Multi-parameter closed-loop control method, device and equipment for sintering of large-size powder rods

Abstract

This application belongs to the field of data processing technology, specifically disclosing a multi-parameter closed-loop control method, apparatus, and equipment for sintering large-size powder rods. This application sets executable sintering process windows at different stages; during the batch sintering of large-size powder rods, the current defect risk index of the large-size powder rods is calculated based on state parameters; when the current defect risk index does not exceed a preset risk threshold, the sintered product undergoes quality inspection, and the sintering process parameters for the next batch of powder rods are corrected based on the inspection results. Through this method, the initial state parameters of the large-size powder rods to be sintered are obtained before sintering, and the target sintering quality parameters are determined; the current defect risk index is calculated during sintering; and the sintering process parameters for the next batch of powder rods are corrected after sintering. This achieves a shift from traditional fixed-program sintering to closed-loop control based on the powder rod state, thereby effectively reducing the risk of powder rod sintering.

Description

Technical Field

[0001] This application belongs to the field of data processing technology, and more specifically, relates to a multi-parameter closed-loop control method, apparatus and equipment for large-size powder rod sintering. Background Technology

[0002] The sintering products of powder rods can be large-size quartz ingots or ULE ultra-low expansion glass. The sintering process involves multiple stages, such as low-temperature dehumidification, medium-temperature dehydroxylation, high-temperature densification, high-temperature homogenization, and slow-cooling stress release. Currently, common sintering control methods rely heavily on preset heating curves, fixed holding times, and operator experience. Due to the long radial heat transfer path and internal gas exhaust distance of large-size powder rods, the outer layer often heats up, softens, and densifies first. Using the above-mentioned sintering control methods can lead to premature formation of a closed layer on the outer surface. This makes it difficult for free water, gases generated during hydroxyl removal, or residual gases in the pores to escape in time, easily leading to bubbles, closed pores, localized density unevenness, and residual stress concentration after cooling. Therefore, sintering powder rods using the above methods carries a high risk. Summary of the Invention

[0003] In view of the shortcomings of the prior art, the purpose of this application is to provide a multi-parameter closed-loop control method, device and equipment for sintering large-size powder rods, which aims to solve the problem that the existing technology has a high risk of powder rod sintering due to the early formation of a closed layer on the outer layer and the inability to timely discharge the gas generated by the removal of free water and hydroxyl groups or the residual gas in the pores.

[0004] To achieve the above objectives, in a first aspect, this application provides a multi-parameter closed-loop control method for sintering large-size powder rods, comprising: Obtain the initial state parameters of the large-size powder rod to be sintered, and determine the target sintering quality parameters based on the specification parameters of the sintering product of the large-size powder rod to be sintered. The executable sintering process windows for different stages are set according to the initial state parameters and the target sintering quality parameters; During the batch sintering of the large-size powder rod to be sintered according to the executable sintering process window, the target state parameters of the large-size powder rod to be sintered are collected in real time, and the current defect risk index of the large-size powder rod to be sintered is calculated based on the target state parameters. When the current defect risk index does not exceed the preset risk threshold, the sintered product is subjected to quality testing, and the sintering process parameters of the next batch of sintered powder rods are corrected in reverse based on the test results.

[0005] In one embodiment, the step of real-time acquisition of target state parameters of the large-size powder rod to be sintered during the batch sintering process according to the executable sintering process window, and calculation of the current defect risk index of the large-size powder rod to be sintered based on the target state parameters, includes: During the batch sintering of the large-size powder rod to be sintered according to the executable sintering process window, the directly measurable external state parameters of the large-size powder rod to be sintered are collected in real time. The external state parameters are converted into online observation vectors, and the internal state parameters are estimated based on the online observation vectors and the external state parameters. Calculate the multi-parameter index values ​​based on the external state parameters and the internal state parameters respectively, and calculate the defect risk index of each region based on the multi-parameter index values ​​and the weighting coefficients corresponding to the multi-parameter index values. The current defect risk index of the large-size powder rod to be sintered is determined based on the defect risk index of each region.

[0006] In one embodiment, the step of converting the external state parameters into an online observation vector and estimating the internal state parameters based on the online observation vector and the external state parameters includes: The external state parameters are converted into online observation vectors based on the matrix transpose. The estimated state, correction gain, and target observation function of each region at the current time are obtained respectively. The estimation strategy based on digital twin update relationships estimates the internal state parameters according to the online observation vector, the external state parameters, the estimated state of each region at the current time, the correction gain, and the target observation function.

[0007] In one embodiment, the multi-parameter index values ​​include: radial shrinkage rate, axial shrinkage uniformity index value, and densification-dehydroxylation matching index value; The step of calculating the multi-parameter index values ​​based on the external state parameters and the internal state parameters includes: The equivalent diameter is extracted from the external state parameters, and the radial contraction rate of the partition is calculated based on the equivalent diameter and the target correction parameters. The axial shrinkage uniformity index value is calculated based on the radial shrinkage rate of each of the aforementioned zones; The target density and initial hydroxyl content are extracted from the internal state parameters, and the densification-dehydroxylation matching index value is calculated based on the target density and the initial hydroxyl content.

[0008] In one embodiment, the multi-parameter index values ​​include: pore connectivity exhaust safety margin; The step of calculating the multi-parameter index values ​​based on the external state parameters and the internal state parameters includes: The characteristic value of pressure difference-driven seepage venting capacity is calculated based on the external state parameters and the internal state parameters, and the characteristic value of pressure gradient-driven diffusion venting capacity is calculated based on the external state parameters and the internal state parameters. The characteristic value of seepage and air release capacity driven by pressure difference is accumulated to obtain the characteristic value of pore air release capacity. The gas release rate is calculated based on the external state parameters and the internal state parameters; The safety margin for pore connectivity venting is calculated based on the characteristic value of the pore venting capacity and the gas release rate.

[0009] In one embodiment, the step of performing quality testing on the sintered product when the current defect risk index does not exceed a preset risk threshold, and then reversing the sintering process parameters of the next batch of sintered powder rods based on the test results, includes: When the current defect risk index does not exceed a preset risk threshold, the sintered product is subjected to quality testing. Obtain the characteristic information of the sintered product, and select sintering process parameter correction and evaluation data from the test results based on the characteristic information; A quality deviation objective function is generated based on the modified evaluation data of the sintering process parameters and the target sintering quality parameters. When the quality deviation objective function meets the preset correction conditions, the sintering process parameters of the next batch of sintered powder rods are corrected in reverse according to the quality deviation objective function.

[0010] In one embodiment, the step of performing quality inspection on the sintered product when the current defect risk index does not exceed a preset risk threshold includes: When the current defect risk index does not exceed the preset risk threshold, a current flag for entering the next stage is set according to the stage transition criteria. When the current flag is a preset flag, the process is allowed to proceed to the next stage, and the sintered product is subjected to quality testing.

[0011] In one embodiment, after the steps of real-time acquisition of target state parameters of the large-size powder rod to be sintered during the batch sintering process according to the executable sintering process window, and calculation of the current defect risk index of the large-size powder rod to be sintered based on the target state parameters, the method further includes: When the current defect risk index of the large-size powder bar to be sintered exceeds the preset risk threshold, the adjustment amount of the sintering process parameters of the large-size powder bar to be sintered is calculated respectively. Based on the aforementioned adjustment amounts, the sintering process parameters of the large-sized powder rod to be sintered are dynamically adjusted within the executable sintering process window.

[0012] Secondly, this application provides a multi-parameter closed-loop control device for sintering large-size powder rods, comprising: The determination module is used to obtain the initial state parameters of the large-size powder rod to be sintered, and to determine the target sintering quality parameters based on the specification parameters of the sintering product of the large-size powder rod to be sintered. The setting module is used to set the executable sintering process windows for different stages according to the initial state parameters and the target sintering quality parameters; The sintering module is used to collect the target state parameters of the large-size powder rod to be sintered in real time during the batch sintering process of the large-size powder rod to be sintered according to the executable sintering process window, and to calculate the current defect risk index of the large-size powder rod to be sintered based on the target state parameters. The correction module is used to perform quality testing on the sintered product when the current defect risk index does not exceed a preset risk threshold, and to reverse-correct the sintering process parameters of the next batch of sintered powder rods based on the test results.

[0013] Thirdly, this application provides an electronic device, comprising: at least one memory for storing a program; and at least one processor for executing the program stored in the memory, wherein when the program stored in the memory is executed, the processor is configured to execute the method described in the first aspect or any possible implementation thereof.

[0014] It is understood that the beneficial effects of the second and third aspects mentioned above can be found in the relevant descriptions in the first aspect above, and will not be repeated here.

[0015] Overall, the technical solutions conceived in this application have the following beneficial effects compared with the prior art: (1) This application realizes the transformation from traditional fixed-program sintering to closed-loop control based on the state of the powder rod. Before sintering, the initial state parameters of the large-size powder rod to be sintered are obtained, and the target sintering quality parameters are determined based on the specification parameters of the sintered product of the large-size powder rod to be sintered. Then, different stages of executable sintering process windows are set to sinter the large-size powder rod to be sintered in this batch. The current defect risk index of the large-size powder rod to be sintered is calculated by multi-parameter index values ​​including radial shrinkage rate, axial shrinkage uniformity index value, densification-dehydroxylation matching index value, and pore connectivity venting safety margin. This enables prediction and intervention before the formation of bubbles, closed pores, and residual stress. After sintering, the sintering process parameters of the next batch of sintered powder rods are corrected in reverse according to the quality deviation objective function. That is, the multi-parameter closed-loop control logic based on temperature, atmosphere, pressure, size shrinkage, hydroxyl removal, and pore venting capacity is not based on a specific mechanical structure. This can effectively reduce the risk of powder rod sintering and thus improve the batch stability of the sintered products.

[0016] (2) This application will also calculate the first... Pore ​​exhaust capacity characteristic value of the region The first characteristic value corresponding to the pore exhaust capacity Gas release rate in the zone At this point, you can set The porous structure provides ventilation constraints, preventing premature densification of the outer layer that could trap internal gases and reducing the risk of air bubbles and closed pores inside large-sized powder rods. Furthermore, this application introduces a densification-dehydroxylation matching index. It is used to control the matching relationship between densification and dehydroxylation, meet the requirements of large-size sintering powder rods for the stability of hydroxyl content and thermal expansion coefficient, and avoid completing dehydroxylation and densification under the condition of pre-sealing of the outer layer, thereby reducing the risk of hydroxyl residue, closed pores and expansion coefficient fluctuation.

[0017] In summary, this application obtains the initial state parameters of large-size powder rods to be sintered, and determines the target sintering quality parameters based on the specification parameters of the sintered product of the large-size powder rods to be sintered; sets executable sintering process windows for different stages based on the initial state parameters and the target sintering quality parameters; during the batch sintering of the large-size powder rods to be sintered according to the executable sintering process windows, the target state parameters of the large-size powder rods to be sintered are collected in real time, and the current defect risk index of the large-size powder rods to be sintered is calculated based on the target state parameters; when the current defect risk index does not exceed a preset risk threshold, the sintered product is subjected to quality inspection, and the sintering process parameters of the next batch of sintered powder rods are corrected in reverse based on the inspection results. By using the above method, the initial state parameters of large-sized powder rods to be sintered are obtained before sintering, and the target sintering quality parameters are determined. The current defect risk index is calculated during sintering, and the sintering process parameters of the next batch of sintered powder rods are corrected after sintering. This realizes the transformation from traditional fixed-program sintering to closed-loop control based on the state of the powder rods, thereby effectively reducing the risk of powder rod sintering and improving the batch stability of the sintered products. Attached Figure Description

[0018] Figure 1 This is one of the flowcharts illustrating the multi-parameter closed-loop control method for large-size powder rod sintering provided in the embodiments of this application; Figure 2 This is a schematic diagram of the sintering stage and collaborative control provided in the embodiments of this application; Figure 3 This is a schematic diagram of the overall structure provided in the embodiments of this application; Figure 4 This is the second flowchart of the multi-parameter closed-loop control method for large-size powder rod sintering provided in the embodiments of this application; Figure 5 This is a schematic diagram of the module structure of the multi-parameter closed-loop control device for large-size powder rod sintering provided in the embodiments of this application; Figure 6 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0020] In this article, the term "and / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. The symbol " / " in this article indicates that the related objects are in an "or" relationship; for example, A / B means A or B.

[0021] The terms "first" and "second," etc., used in the specification and claims herein are used to distinguish different objects, not to describe a specific order of objects. For example, "first response message" and "second response message," etc., are used to distinguish different response messages, not to describe a specific order of response messages.

[0022] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of the terms "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0023] Based on this, embodiments of this application provide a multi-parameter closed-loop control method for sintering large-size powder rods, referring to... Figure 1 , Figure 1 This is one of the flowcharts illustrating the multi-parameter closed-loop control method for large-size powder rod sintering provided in this application embodiment. In this embodiment, the multi-parameter closed-loop control method for large-size powder rod sintering includes steps S10 to S40: Step S10: Obtain the initial state parameters of the large-size powder rod to be sintered, and determine the target sintering quality parameters based on the specification parameters of the sintering product of the large-size powder rod to be sintered.

[0024] It should be noted that different batches of powder rods may vary in diameter, length, mass, porosity, hydroxyl content, axial density distribution, and compositional uniformity. Directly using the same sintering curve could easily lead to insufficient moisture removal, insufficient dehydroxylation, or excessively rapid densification in some powder rods. Therefore, before sintering, it is necessary to obtain the initial state parameters of the large-sized powder rods to be sintered. These initial state parameters include, but are not limited to, diameter, length, mass, initial porosity, initial hydroxyl content, water content, axial density fluctuation index, and diameter deviation. When the large-sized powder rods to be sintered are ULE powder rods, the initial state parameters also include: titanium doping and compositional uniformity index. If the initial porosity... A higher initial hydroxyl content indicates a complex internal exhaust path for large-sized powder rods to be sintered, requiring a slower heating rate and longer holding time; if the initial hydroxyl content is high... A higher value indicates that the intermediate-temperature dehydroxylation stage requires a longer time or a higher atmosphere flow rate; if the axial density fluctuation index... A larger corresponding value indicates uneven axial density in the large-sized powder rods to be sintered, requiring the use of multi-zone temperature compensation. The axial density fluctuation index can be expressed as: .

[0025] in, Indicates the first Equivalent density of each axial detection segment Indicates the axial average density. This indicates a positive number to prevent the denominator from being too small.

[0026] It should be understood that, in this embodiment, the quality requirements of the sintered product need to be converted into calculable target parameters. That is, the target sintering quality parameters are determined based on the specifications of the sintered product of the large-size powder rod to be sintered. These target sintering quality parameters include, but are not limited to, target density, target residual porosity, target hydroxyl content, allowable residual stress, target shrinkage rate, bubble grade, dimensional deviation, and coefficient of thermal expansion. The target sintering quality parameters characterize the state of the sintered product of the large-size powder rod to be sintered. The difference between the target sintering quality parameters and the initial state parameters determines the "state transformation amount" that needs to be completed during the sintering process. For example, if the initial density... With target density A significant difference between the two indicates a heavy densification task; if the initial hydroxyl content... A significant difference between the target hydroxyl content and the actual content indicates a heavy workload for dehydroxylation. When large-size powder rods to be sintered are ULE powder rods, the target coefficient of thermal expansion can be achieved. The uniformity of titanium doping is incorporated into the target sintering quality parameters. This ensures that when generating the subsequent objective function for quality deviation, attention is paid not only to density and bubbles, but also to hydroxyl residue and the stability of the expansion coefficient. The large-sized powder rods to be sintered can be high-purity quartz powder rods with diameters of approximately 200 to 500 mm and lengths of approximately 500 to 2000 mm.

[0027] Step S20: Set executable sintering process windows for different stages based on the initial state parameters and the target sintering quality parameters.

[0028] Understandably, after obtaining the initial state parameters and target sintering quality parameters, these need to be set as executable sintering process windows for different stages. Their function is to provide the execution entity (controller) with a reasonable initial trajectory, including the temperature range, heating rate, holding time, atmosphere flow rate, and furnace pressure range for each stage. At this point, the final curve is not required to remain fixed but can be dynamically adjusted within the executable sintering process window. The sintering furnace can be horizontal, vertical, or other multi-zone heating equipment suitable for powder bar sintering.

[0029] It should be understood, and it needs to be explained, that reference Figure 2 , Figure 2 This diagram illustrates the sintering stages and their coordinated control. For large-sized powder rods to be sintered, the sintering process is divided into four stages: low-temperature dehumidification, medium-temperature dehydroxylation, high-temperature densification, high-temperature homogenization, and slow-cooling stress release. Each stage includes four categories of information: temperature strategy, atmosphere strategy, shrinkage control, and target / risk. Specifically, the low-temperature dehumidification stage focuses on removing free water to prevent sudden release of internal moisture at subsequent high temperatures; the medium-temperature dehydroxylation stage focuses on controlling hydroxyl removal and gas release; the high-temperature densification stage focuses on increasing density while preventing premature sealing of the outer layer; the high-temperature homogenization stage focuses on reducing the microstructure and compositional gradient; and the slow-cooling stress release stage focuses on controlling cooling stress and deformation. The trend graph below illustrates the relationship between key variables and time: temperature gradually increases in the early stages, remains relatively stable in the high-temperature homogenization stage, and decreases in the slow-cooling stage; the shrinkage rate reaches its peak in the high-temperature densification stage; the hydroxyl content mainly decreases in the medium-temperature dehydroxylation and high-temperature densification stages; and pore connectivity continuously decreases with densification. Therefore, maintaining an effective exhaust channel before the outer layer is a key control principle that distinguishes this invention from traditional fixed-curve sintering. The example temperature ranges, control priorities, and target settings for each sintering stage are shown in Table 1. Table 1:

[0030] Step S30: During the batch sintering of the large-size powder rod to be sintered according to the executable sintering process window, the target state parameters of the large-size powder rod to be sintered are collected in real time, and the current defect risk index of the large-size powder rod to be sintered is calculated based on the target state parameters.

[0031] It should be understood that after setting the executable sintering process window, the entry point for the online closed loop of the sintering process is reached. During the batch sintering of large-sized powder rods according to the executable sintering process window, the temperature, shrinkage, and exhaust state of the large-sized powder rods during the actual sintering process will be affected by the initial differences in the powder rods, the thermal inertia of the furnace body, the atmosphere flow, and the degree of local densification of the material. Therefore, it is necessary to collect the target state parameters of the large-sized powder rods in real time. These target state parameters include, but are not limited to, multi-zone furnace temperature, powder rod surface temperature, local diameter or displacement of the powder rod, atmosphere flow rate, furnace pressure, exhaust humidity, exhaust gas composition, internal porosity, local density, and hydroxyl content. At this time, the current defect risk index of the large-sized powder rods can be calculated based on the target state parameters as an online risk criterion to achieve risk assessment.

[0032] Furthermore, after step S30, the method further includes: when the current defect risk index of the large-size powder rod to be sintered exceeds a preset risk threshold, calculating the adjustment amount of the sintering process parameters of the large-size powder rod to be sintered respectively; and dynamically adjusting the sintering process parameters of the large-size powder rod to be sintered within the executable sintering process window according to each of the adjustment amounts.

[0033] Understandably, when the current defect risk index of a large-sized powder rod to be sintered exceeds a preset risk threshold, it indicates that the risk is uncontrollable. In this case, sintering process parameters such as heating rate, holding time, atmosphere flow rate, furnace pressure, and multi-zone temperature can be dynamically adjusted within the executable sintering process window. On one hand, the dynamic adjustment of the heating rate can be expressed as: .

[0034] in, This indicates the adjusted heating rate. This indicates the initial heating rate at the current stage. and All represent adjustment coefficients. express When the risk of defects increases or the venting margin is insufficient, the heating rate automatically decreases.

[0035] On the other hand, the dynamic compensation for heat preservation time can be expressed as: .

[0036] in, Indicates the insulation time after compensation. Indicates the baseline insulation time. , and All represent weighting coefficients. This indicates the target matching value. When the risk is high, the exhaust is insufficient, or the densification-dehydroxylation process is mismatched, the holding time can be extended to allow time for the exhaust and dehydroxylation processes.

[0037] On the other hand, the coordinated dynamic adjustment of atmosphere flow rate and furnace pressure can be expressed as:

[0038] .

[0039] in, and These represent the adjusted atmosphere flow rate and furnace pressure, respectively. and All of these represent adjustment coefficients. The purpose of this coordinated dynamic adjustment is to enhance exhaust driving force and reduce the risk of gas retention and bubbling when the gas release rate is too high.

[0040] Furthermore, the dynamic compensation of temperature across multiple zones can be expressed as: .

[0041] in, Indicates the first Temperature after heating zone compensation Indicates the estimated density. Indicates the target contraction rate. This represents the average temperature of each zone. If a zone shrinks too quickly or has a high risk of defects, the temperature compensation for that zone will be reduced. If a zone is not sufficiently densified and the risk is permissible, then the zone can be compensated for with heating within a safe range.

[0042] It should be noted that after performing the above operations, this embodiment does not directly end the control, but continues to return to the step of real-time acquisition of target state parameters of large-size powder rods to be sintered, forming a closed loop of process of "real-time acquisition of target state parameters - calculation of current defect risk index - comparison of current defect risk index with preset risk threshold - real-time acquisition of target state parameters", until the defect risk index of large-size powder rods to be sintered does not exceed the preset risk threshold, and the current flag for entering the next stage from the current stage is the preset flag.

[0043] Step S40: When the current defect risk index does not exceed the preset risk threshold, the sintered product is subjected to quality inspection, and the sintering process parameters of the next batch of sintered powder rods are corrected in reverse according to the inspection results.

[0044] It should be noted that after determining the current defect risk index of the large-size powder rod to be sintered, it is necessary to determine whether the current defect risk index exceeds the preset risk threshold. If it does, it indicates that the risk is uncontrollable and the sintering process parameters of the large-size powder rod to be sintered need to be dynamically adjusted. If not, it indicates that the risk is controllable. When the quality deviation objective function meets the preset correction conditions, the sintering process parameters of the next batch of sintered powder rods are corrected in reverse according to the quality deviation objective function. For example, taking large-size high-purity quartz powder rods as an example, if the bubble index is found to be too high, the holding time of the intermediate-temperature dehydroxylation stage and the high-temperature densification stage of the next batch will be increased; if the axial density fluctuation is found to be too large, the multi-zone temperature compensation coefficient of the next batch will be increased.

[0045] Further, step S40 includes: when the current defect risk index does not exceed a preset risk threshold, performing quality testing on the sintered product; acquiring characteristic information of the sintered product, and selecting sintering process parameter correction evaluation data from the test results based on the characteristic information; generating a quality deviation objective function based on the sintering process parameter correction evaluation data and the target sintering quality parameter; and when the quality deviation objective function meets a preset correction condition, reversibly correcting the sintering process parameters of the next batch of sintered powder rods based on the quality deviation objective function.

[0046] Understandably, when the current defect risk index does not exceed the preset risk threshold, it is still necessary to conduct quality inspection on the sintered product. The quality inspection indicators at this time include, but are not limited to, density, hydroxyl content, bubble / closed-cell level, residual stress, dimensional deviation, and axial density uniformity. For sintered products with different characteristic information, the key sintering process parameter correction and evaluation data are different. When the sintered product is ordinary quartz ingot, the sintering process parameter correction and evaluation data can be density, bubble, hydroxyl content, and residual stress. When the sintered product is ULE ingot, it also includes the coefficient of thermal expansion and titanium doping uniformity.

[0047] It should be understood that after selecting sintering process parameter correction and evaluation data from the test results based on characteristic information, it is necessary to compare them with the target sintering quality parameters to form a quality deviation objective function. This quality deviation objective function is used to evaluate the deviation between the sintering process parameter correction and evaluation data and the target sintering quality parameters, and to guide the reverse correction of the sintering process parameters for the next batch of sintered powder bars. The quality deviation objective function can be expressed as: .

[0048] in, Indicates the batch number. , , , , , and These represent the density, hydroxyl content, residual stress, bubble index, dimensional deviation, axial density fluctuation, and coefficient of thermal expansion used in this screening, respectively. , , , , , and All of these represent the weighting coefficients of the above-mentioned sintering process parameter correction evaluation data. When the sintered product is ordinary quartz ingot, A smaller value can be taken or no participation is allowed; when the sintered product is a ULE ingot, and It can improve adaptability.

[0049] It should be noted that the reverse correction of the sintering process parameters for the next batch of sintered powder rods can be expressed as: .

[0050] in, This represents the sintering process parameters of the (n+1)th batch of sintered powder rods after reverse correction. Indicates the first Batch sintering process parameters, Indicates the learning step size. This represents the scaling matrix or empirical sensitivity matrix. This indicates that the updated parameters will be projected onto the allowed executable sintering process window. Within this range, avoid making corrections that exceed the safety limits of the equipment or materials.

[0051] It should also be emphasized that, for the first For batch sintering process parameters, they can be expressed as: .

[0052] in, Indicates the first Batch sintering process parameters, Indicates the heating rate, Indicates the heat preservation time. Indicates atmospheric flow rate. This indicates the furnace pressure.

[0053] Furthermore, the step of performing quality inspection on the sintered product when the current defect risk index does not exceed the preset risk threshold includes: when the current defect risk index does not exceed the preset risk threshold, setting a current flag for entering the next stage from the current stage according to the stage transition criterion; when the current flag is a preset flag, allowing entry into the next stage and performing quality inspection on the sintered product.

[0054] It should be understood that after determining that the current defect risk index does not exceed the preset risk threshold, it is also necessary to determine whether the current indicator for transitioning from the current stage to the next stage is a preset indicator. The stage transition criterion can be expressed as: ,but .

[0055] in, For the first Phase 1 enters the first A marker of a stage.

[0056] It should also be emphasized that a phase is set only when all the conditions included in the phase transition criterion are met. This is the preset flag, at which point it is allowed to enter the next stage. Conversely, if any of the above conditions are not met, the closed-loop adjustment of "real-time acquisition of target state parameters - calculation of current defect risk index - comparison of current defect risk index with preset risk threshold - real-time acquisition of target state parameters" will continue to be performed in the current stage. The above settings can prevent the powder rod from entering the high-temperature densification stage too early in the case of insufficient exhaust, insufficient removal of hydroxyl groups or uneven shrinkage.

[0057] It should be noted that the reference Figure 3 , Figure 3 This is a schematic diagram of the overall structure, used to describe the system-level implementation of the technical solution in this embodiment. Specifically: the temperature sensor, surface diameter measurement / visual monitoring unit, and furnace pressure / flow monitoring unit on the left are used to collect the target state parameters of large-sized powder rods to be sintered in real time. The sintering furnace body in the middle includes a multi-zone heating unit, a powder rod support mechanism, and powder rod and atmosphere input / output channels. It corresponds to the executable sintering process windows at different stages, judges whether the current defect risk index exceeds the preset risk threshold, and executes corresponding operations, such as reducing the heating rate, extending the holding time, adjusting the atmosphere flow rate or furnace pressure, etc. The data acquisition and algorithm unit below is used to calculate the current defect risk index of the large-sized powder rods to be sintered. The controller on the right is used to adjust the temperature, atmosphere, furnace pressure, and holding time according to the algorithm output. The quality detection and feedback unit after sintering is used to perform quality detection on the sintered products and correct the sintering process parameters of the next batch of sintered powder rods based on the detection results.

[0058] This embodiment acquires the initial state parameters of a large-sized powder rod to be sintered, and determines the target sintering quality parameters based on the specification parameters of the sintered product of the large-sized powder rod. It sets executable sintering process windows for different stages based on the initial state parameters and the target sintering quality parameters. During the batch sintering of the large-sized powder rod according to the executable sintering process windows, the target state parameters of the large-sized powder rod are collected in real time, and the current defect risk index of the large-sized powder rod is calculated based on the target state parameters. When the current defect risk index does not exceed a preset risk threshold, the sintered product is subjected to quality inspection, and the sintering process parameters for the next batch of sintered powder rods are corrected in reverse based on the inspection results. By using the above method, the initial state parameters of large-sized powder rods to be sintered are obtained before sintering, and the target sintering quality parameters are determined. The current defect risk index is calculated during sintering, and the sintering process parameters of the next batch of sintered powder rods are corrected after sintering. This realizes the transformation from traditional fixed-program sintering to closed-loop control based on the state of the powder rods, thereby effectively reducing the risk of powder rod sintering and improving the batch stability of the sintered products.

[0059] In one specific embodiment, this application provides steps for calculating the current defect risk index of large-size powder rods to be sintered. Please refer to... Figure 4 , Figure 4 This is the second flowchart illustrating the multi-parameter closed-loop control method for large-size powder rod sintering provided in this application embodiment. Step S30 includes steps S301 to S304: Step S301: During the batch sintering of the large-size powder rod to be sintered according to the executable sintering process window, the directly measurable external state parameters of the large-size powder rod to be sintered are collected in real time.

[0060] It should be noted that the target state parameters for large-sized powder rods to be sintered include directly measurable external state parameters and non-measurable internal state parameters. The directly measurable external state parameters include, but are not limited to, multi-zone furnace temperature, powder rod surface temperature, local diameter or displacement of powder rod, atmosphere flow rate, furnace pressure, exhaust humidity and exhaust gas composition, etc. The non-measurable internal state parameters include, but are not limited to, internal porosity, local density and hydroxyl content, etc.

[0061] Step S302: Convert the external state parameters into online observation vectors, and estimate the internal state parameters based on the online observation vectors and the external state parameters.

[0062] Understandably, for directly measurable external state parameters, they can be converted into online observation vectors required for subsequent calculations using matrix transpose, specifically as follows: .

[0063] in, Represents the online observation vector. Indicates the first The furnace temperature in the zone This indicates the surface temperature of a large-sized powder rod to be sintered. This indicates the local equivalent diameter of a large-sized powder rod to be sintered. Indicates furnace pressure. Indicates atmospheric flow rate. This indicates exhaust humidity or moisture content. This represents the signal of the exhaust gas components, and T represents the matrix transpose.

[0064] Further, step S302 includes: converting the external state parameters into an online observation vector according to the matrix transpose; obtaining the estimated state, correction gain, and target observation function of each region at the current time; and estimating the internal state parameters based on the estimation strategy of digital twin update relationship, according to the online observation vector, the external state parameters, the estimated state of each region at the current time, the correction gain, and the target observation function.

[0065] It should be understood that for unmeasurable internal state parameters, estimation strategies based on digital twin update relationships can be used to estimate them, specifically: .

[0066] in, Indicates the first District Estimated state at time [time] This indicates the control inputs, including heating rate, holding time, atmosphere flow rate, and furnace pressure. Indicates the initial parameters of the powder stick. Indicates the correction gain. This represents the observation function.

[0067] Step S303: Calculate the multi-parameter index values ​​based on the external state parameters and the internal state parameters respectively, and calculate the defect risk index of each region based on the multi-parameter index values ​​and the weighting coefficients corresponding to the multi-parameter index values.

[0068] It should be understood that the multi-parameter index values ​​refer to the parameter indicators used to calculate the defect risk index of each region. These multi-parameter index values ​​include, but are not limited to, radial shrinkage rate, axial shrinkage uniformity index value, densification-dehydroxylation matching index value, and pore connectivity venting safety margin, etc. Through the above multi-parameter index values, it is calculated whether there is a risk of premature sealing of the outer layer, internal gas retention, delayed hydroxyl removal, uneven shrinkage, or stress in the large-size powder rod to be sintered.

[0069] Further, the multi-parameter index values ​​include: radial shrinkage rate, axial shrinkage uniformity index value, and densification-dehydroxylation matching index value; step S303 includes: extracting the equivalent diameter from the external state parameters, and calculating the partition radial shrinkage rate based on the equivalent diameter and the target correction parameter; calculating the axial shrinkage uniformity index value based on the radial shrinkage rate of each partition; extracting the target density and initial hydroxyl content from the internal state parameters, and calculating the densification-dehydroxylation matching index value based on the target density and the initial hydroxyl content.

[0070] It should be noted that after extracting the equivalent diameter from the external state parameters, the radial shrinkage rate of the partition can be calculated based on the diameter change of the large-sized powder rod to be sintered. The larger the radial shrinkage rate of the partition, the faster the densification of that region. When the outer region... When the size is too large and the internal venting capacity is insufficient, it is prone to the risk of closed pores and air bubbles, specifically: .

[0071] in, Indicates the first The radial contraction rate of the region, Indicates the first The equivalent diameter of the region, This indicates a correction amount to prevent the denominator from being too small.

[0072] It should be noted that after calculating the radial shrinkage rate of the partition, the axial shrinkage uniformity index can also be calculated based on the radial shrinkage rate of the partition, specifically: .

[0073] in, The value of the axial shrinkage uniformity index is used to evaluate the shrinkage difference between different heating zones. When the axial shrinkage uniformity index is too large, it indicates that there is uneven axial shrinkage in large-sized powder bars to be sintered. In this case, multi-zone temperature compensation should be implemented first, rather than simply increasing or decreasing the temperature of the entire furnace.

[0074] On the other hand, the relationship between hydroxyl removal and densification can be represented by the densification-dehydroxylation matching index, specifically: .

[0075] in, This indicates the value of the densification-dehydroxylation matching index. This represents the minimum value. Indicates the maximum value. Indicates the target density. This indicates the initial hydroxyl content.

[0076] It should be noted that the densification-dehydroxylation matching index values... An excessively high value indicates that the densification rate is too fast relative to the hydroxyl removal rate, which may lead to hydroxyl residue after the outer layer is sealed; the densification-dehydroxylation matching index value is important. If the value is too small, it indicates that the dehydroxylation process is dominant and densification is insufficient, which may lead to low efficiency or insufficient structural homogenization. Therefore, this densification-dehydroxylation matching index value can make the control of hydroxyl groups in the sintering of large-sized powder rods more precise.

[0077] Further, the multi-parameter index values ​​include: pore connectivity venting safety margin; step S303 includes: calculating the pressure difference-driven seepage venting capacity characteristic value based on the external state parameters and the internal state parameters, and calculating the pressure gradient-driven diffusion venting capacity characteristic value based on the external state parameters and the internal state parameters; accumulating the pressure difference-driven seepage venting capacity characteristic value and the pressure difference-driven seepage venting capacity characteristic value to obtain the pore venting capacity characteristic value; calculating the gas release rate based on the external state parameters and the internal state parameters; and calculating the pore connectivity venting safety margin based on the pore venting capacity characteristic value and the gas release rate.

[0078] It should be noted that the specific calculation method for the characteristic value of pore exhaust capacity can be expressed as follows: .

[0079] in, Indicates the first Characteristic values ​​of pore exhaust capacity in the region This represents the characteristic value of pressure differential-driven seepage venting capacity. This represents the characteristic value of diffusion exhaust capability driven by the partial pressure gradient. Indicates equivalent penetration rate. Indicates the equivalent exhaust cross-sectional area. Indicates gas viscosity, Indicates the equivalent exhaust path, Indicates pressure difference, Indicates the effective diffusion coefficient. Represents the gas constant. Indicates temperature. This represents the gas partial pressure difference. Through the above method, the atmosphere flow, furnace pressure, and the interconnectivity of the powder rod pores are unified into a single characteristic value for pore exhaust capacity.

[0080] It should be noted that the gas release rate corresponding to the characteristic value of pore exhaust capacity can be specifically calculated as follows: .

[0081] in, Indicates the first The gas release rate of the zone, This indicates the amount of free water or adsorbed water. Indicates hydroxyl content, Indicates real-time porosity. This represents the equivalent volume of the region. , as well as All of these represent conversion coefficients. Through the above method, the gas release during dehumidification, dehydroxylation, and pore closure processes is unified into a single gas release rate.

[0082] It should also be emphasized that, in order to directly determine whether the exhaust is safe, it is also necessary to calculate the safety margin of pore connectivity exhaust based on the characteristic value of pore exhaust capacity and the gas release rate, specifically: .

[0083] in, Indicates the safety margin for venting through pore connectivity. Indicates the first Characteristic values ​​of pore exhaust capacity in the region No. The gas release rate of the zone.

[0084] It should be noted that the safety margin for venting through pore connectivity... If the gas release rate exceeds the pore exhaust capacity, there is a risk of gas retention, bubbling, or pore blockage inside the large-sized powder rod to be sintered. At this time, even if the current temperature has not yet reached the normal stage transition temperature, the speed should be reduced, the temperature should be maintained, or the atmosphere / furnace pressure should be adjusted.

[0085] It should also be emphasized that, after calculating the above multi-parameter index values, the defect risk index for each region can be calculated based on the multi-parameter index values ​​and the corresponding weighting coefficients, as follows: .

[0086] in, Indicates the first The defect risk index of the area , , , , and These represent the weighting coefficients corresponding to the values ​​of the multi-parameter indicators, which can be determined based on empirical settings, fitting of historical batch data, expert rules, Bayesian updates, or machine learning models. Through this method, temperature gradient, shrinkage rate, venting capacity, hydroxyl removal, pore connectivity, and axial shrinkage uniformity are unified into a single criterion: the defect risk index for each region.

[0087] Step S304: Determine the current defect risk index of the large-size powder rod to be sintered based on the defect risk index of each region.

[0088] Understandably, after obtaining the defect risk index for each region, the current defect risk index of the large-size powder rod to be sintered can be determined based on the defect risk index for each region, specifically: .

[0089] in, This indicates the current defect risk index of large-size powder rods to be sintered. (The remaining text appears to be incomplete and possibly contains errors. A more accurate translation would require the full context.) When the value is greater than 1, it is determined that there is a risk of defects in the current sintering state. At this time, it is necessary to reduce the heating rate, extend the holding time, and adjust the atmosphere flow rate or furnace pressure. Without real-time collected status parameters, this embodiment can only achieve offline empirical judgment and cannot achieve true online risk closed-loop judgment.

[0090] In this embodiment, during the batch sintering of the large-size powder rod to be sintered according to the executable sintering process window, directly measurable external state parameters of the large-size powder rod to be sintered are collected in real time; the external state parameters are converted into online observation vectors, and internal state parameters are estimated based on the online observation vectors and the external state parameters; multi-parameter index values ​​are calculated based on the external state parameters and the internal state parameters respectively, and defect risk indices for each region are calculated based on the multi-parameter index values ​​and the weighting coefficients corresponding to the multi-parameter index values; the current defect risk index of the large-size powder rod to be sintered is determined based on the defect risk indices for each region. In the above manner, for internal state parameters that cannot be directly measured, external state parameters can be converted into online observation vectors. The internal state parameters are estimated by introducing a digital twin update relationship to estimate the internal state. Then, the defect risk index of each region is calculated based on the values ​​of multiple parameters and the weighting coefficients corresponding to the values ​​of multiple parameters. Temperature gradient, shrinkage rate, venting capacity, hydroxyl removal, pore connectivity and axial shrinkage uniformity are unified into a single judgment quantity, namely the defect risk index of each region. This can effectively improve the accuracy of calculating the current defect risk index of large-size powder rods to be sintered and achieve true online risk closed-loop judgment.

[0091] The following describes the multi-parameter closed-loop control device for large-size powder rod sintering provided in this application. The multi-parameter closed-loop control device for large-size powder rod sintering described below can be referred to in correspondence with the multi-parameter closed-loop control method for large-size powder rod sintering described above. Please refer to... Figure 5 , Figure 5 This is a schematic diagram of the module structure of the multi-parameter closed-loop control device for large-size powder rod sintering provided in this application embodiment, including: The determination module T10 is used to obtain the initial state parameters of the large-size powder rod to be sintered, and to determine the target sintering quality parameters based on the specification parameters of the sintering product of the large-size powder rod to be sintered.

[0092] The setting module T20 is used to set executable sintering process windows for different stages based on the initial state parameters and the target sintering quality parameters.

[0093] The sintering module T30 is used to collect the target state parameters of the large-size powder rod to be sintered in real time during the batch sintering process of the large-size powder rod to be sintered according to the executable sintering process window, and to calculate the current defect risk index of the large-size powder rod to be sintered based on the target state parameters.

[0094] The correction module T40 is used to perform quality inspection on the sintered product when the current defect risk index does not exceed the preset risk threshold, and to reverse correct the sintering process parameters of the next batch of sintered powder rods based on the inspection results.

[0095] This embodiment acquires the initial state parameters of a large-sized powder rod to be sintered, and determines the target sintering quality parameters based on the specification parameters of the sintered product of the large-sized powder rod. It sets executable sintering process windows for different stages based on the initial state parameters and the target sintering quality parameters. During the batch sintering of the large-sized powder rod according to the executable sintering process windows, the target state parameters of the large-sized powder rod are collected in real time, and the current defect risk index of the large-sized powder rod is calculated based on the target state parameters. When the current defect risk index does not exceed a preset risk threshold, the sintered product is subjected to quality inspection, and the sintering process parameters for the next batch of sintered powder rods are corrected in reverse based on the inspection results. By using the above method, the initial state parameters of large-sized powder rods to be sintered are obtained before sintering, and the target sintering quality parameters are determined. The current defect risk index is calculated during sintering, and the sintering process parameters of the next batch of sintered powder rods are corrected after sintering. This realizes the transformation from traditional fixed-program sintering to closed-loop control based on the state of the powder rods, thereby effectively reducing the risk of powder rod sintering and improving the batch stability of the sintered products.

[0096] It is understood that the detailed functional implementation of each of the above modules can be found in the description of the aforementioned method embodiments, and will not be repeated here.

[0097] It should be understood that the above-described device is used to execute the methods in the above embodiments. The implementation principle and technical effect of the corresponding program modules in the device are similar to those described in the above methods. The working process of the device can be referred to the corresponding process in the above methods, and will not be repeated here.

[0098] Based on the methods in the above embodiments, this application provides an electronic device, please refer to... Figure 6 , Figure 6 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application.

[0099] It should be noted that the system may include: a processor 10, a communications interface 20, a memory 30, and a communication bus 40. The processor 10, communications interface 20, and memory 30 communicate with each other via the communication bus 40. The processor 10 can invoke logical instructions stored in the memory 30 to execute the methods described in the above embodiments.

[0100] Furthermore, the logical instructions in the aforementioned memory 30 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application.

[0101] It is understood that the various numerical designations used in the embodiments of this application are merely for descriptive convenience and are not intended to limit the scope of the embodiments of this application. Those skilled in the art will readily understand that the above descriptions are merely preferred embodiments of this application and are not intended to limit this application. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A multi-parameter closed-loop control method for sintering large-size powder rods, characterized in that, include: Obtain the initial state parameters of the large-size powder rod to be sintered, and determine the target sintering quality parameters based on the specification parameters of the sintering product of the large-size powder rod to be sintered. The executable sintering process windows for different stages are set according to the initial state parameters and the target sintering quality parameters; During the batch sintering of the large-size powder rod to be sintered according to the executable sintering process window, the target state parameters of the large-size powder rod to be sintered are collected in real time, and the current defect risk index of the large-size powder rod to be sintered is calculated based on the target state parameters. The current defect risk index refers to the basis for online determination of whether there is a defect risk in the current sintering state. When the current defect risk index does not exceed the preset risk threshold, the sintered product is subjected to quality testing, and the sintering process parameters of the next batch of sintered powder rods are corrected in reverse based on the test results. The step of collecting target state parameters of the large-size powder rods in real time during the batch sintering process according to the executable sintering process window, and calculating the current defect risk index of the large-size powder rods based on the target state parameters, includes: During the batch sintering of the large-sized powder rods to be sintered according to the executable sintering process window, the directly measurable external state parameters of the large-sized powder rods to be sintered are collected in real time; wherein, the external state parameters include multi-zone furnace temperature, powder rod surface temperature, powder rod local diameter or displacement, atmosphere flow rate, furnace pressure, exhaust humidity and exhaust gas composition. The external state parameters are converted into online observation vectors, and the internal state parameters are estimated based on the online observation vectors and the external state parameters; wherein, the internal state parameters include internal porosity, local density, and hydroxyl content; Multi-parameter index values ​​are calculated based on the external state parameters and the internal state parameters, and the defect risk index of each region is calculated based on the multi-parameter index values ​​and the weighting coefficients corresponding to the multi-parameter index values; wherein, the multi-parameter index values ​​include radial shrinkage rate, axial shrinkage uniformity index value, densification-dehydroxylation matching index value, and pore connectivity venting safety margin. The current defect risk index of the large-size powder rod to be sintered is determined based on the defect risk index of each region.

2. The multi-parameter closed-loop control method as described in claim 1, characterized in that, The step of converting the external state parameters into an online observation vector and estimating the internal state parameters based on the online observation vector and the external state parameters includes: The external state parameters are converted into online observation vectors based on the matrix transpose. The estimated state, correction gain, and target observation function of each region at the current time are obtained respectively. The estimation strategy based on digital twin update relationships estimates the internal state parameters according to the online observation vector, the external state parameters, the estimated state of each region at the current time, the correction gain, and the target observation function.

3. The multi-parameter closed-loop control method as described in claim 1, characterized in that, The step of calculating the multi-parameter index values ​​based on the external state parameters and the internal state parameters includes: The equivalent diameter is extracted from the external state parameters, and the radial contraction rate of the partition is calculated based on the equivalent diameter and the target correction parameters. The axial shrinkage uniformity index value is calculated based on the radial shrinkage rate of each of the aforementioned zones; The target density and initial hydroxyl content are extracted from the internal state parameters, and the densification-dehydroxylation matching index value is calculated based on the target density and the initial hydroxyl content.

4. The multi-parameter closed-loop control method as described in claim 1, characterized in that, The multi-parameter index values ​​include: pore connectivity exhaust safety margin; The step of calculating the multi-parameter index values ​​based on the external state parameters and the internal state parameters includes: The characteristic value of pressure difference-driven seepage venting capacity is calculated based on the external state parameters and the internal state parameters, and the characteristic value of pressure gradient-driven diffusion venting capacity is calculated based on the external state parameters and the internal state parameters. The characteristic value of seepage and air release capacity driven by pressure difference is accumulated to obtain the characteristic value of pore air release capacity. The gas release rate is calculated based on the external state parameters and the internal state parameters; The safety margin for pore connectivity venting is calculated based on the characteristic value of the pore venting capacity and the gas release rate.

5. The multi-parameter closed-loop control method as described in any one of claims 1 to 4, characterized in that, The step of performing quality testing on the sintered product when the current defect risk index does not exceed a preset risk threshold, and then reversing the sintering process parameters for the next batch of sintered powder rods based on the test results, includes: When the current defect risk index does not exceed a preset risk threshold, the sintered product is subjected to quality testing. Obtain the characteristic information of the sintered product, and select sintering process parameter correction and evaluation data from the test results based on the characteristic information; A quality deviation objective function is generated based on the modified evaluation data of the sintering process parameters and the target sintering quality parameters. When the quality deviation objective function meets the preset correction conditions, the sintering process parameters of the next batch of sintered powder rods are corrected in reverse according to the quality deviation objective function.

6. The multi-parameter closed-loop control method as described in claim 5, characterized in that, The step of performing quality testing on the sintered product when the current defect risk index does not exceed a preset risk threshold includes: When the current defect risk index does not exceed the preset risk threshold, a current flag for entering the next stage is set according to the stage transition criteria. When the current flag is a preset flag, the process is allowed to proceed to the next stage, and the sintered product is subjected to quality testing.

7. The multi-parameter closed-loop control method as described in claim 1, characterized in that, After the steps of collecting target state parameters of the large-size powder rods in real time and calculating the current defect risk index of the large-size powder rods based on the target state parameters during the batch sintering of the large-size powder rods according to the executable sintering process window, the method further includes: When the current defect risk index of the large-size powder bar to be sintered exceeds the preset risk threshold, the adjustment amount of the sintering process parameters of the large-size powder bar to be sintered is calculated respectively. Based on the aforementioned adjustment amounts, the sintering process parameters of the large-sized powder rod to be sintered are dynamically adjusted within the executable sintering process window.

8. A multi-parameter closed-loop control device for sintering large-size powder rods, characterized in that, include: The determination module is used to obtain the initial state parameters of the large-size powder rod to be sintered, and to determine the target sintering quality parameters based on the specification parameters of the sintering product of the large-size powder rod to be sintered. The setting module is used to set the executable sintering process windows for different stages according to the initial state parameters and the target sintering quality parameters; The sintering module is used to collect the target state parameters of the large-size powder rod to be sintered in real time during the batch sintering process of the large-size powder rod to be sintered according to the executable sintering process window, and to calculate the current defect risk index of the large-size powder rod to be sintered according to the target state parameters. The current defect risk index refers to the basis for online determination of whether there is a defect risk in the current sintering state. The correction module is used to perform quality inspection on the sintered product when the current defect risk index does not exceed the preset risk threshold, and to reverse correct the sintering process parameters of the next batch of sintered powder rods based on the inspection results. The sintering module is further configured to, during the batch sintering of the large-size powder rods to be sintered according to the executable sintering process window, collect directly measurable external state parameters of the large-size powder rods to be sintered in real time; wherein, the external state parameters include multi-zone furnace temperature, powder rod surface temperature, powder rod local diameter or displacement, atmosphere flow rate, furnace pressure, exhaust humidity, and exhaust gas composition; convert the external state parameters into online observation vectors, and estimate internal state parameters based on the online observation vectors and the external state parameters; wherein, the internal state parameters include internal porosity, local density, and hydroxyl content; calculate multi-parameter index values ​​based on the external state parameters and the internal state parameters respectively, and calculate the defect risk index of each region based on the multi-parameter index values ​​and the weighting coefficients corresponding to the multi-parameter index values; wherein, the multi-parameter index values ​​include radial shrinkage rate, axial shrinkage uniformity index value, densification-dehydroxylation matching index value, and pore connectivity exhaust safety margin; determine the current defect risk index of the large-size powder rods to be sintered based on the defect risk index of each region.

9. An electronic device, characterized in that, include: At least one memory for storing computer programs; At least one processor is configured to execute a program stored in the memory, wherein when the program stored in the memory is executed, the processor is configured to perform the method as described in any one of claims 1-7.

Images