain the sintering speed adjustment amount, it also includes: acquiring sintering history data, extracting multiple thermal state parameters and corresponding sintering speeds of multiple historical time windows based on the sintering history data; obtaining a corresponding fused feature matrix based on the multiple thermal state parameters and corresponding sintering speeds of each historical time window; using the fused feature matrix as a training data set, using the sintering speed corresponding to each row of the fused feature matrix as a training label, inputting the training data set and the training label into the preset model for training, and obtaining the sintering endpoint control model.

[0058] In one embodiment of the present application, the sintering endpoint control method also includes: at every preset update time, re-extracting multiple historical time windows based on the sintering historical data, and obtaining a corresponding fusion feature matrix based on multiple thermal state parameters and corresponding sintering speeds in each historical time window; training the sintering endpoint control model according to the fusion feature matrix corresponding to the historical time window to update the sintering endpoint control model.

[0059] In one embodiment of the present application, the sintering endpoint control model is initialized and trained using sintering historical data, and an update time window for model update is defined. A fixed-size time window is selected as the update time window to determine the online regular update time of the sintering endpoint control model. The update time window is set according to the actual production situation of the sintering machine. In this embodiment, due to fluctuations in sintering raw materials, changes in material layer thickness, etc., the update time window needs to be determined in combination with the actual production situation.

[0060] In one embodiment of the present application, when the update time window arrives, the sintering history data within the most recent historical time window is selected from the database to retrain the model. The retrained model can use online learning technology, such as incremental learning or incremental learning, to gradually adapt to the data analysis rules of the new working conditions.

[0061] See also Figure 5 , Figure 5 is a block diagram of a sintering endpoint control device shown in an exemplary embodiment of the present application. The device can be applied to Figure 1 The implementation environment shown is as follows. The device may also be applicable to other exemplary implementation environments and specifically configured in other devices. This embodiment does not limit the implementation environment to which the device is applicable.

[0062] like Figure 5 As shown, the exemplary sintering endpoint control device includes:

[0063] The data input module 501 is used to obtain sintering operation data, and extract multiple thermal state parameters and corresponding sintering speeds in a target time window based on the sintering operation data;

[0064] A coefficient calculation module 502 is used to obtain a screening coefficient according to the change amount of the thermal state parameter and the change amount of the sintering speed in the target time window, and to screen the thermal state parameter based on the screening coefficient to obtain a set of thermal state characteristics;

[0065] A feature fusion module 503 is used to splice the set of thermal state features based on time series to obtain a thermal state feature matrix, and to fuse the thermal state feature matrix based on time series based on a preset convolutional neural network to obtain a fused feature matrix;

[0066] The model training module 504 is used to train the preset model based on the fusion feature matrix to obtain a sintering endpoint control model. The input of the sintering endpoint control model is the thermal state parameter, and the output of the sintering endpoint control model is used as the sintering speed adjustment amount to control the sintering endpoint according to the sintering speed adjustment amount.

[0067] Figure 6 The structure diagram of the computer system suitable for implementing the electronic device of the embodiment of the present application is shown. It should be noted that: Figure 6 The computer system 600 of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0068] like Figure 6 As shown, the computer system 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 602 or the program loaded from the storage part 608 to the random access memory (RAM) 603, such as executing the method described in the above embodiment. In the RAM 603, various programs and data required for system operation are also stored. The CPU 601, ROM 602 and RAM 603 are connected to each other through a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0069] The following components are connected to the I / O interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed so that a computer program read therefrom is installed into the storage section 608 as needed.

[0070] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication section 609, and / or installed from a removable medium 611. When the computer program is executed by a central processing unit (CPU) 601, various functions defined in the system of the present application are executed.

[0071] It should be noted that the computer-readable medium shown in the embodiment of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a computer-readable computer program is carried. This propagated data signal can take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. A computer program contained on a computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0072] The flowchart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present application. Wherein, each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0073] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. The names of these units do not, in some cases, constitute limitations on the units themselves.

[0074] Another aspect of the present application further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor of a computer, the computer executes the sintering endpoint control method as described above. The computer-readable storage medium may be included in the electronic device described in the above embodiment, or may exist independently without being assembled into the electronic device.

[0075] Another aspect of the present application also provides a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the sintering endpoint control method provided in each of the above embodiments.

[0076] The above embodiments are merely illustrative of the principles and effects of the present application, and are not intended to limit the present application. Anyone familiar with the technology may modify or alter the above embodiments without violating the spirit and scope of the present application.

Claims

1. A sintering endpoint control method, characterized in that: The sintering endpoint control method comprises: Acquire sintering operation data, and extract multiple thermal state parameters and corresponding sintering speeds in a target time window based on the sintering operation data; Obtaining a screening coefficient according to a change amount of the thermal state parameter and a change amount of the sintering speed in a target time window, and screening the thermal state parameter based on the screening coefficient to obtain a set of thermal state characteristics; The set of thermal state features is spliced ​​based on time series to obtain a thermal state feature matrix, and the thermal state feature matrix is ​​fused based on time series based on a preset convolutional neural network to obtain a fused feature matrix; The fused feature matrix is ​​input into a preset sintering endpoint control model to obtain a sintering speed adjustment amount, and the current sintering speed is adjusted based on the sintering speed adjustment amount to control the sintering endpoint.

2. The sintering endpoint control method according to claim 1, characterized in that: The screening coefficient is obtained according to the change amount of the thermal state parameter and the change amount of the sintering speed in the target time window, and the set of thermal state characteristics obtained by screening the thermal state parameter based on the screening coefficient includes: Based on the multiple thermal state parameters of the target time window and the corresponding sintering speeds, a parameter change sequence and a speed change sequence are obtained, wherein the parameter change sequence and the speed change sequence are arranged based on a time series; The screening coefficient corresponding to each item of the parameter change sequence and the speed change sequence is calculated, and the set of thermal state characteristics is screened out from the parameter change sequence and the speed change sequence based on the screening coefficient.

3. The sintering endpoint control method according to claim 1, characterized in that: The set of thermal state features is spliced ​​based on time series to obtain a thermal state feature matrix, and the thermal state feature matrix is ​​fused based on time series based on a preset convolutional neural network to obtain a fused feature matrix, including: splicing the set of thermal state features based on time series to obtain a thermal state feature matrix, wherein the number of rows of the thermal state feature matrix is ​​the number of thermal state features, and the number of columns of the thermal state feature matrix is ​​the size of the target time window; The thermal state feature matrix is ​​input into a preset convolutional neural network to fuse the feature matrix, the number of rows of the fused feature matrix is ​​the number of the fused features, the number of columns of the fused feature matrix is ​​the size of the target time window, and the fused features include parameter features and speed features.

4. The sintering endpoint control method according to any one of claims 1 to 3, characterized in that: Before inputting the fused feature matrix into a preset sintering endpoint control model to obtain the sintering speed adjustment amount, the method further includes: Acquire sintering history data, and extract multiple thermal state parameters and corresponding sintering speeds in multiple historical time windows based on the sintering history data; A corresponding fusion feature matrix is ​​obtained based on multiple thermal state parameters and corresponding sintering speeds in each historical time window; The fused feature matrix of multiple historical time windows is used as a training data set, the change in sintering speed corresponding to each historical time window is used as a training label, and the training data set and training labels are input into a preset model for training to obtain a sintering endpoint control model.

5. The sintering endpoint control method according to claim 4, characterized in that: The sintering endpoint control method further comprises: At every preset update time, a plurality of historical time windows are extracted again based on the sintering historical data, and a corresponding fusion feature matrix is ​​obtained based on a plurality of thermal state parameters and a corresponding sintering speed in each historical time window; The sintering endpoint control model is trained according to the fusion feature matrix corresponding to the historical time window to update the sintering endpoint control model.

6. The sintering endpoint control method according to any one of claims 1 to 3, characterized in that: A plurality of thermal state parameters and corresponding sintering speeds of a target time window extracted based on the sintering operation data include: Detecting a mutation time point from the sintering operation data based on a differential method, wherein the mutation time point is a time point when a change in the sintering speed exceeds a preset change; A target time window is determined according to the mutation time point, and a plurality of thermal state parameters and corresponding sintering speeds of the target time window are extracted.

7. A sintering endpoint control system, characterized in that: The sintering endpoint control system includes a data acquisition module, an intelligent algorithm module and an industrial control module; The data acquisition module includes a plurality of sensors, a data acquisition unit and a data transmission unit. The sensors are used to collect thermal state parameters during the sintering operation. The data acquisition unit is used to connect and receive the thermal state parameters collected by each sensor and store them. The data transmission unit is used to transmit the thermal state parameters to the intelligent algorithm module. The intelligent algorithm module is used to input the thermal state parameters into the sintering endpoint control model to obtain the sintering speed adjustment amount, and send the sintering speed adjustment amount to the industrial control module; The industrial control module is used to train and update the sintering endpoint control model in the intelligent algorithm module, and is also used to control the current sintering speed during the sintering operation based on the sintering speed adjustment amount to control the sintering endpoint.

8. A sintering endpoint control device, characterized in that: The sintering endpoint control device comprises: A data input module, used to obtain sintering operation data, and extract a plurality of thermal state parameters and corresponding sintering speeds in a target time window based on the sintering operation data; A coefficient calculation module, used to obtain a screening coefficient according to the change amount of the thermal state parameter and the change amount of the sintering speed in the target time window, and to screen the thermal state parameter based on the screening coefficient to obtain a set of thermal state characteristics; A feature fusion module, used for splicing the set of thermal state features based on time series to obtain a thermal state feature matrix, and fusing the thermal state feature matrix based on time series based on a preset convolutional neural network to obtain a fused feature matrix; The model training module is used to input the fusion feature matrix into a preset sintering endpoint control model to obtain a sintering speed adjustment amount, and adjust the current sintering speed based on the sintering speed adjustment amount to control the sintering endpoint.

9. An electronic device, characterized in that: The electronic device comprises: one or more processors; A storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, enables the electronic device to implement the sintering endpoint control method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor of a computer, the computer is caused to execute the sintering endpoint control method according to any one of claims 1 to 7.

Images