Sintering furnace temperature feedforward compensation method and system thereof

Abstract

The present application belongs to the technical field of industrial heat treatment, and particularly relates to a sintering furnace temperature feedforward compensation method and system. The method comprises: obtaining three-dimensional space coordinates of each heating element and three-dimensional space coordinates of each temperature measuring point; constructing an influence matrix according to the three-dimensional space coordinates of all the heating elements and the three-dimensional space coordinates of all the temperature measuring points; combining the influence matrix, predicting the temperature of each temperature measuring point according to the power of each heating element and the corresponding ambient temperature to obtain a predicted temperature; obtaining the predicted temperature, combining a target temperature to calculate a temperature deviation; and based on the influence matrix and the temperature deviation, combining a regularized least square to solve the required power compensation amount. The present application can realize lightweight calculation, support real-time operation at the edge, is easy to implement, and has low implementation cost.

Description

Technical Field

[0001] This invention belongs to the field of industrial heat treatment technology, specifically relating to a sintering furnace temperature feedforward compensation method and system. Background Technology

[0002] In the field of new energy materials, the sintering process is a crucial step in the preparation of materials such as lithium-ion battery cathode materials and solid electrolytes, determining their final performance. The uniformity of temperature distribution within the sintering furnace has a vital impact on material properties, specifically in the following aspects:

[0003] First, regarding the crystal structure of the material, uneven temperature distribution within the sintering furnace can lead to inconsistent grain sizes, negatively impacting the material's electrochemical performance. Second, from a batch consistency perspective, products at different locations within the furnace will exhibit varying performance due to temperature differences, potentially resulting in over- or under-sintering in localized areas, ultimately leading to scrap and affecting overall production quality and efficiency. Third, in terms of energy consumption, ensuring the lowest possible temperature point within the sintering furnace meets the acceptable standard typically requires raising the overall sintering temperature, undoubtedly resulting in significant energy waste.

[0004] Currently, traditional sintering furnaces generally employ zoned PID control, where each temperature zone is independently controlled. However, due to various factors, this control method struggles to maintain a uniform temperature distribution within the furnace. Specifically, heat dissipation is a significant factor; the furnace head and tail, being closer to the external environment, experience faster heat dissipation, resulting in relatively lower temperatures in these areas. Simultaneously, heat conduction coupling exacerbates temperature unevenness, similarly causing lower temperatures at the furnace head and tail. Furthermore, as equipment age, degradation of insulation performance and heating element efficiency leads to changes in the furnace's temperature characteristics. Additionally, variations in operating conditions cannot be ignored; fluctuations in ambient temperature, differences in load, and changes in atmosphere flow rate all affect the temperature distribution within the sintering furnace. Therefore, improving the uniformity of temperature distribution within the sintering furnace has become a critical issue urgently needing resolution in the field of new energy material preparation.

[0005] To address the aforementioned technical issues, patent publication number CN120576594A discloses a sintering furnace temperature control method based on a BP neural network prediction model. This method constructs an initial model based on an Adaboost-based BP neural network, trains the Adaboost-based BP neural network using experimental data to obtain a prediction model, and predicts and adjusts the heating power required by the sintering furnace in real time based on the sintering temperature curve of the desired sintering target. This results in a more timely and linear heating process with stronger anti-interference capabilities, further improving the stability of sintered products and reducing the product defect rate. However, this method requires a large amount of experimental data to train the neural network and involves complex calculations or relies on offline modeling, making it difficult to run in real time at edge devices.

[0006] For example, patent publication number CN121326061A discloses a temperature uniformity control system for a well-type furnace. In this system, a thermal field perspective module acquires the three-dimensional temperature distribution within the furnace in real time through multispectral imaging and physical field inversion. A thermal field reconstruction module integrates distributed variable emissivity wall units and directional micro-area energy injection units, used for macroscopically guiding thermal radiation flow and microscopically compensating for internal hot spots, respectively. An adaptive reconstruction controller performs online self-calibration of a high-precision physical field model and generates coordinated control commands for the two execution units based on model predictive control, achieving physical reconstruction of the thermal field. Through a tight closed loop of perception, decision-making, and execution, proactive, precise, and adaptive control of the temperature field is achieved, significantly improving the temperature uniformity, control response speed, and process adaptability of heat treatment. However, this method requires specialized optical equipment such as multispectral imaging, resulting in high implementation costs, and the complex multispectral inversion calculations make it difficult to operate at edge processing levels. Summary of the Invention

[0007] The purpose of this invention is to overcome the shortcomings of existing technologies, such as computational complexity, inability to run at the edge, and high implementation cost, and to provide a sintering furnace temperature feedforward compensation method and system that can achieve lightweight calculation, support real-time operation at the edge, is easy to implement, and has low implementation cost.

[0008] The technical solution adopted by this invention to solve its technical problem is: a sintering furnace temperature feedforward compensation method, the method comprising the following steps:

[0009] S1, obtain the three-dimensional spatial coordinates of each heating element and the three-dimensional spatial coordinates of each temperature measuring point respectively;

[0010] S2, construct an influence matrix based on the three-dimensional spatial coordinates of all the heating elements and the three-dimensional spatial coordinates of all the temperature measuring points. ;

[0011] S3, Combining the influence matrix, predict the temperature of each temperature measuring point based on the current power of each heating element and the corresponding ambient temperature, and obtain the predicted temperature. ;

[0012] S4, Obtain the predicted temperature and calculate the temperature deviation based on the target temperature. ;

[0013] S5, based on the influence matrix and temperature deviation, combines regularized least squares to solve for the required power compensation. .

[0014] Furthermore, specifically, the method further includes:

[0015] Step S6: Determine if there is actual running data at present;

[0016] If not, the power compensation amount is output directly, and signal control is performed based on the power compensation amount;

[0017] If so, the influence matrix is ​​calibrated online based on the actual operating data, and the process returns to step S3.

[0018] Furthermore, specifically, step S2 includes the following steps:

[0019] Based on the three-dimensional spatial coordinates of the heating element and the three-dimensional spatial coordinates of the temperature measuring point, calculate the Euclidean distance between the j-th heating element and the i-th temperature measuring point. ;

[0020] By using the distance exponential decay function, combined with the Euclidean distance Calculate the influence coefficient of each heating element on each temperature measuring point. ;

[0021] The influence matrix is ​​then subjected to column normalization. More specifically, step S5 includes the following steps:

[0022] Power compensation quantity is established based on the influence matrix. Temperature deviation The linear relationship is expressed as follows:

[0023]

[0024] The power compensation amount is solved using regularized least squares. The objective function is:

[0025]

[0026] Calculate the power compensation amount

[0027] in, The regularization coefficient is . , It is an identity matrix.

[0028] Furthermore, specifically, the formula for calculating the predicted temperature is as follows:

[0029] ;

[0030] in, This represents the current power vector of each heating element. , The ambient temperature;

[0031] The formula for calculating the temperature deviation is:

[0032]

[0033] in, For the target temperature, This represents the current power of a heating element.

[0034] Furthermore, specifically, the formula for calculating the influence coefficient is as follows:

[0035] When the Euclidean distance When >0, , where λ is the characteristic attenuation length;

[0036] When the Euclidean distance When =0, .

[0037] Furthermore, specifically, the online calibration of the influence matrix based on the actual operating data includes the following steps:

[0038] Obtain K sets of actual operating data ,in, For heating power vector, For the measured temperature vector and This represents the ambient temperature vector.

[0039] The characteristic attenuation length parameter is calibrated based on the operational data, and the calibration formula is as follows:

[0040]

[0041] in, Let λ represent the influence matrix.

[0042] The influence coefficients are recalculated based on the calibrated characteristic attenuation length parameters, and the influence matrix is ​​updated.

[0043] A sintering furnace temperature feedforward compensation system, the system comprising:

[0044] Several heating elements and several thermocouples are installed inside the furnace body;

[0045] Solid-state relays are used to control the heating of the furnace body, with each heating element connected to the solid-state relay.

[0046] The PLC control module is connected to each of the thermocouples and solid-state relays to acquire temperature signals, as well as output PWM signals and control signals.

[0047] An edge computing module is connected to the PLC control module. The edge computing module is configured to execute the sintering furnace temperature feedforward compensation method as described above, and output the power compensation amount to the PLC control module so that the PLC control module controls the furnace body based on the power compensation amount.

[0048] A visual interaction module is connected to the PLC control module to display temperature distribution and compensation effect.

[0049] Furthermore, specifically, the edge computing module includes:

[0050] The data acquisition module collects the power and corresponding ambient temperature of each heating element;

[0051] The construction module constructs an influence matrix based on the three-dimensional spatial coordinates of all the heating elements and the three-dimensional spatial coordinates of all the temperature measuring points. ;

[0052] The temperature prediction module, in conjunction with the influence matrix, predicts the temperature at each temperature measurement point based on the current power of each heating element and the corresponding ambient temperature, thus obtaining the predicted temperature. ;

[0053] The compensation calculation module calculates the temperature deviation based on the target temperature. Based on the influence matrix and temperature deviation, the required power compensation is calculated using regularized least squares. ;

[0054] The online calibration module calibrates the model parameters based on actual operating data.

[0055] Furthermore, specifically, the edge computing module is connected to the PLC control module via the Modbus TCP protocol.

[0056] The beneficial effects of the sintering furnace temperature feedforward compensation method of the present invention are:

[0057] 1. This invention directly utilizes the three-dimensional coordinates of the heating element and the temperature measuring point to construct an influence matrix, enabling temperature compensation to be initiated without any historical training data, simulation data, or specialized optical equipment;

[0058] 2. Employing influence matrix and regularized least squares, the computational complexity is low, and inference can be completed in milliseconds on edge devices, significantly reducing deployment costs and meeting the needs of industrial real-time control;

[0059] 3. This invention incorporates three-dimensional coordinates as prior information into the model, and the influence matrix has a clear physical basis. After changing materials, only one parameter needs to be calibrated online to adapt it. It has good adaptability to different furnace structures and materials, wide applicability, and improves the model's generalization ability. Attached Figure Description

[0060] The present invention will now be described in further detail with reference to the accompanying drawings and specific embodiments.

[0061] Figure 1 This is a schematic diagram of the method flow of Embodiment 1 of the present invention;

[0062] Figure 2 This is a schematic diagram of the system structure of Embodiment 2 of the present invention;

[0063] Figure 3 This is a schematic diagram of the edge computing module structure in Embodiment 2 of the present invention;

[0064] Figure 4 This is a schematic diagram of the computer device structure according to Embodiment 3 of the present invention;

[0065] In the diagram, 20 is a heating element; 30 is a thermocouple; 40 is a solid-state relay; 50 is a PLC control module; 80 is a visualization interaction module; 90 is an edge computing module; 901 is a data acquisition module; 902 is a construction module; 903 is a temperature prediction module; 904 is a compensation calculation module; 905 is an online calibration module; 10 is a computer device; 1002 is a processor; 1004 is a memory; and 1006 is a transmission device. Detailed Implementation

[0066] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, illustrating only the basic structure of the invention, and therefore only show the components relevant to the invention.

[0067] Example 1:

[0068] This invention provides a sintering furnace temperature feedforward compensation method, such as... Figure 1 As shown, the method includes the following steps:

[0069] S1, obtain the three-dimensional spatial coordinates of each heating element and each temperature measuring point; further, by reading the equipment design drawings, the three-dimensional spatial coordinates of each heating element and each temperature measuring point will be measured and obtained, where the heating element position set H = {(x h1, y h1 , z h1 ), …, (x hn , y hn , z hn )}, where n is the number of heating elements, and the set of temperature measuring point locations S = {(x S1 , y S1 , z S1 ), …, (x Sm , y Sm , z Sm )}, where m is the number of temperature measuring points, and the upper limit of the rated power of each heating element is P. max，j .

[0070] S2, construct the influence matrix based on the three-dimensional spatial coordinates of all heating elements and the three-dimensional spatial coordinates of all temperature measuring points. The constructed influence matrix can initiate temperature compensation and proceed to the next step without requiring any historical training or simulation data.

[0071] S3, Combining the influence matrix, predict the temperature of each temperature measuring point based on the current power of each heating element and the corresponding ambient temperature, and obtain the predicted temperature. ;

[0072] S4, Obtain the predicted temperature and calculate the temperature deviation based on the target temperature. ;

[0073] S5, based on the influence matrix and temperature deviation, combines regularized least squares to solve for the required power compensation. In this embodiment, the method further includes:

[0074] Step S6: Determine if there is actual running data at present;

[0075] If not, the power compensation amount is output directly, and signal control is performed based on the power compensation amount;

[0076] If so, the influence matrix is ​​calibrated online based on the actual operating data, and the process returns to step S3.

[0077] In this embodiment, step S2 specifically includes the following steps:

[0078] S21, Calculate the Euclidean distance between the j-th heating element and the i-th temperature measuring point based on the three-dimensional spatial coordinates of the heating element and the three-dimensional spatial coordinates of the temperature measuring point. ;

[0079]

[0080] The proximity between the heating element and the temperature measuring point is quantified by using Euclidean distance, which facilitates the calculation of the influence coefficient in subsequent steps.

[0081] S22, using the distance exponential decay function combined with Euclidean distance Calculate the influence coefficient of each heating element on each temperature measuring point.

[0082] Furthermore, the formula for calculating the influence coefficient is as follows:

[0083] When Euclidean distance When >0, , where λ is the characteristic attenuation length;

[0084] When Euclidean distance When =0, .

[0085] It should be noted that, in the absence of historical data, the characteristic attenuation length λ is a preset empirical value. When historical data or actual operating data are available, the characteristic attenuation length λ can also be calibrated to improve the accuracy of the constructed influence matrix, thereby further improving the compensation accuracy.

[0086] S23, based on Influence coefficient Construct an influence matrix and perform column normalization on the influence matrix.

[0087] Specifically, divide all elements in each column by the sum of the elements in that column, so that the sum of each column is 1, to ensure energy conservation, i.e., express the formula:

[0088] .

[0089] In addition, in this embodiment, for cases with a large temperature range, the entire temperature range can be divided into multiple intervals: influence matrices can be established in the low temperature region, the medium temperature region, and the high temperature region respectively.

[0090] Select the corresponding influence matrix based on the current temperature range.

[0091] To improve the accuracy of the construction, linear interpolation is used to smooth the transition at the boundaries of each temperature range. This method can handle the nonlinear thermophysical property changes of the material.

[0092] In this embodiment, the formula for calculating the predicted temperature is:

[0093] ;

[0094] in, This represents the current power vector of each heating element. , The ambient temperature;

[0095] Furthermore, the formula for calculating temperature deviation is:

[0096]

[0097] in, Target temperature This represents the current power of a heating element.

[0098] Deviation indicates the temperature gap that needs to be filled inside the furnace; a positive value indicates that the temperature needs to be increased, and a negative value indicates that the temperature needs to be decreased.

[0099] In this embodiment, step S5 specifically includes the following steps:

[0100] S51, Establish power compensation amount based on influence matrix Temperature deviation The linear relationship is expressed as follows:

[0101]

[0102] S52, using regularized least squares to solve for the power compensation amount. The objective function is:

[0103]

[0104] in, To minimize the error between the predicted temperature change and the target deviation, This is a regularization term that penalizes excessive power adjustments to prevent overload of the heating element or system oscillation. This form is the standard form of Tikhonov regularization.

[0105] The power compensation amount is calculated by differentiating the above regularized least squares objective function and setting the derivative to zero.

[0106] in, It is the identity matrix. The regularization coefficient is . Furthermore, The smaller the value, the higher the fitting accuracy, but it may produce excessively large control inputs; The larger the value, the smoother the control, but this may sacrifice temperature uniformity. It is 0.01 to 0.1 times. The maximum eigenvalue needs to be determined based on the actual system debugging. value.

[0107] In this embodiment, step S6, directly outputting the power compensation amount and performing signal control based on the power compensation amount, includes: compensating the current power based on the power compensation amount, and the PLC control module performing signal control according to the compensated power. Further, the formula for calculating the compensated power is:

[0108] .

[0109] To ensure that the power of each heating element does not exceed the safe range, the compensated power is also limited, that is:

[0110] .

[0111] Online calibration of the influence matrix based on actual operational data includes the following steps:

[0112] Obtain K sets of actual operating data ,in, For heating power vector, For the measured temperature vector and This represents the ambient temperature vector.

[0113] The characteristic attenuation length parameter is calibrated based on the operational data, and the calibration formula is as follows:

[0114]

[0115] in, Represents the influence matrix λ;

[0116] The influence coefficients are recalculated based on the calibrated characteristic attenuation length parameters, and the influence matrix is ​​updated. With the characteristic attenuation length as the optimization target, the influence matrix is ​​adaptively calibrated using a small amount (e.g., 3-10 sets) of actual operating data, so as to minimize the error of the calculated power compensation.

[0117] It should be noted that the sintering furnace temperature feedforward compensation method of this invention can be applied to the following equipment:

[0118] Lithium-ion battery cathode material sintering furnace: used for the calcination process of cathode materials such as NCM (lithium nickel cobalt manganese oxide) and LFP (lithium iron phosphate), solving the problem of inconsistent grain size caused by uneven temperature distribution in multiple temperature zones.

[0119] Solid electrolyte sintering furnace: Used for the sintering process of solid electrolyte materials such as sulfides (e.g., LPSCl, LGPS) and oxides (e.g., LLZO, LATP), to meet their strict requirements for temperature uniformity and atmosphere control.

[0120] Continuous pusher kiln / roller kiln: a continuous sintering equipment used for large-scale production of new energy materials. In this embodiment, heat loss and thermal coupling effect in the furnace length direction can be compensated in real time to improve batch consistency.

[0121] Batch-type box furnace: A box sintering furnace used for research and development and small-batch production. This embodiment can quickly build a model without historical data, shortening the process development cycle.

[0122] The sintering furnace temperature feedforward compensation method of this invention can be used as an intelligent temperature control module for sintering equipment, integrated into new equipment, or added to existing equipment as a retrofit solution without replacing the original hardware.

[0123] In summary, this invention directly constructs an influence matrix using the three-dimensional coordinates of the heating element and the temperature measurement point, enabling temperature compensation to be initiated without any historical training data, simulation data, or dedicated optical equipment. Employing the influence matrix and regularized least squares, the computational complexity is low, allowing inference to be completed in milliseconds on edge devices, significantly reducing deployment costs and meeting the real-time control requirements of industry. Furthermore, by integrating three-dimensional coordinates as prior information into the model, the influence matrix has a clear physical basis. After changing materials, only one parameter needs to be calibrated online for adaptation, demonstrating good adaptability to different furnace structures and materials, broad applicability, and improved model generalization ability.

[0124] Example 2:

[0125] This invention also provides a sintering furnace temperature feedforward compensation system, such as... Figure 2 As shown, the system includes:

[0126] Several heating elements 20 and several thermocouples 30 are arranged inside the furnace body;

[0127] Solid-state relay 40, each heating element 20 is connected to solid-state relay 40 to control the heating of the furnace body;

[0128] PLC control module 50, each thermocouple 30 and solid-state relay 40 is connected to PLC control module 50 to acquire temperature signals, as well as PWM signals and control signals output;

[0129] An edge computing module 90 is connected to a PLC control module 50. The edge computing module 90 is configured to execute the sintering furnace temperature feedforward compensation method as described in any one of claims 1 to 7, and output the power compensation amount to the PLC control module 50, so that the PLC control module 50 controls the furnace body based on the power compensation amount.

[0130] The visualization interaction module 80 is connected to the PLC control module 50 to display the temperature distribution and compensation effect.

[0131] Edge computing module 90 includes:

[0132] The data acquisition module 901 collects the power and corresponding ambient temperature of each heating element 20;

[0133] Module 902 constructs an influence matrix based on the three-dimensional spatial coordinates of all heating elements 20 and the three-dimensional spatial coordinates of all temperature measuring points. ;

[0134] The temperature prediction module 903, in conjunction with the influence matrix, predicts the temperature at each temperature measurement point based on the current power of each heating element 20 and the corresponding ambient temperature, thus obtaining the predicted temperature. ;

[0135] Compensation calculation module 904 calculates temperature deviation in conjunction with the target temperature. Based on the influence matrix and temperature deviation, the required power compensation is calculated using regularized least squares. ;

[0136] The online calibration module 905 calibrates the model parameters based on actual operating data.

[0137] In this embodiment, all devices are powered by a uniform 24V DC or 220V AC power supply.

[0138] In this embodiment, the edge computing module 90 is connected to the PLC control module 50 via the Modbus TCP protocol, which improves the effectiveness and reliability of signal transmission and further enhances the accuracy of the compensation method.

[0139] In this embodiment, the edge computing module 90 is embedded hardware, such as an industrial control computer or a Raspberry Pi-level edge processing device or others, which reduces the implementation cost.

[0140] The foregoing Figure 1 The various variations and specific examples of the sintering furnace temperature feedforward compensation method in Embodiment 1 are also applicable to the sintering furnace temperature feedforward compensation device in this embodiment. Through the foregoing detailed description of the sintering furnace temperature feedforward compensation method, those skilled in the art can clearly understand the implementation method of the sintering furnace temperature feedforward compensation device in this embodiment. Therefore, for the sake of brevity, it will not be described in detail here.

[0141] Example 3:

[0142] This application provides a computer device including a processor and a memory. The memory stores at least one instruction or at least one program. The at least one instruction or at least one program is loaded and executed by the processor to implement a sintering furnace temperature feedforward compensation method as provided in the above method embodiments.

[0143] Figure 4 A schematic diagram of the hardware structure of an apparatus for implementing a sintering furnace temperature feedforward compensation method provided in the embodiments of this application is shown. The apparatus may constitute or include the device or system provided in the embodiments of this application. Figure 4 As shown, the computer device 10 may include one or more processors 1002 (the processor may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 1004 for storing data, and a transmission device 1006 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the I / O interface), a network interface, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 4 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, computer device 10 may also include... Figure 4 The more or fewer components shown, or having the same Figure 4 The different configurations shown.

[0144] It should be noted that the aforementioned one or more processors and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuit may be a single, independent processing module, or may be integrated, in whole or in part, into any other element within the computer device 10 (or mobile device). As involved in the embodiments of this application, the data processing circuit serves as a processor control mechanism (e.g., selection of a variable resistor termination path connected to an interface).

[0145] The memory 1004 can be used to store software programs and modules for application software, such as the program instructions / data storage device corresponding to a sintering furnace temperature feedforward compensation method in this embodiment of the application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory 1004, thereby implementing the aforementioned method. The memory 1004 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 1004 may further include memory remotely located relative to the processor, and these remote memories can be connected to the computer device 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0146] The transmission device 1006 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the computer device 10. In one example, the transmission device 1006 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 1006 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0147] The display may be, for example, a touchscreen liquid crystal display (LCD) that allows the user to interact with the user interface of the computer device 10 (or mobile device).

[0148] Example 4:

[0149] This application also provides a computer-readable storage medium, which can be located in a server to store at least one instruction or at least one program related to implementing a sintering furnace temperature feedforward compensation method in the method embodiment. The at least one instruction or the at least one program is loaded and executed by the processor to implement the sintering furnace temperature feedforward compensation method provided in the above method embodiment.

[0150] Optionally, in this embodiment, the storage medium may be located at at least one of the multiple network servers in a computer network. Optionally, in this embodiment, the storage medium may include, but is not limited to, various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0151] Example 5:

[0152] This invention also provides a computer program product or 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 executes the computer instructions, causing the computer device to perform a sintering furnace temperature feedforward compensation method provided in the various optional embodiments described above.

[0153] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims can be performed in a different order than that shown in the embodiments and still achieve the desired results. Additionally, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are also possible or may be advantageous.

[0154] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the device, equipment, and storage medium embodiments are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0155] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0156] Based on the above-described preferred embodiments of the present invention, and through the foregoing description, those skilled in the art can make various changes and modifications without departing from the inventive concept. The technical scope of this invention is not limited to the contents of the specification, but must be determined according to the scope of the claims.

Claims

1. A method for sintering furnace temperature feedforward compensation, characterized in that, The method includes the following steps: S1, obtain the three-dimensional spatial coordinates of each heating element and the three-dimensional spatial coordinates of each temperature measuring point respectively; S2, construct an influence matrix based on the three-dimensional spatial coordinates of all the heating elements and the three-dimensional spatial coordinates of all the temperature measuring points. ; S3, Combining the influence matrix, predict the temperature of each temperature measuring point based on the current power of each heating element and the corresponding ambient temperature, and obtain the predicted temperature. ; S4, Obtain the predicted temperature and calculate the temperature deviation based on the target temperature. ; S5, based on the influence matrix and temperature deviation, combines regularized least squares to solve for the required power compensation. .

2. The sintering furnace temperature feedforward compensation method according to claim 1, characterized in that, The method further includes: Step S6: Determine if there is actual running data at present; If not, the power compensation amount is output directly, and signal control is performed based on the power compensation amount; If so, the influence matrix is ​​calibrated online based on the actual operating data, and the process returns to step S3.

3. The sintering furnace temperature feedforward compensation method according to claim 2, characterized in that, Step S2 specifically includes the following steps: Based on the three-dimensional spatial coordinates of the heating element and the three-dimensional spatial coordinates of the temperature measuring point, calculate the Euclidean distance between the j-th heating element and the i-th temperature measuring point. ; By using the distance exponential decay function, combined with the Euclidean distance Calculate the influence coefficient of each heating element on each temperature measuring point. ; The influence matrix is ​​then subjected to column normalization.

4. The sintering furnace temperature feedforward compensation method according to claim 1, characterized in that, Step S5 specifically includes the following steps: Power compensation quantity is established based on the influence matrix. Temperature deviation The linear relationship is expressed as follows: ， The power compensation amount is solved using regularized least squares. The objective function is: ， Calculate the power compensation amount , in, The regularization coefficient is . , It is an identity matrix.

5. The sintering furnace temperature feedforward compensation method according to claim 1, characterized in that, The formula for calculating the predicted temperature is: ； in, This represents the current power vector of each heating element. , Ambient temperature; The formula for calculating the temperature deviation is: ， in, For the target temperature, This represents the current power of a heating element.

6. The sintering furnace temperature feedforward compensation method according to claim 3, characterized in that, The formula for calculating the influence coefficient is as follows: When the Euclidean distance When >0, , where λ is the characteristic attenuation length; When the Euclidean distance When =0, .

7. The sintering furnace temperature feedforward compensation method according to claim 6, characterized in that, The online calibration of the influence matrix based on the actual operating data includes the following steps: Obtain K sets of actual operating data ,in, For heating power vector, For the measured temperature vector and This represents the ambient temperature vector. The characteristic attenuation length parameter is calibrated based on the operational data, and the calibration formula is as follows: ， in, Let λ represent the influence matrix. The influence coefficients are recalculated based on the calibrated characteristic attenuation length parameters, and the influence matrix is ​​updated.

8. A sintering furnace temperature feedforward compensation system, characterized in that, The system includes: Several heating elements (20) and several thermocouples (30) are arranged inside the furnace body; Solid-state relays (40), each of the heating elements (20) is connected to the solid-state relays (40) for controlling the heating of the furnace body; The PLC control module (50) is connected to each of the thermocouples (30) and the solid-state relays (40) to acquire temperature signals, as well as output PWM signals and control signals; An edge computing module (90) is connected to the PLC control module (50). The edge computing module (90) is configured to perform the sintering furnace temperature feedforward compensation method as described in any one of claims 1 to 7, and output the power compensation amount to the PLC control module so that the PLC control module (50) controls the furnace body based on the power compensation amount. A visual interaction module (80) is connected to the PLC control module (50) to display temperature distribution and compensation effect.

9. A sintering furnace temperature feedforward compensation system according to claim 8, characterized in that, The edge computing module (90) includes: The data acquisition module (901) acquires the power and corresponding ambient temperature of each heating element; The construction module (902) constructs an influence matrix based on the three-dimensional spatial coordinates of all the heating elements and the three-dimensional spatial coordinates of all the temperature measuring points. ; The temperature prediction module (903), in conjunction with the influence matrix, predicts the temperature of each temperature measuring point based on the current power of each heating element and the corresponding ambient temperature, and obtains the predicted temperature. ; The compensation calculation module (904) calculates the temperature deviation in conjunction with the target temperature. Based on the influence matrix and temperature deviation, the required power compensation is calculated using regularized least squares. ; The online calibration module (905) calibrates the model parameters based on actual operating data.

10. A sintering furnace temperature feedforward compensation system according to claim 8, characterized in that, The edge computing module is connected to the PLC control module via the Modbus TCP protocol.

Images