Self-adaptive temperature regulation and control method for heat treatment furnace

Abstract

The invention discloses a self-adaptive temperature regulation and control method for a heat treatment furnace, and relates to the technical field of heat treatment furnace regulation and control. The method comprises the following steps: acquiring Q temperature control points of a target heat treatment furnace, and determining a temperature value sequence of the Q temperature control points; carrying out temperature value dense analysis, and determining dense temperature values of temperature control points; obtaining a calibration processing temperature, and carrying out the preliminary recognition of an equipment temperature control parameter adjustment group through combining with the dense temperature values of the temperature control points, and obtaining an initial equipment temperature control parameter adjustment group; performing data synchronous retrieval of Q temperature control points on the historical regulation and control log set to obtain a Q temperature control point attenuation coefficient-equipment temperature control parameter regulation group mapping data set; performing two-item optimization on the initial equipment temperature control parameter adjustment group to obtain a target equipment temperature control parameter adjustment group; and the temperature of the target heat treatment furnace is adjusted and controlled in a self-adaptive mode. The technical problem that in the prior art, the temperature of a heat treatment furnace is difficult to adjust according to the actual situation is solved, and the technical effect of optimizing the heat treatment effect is achieved by conducting self-adaptive adjustment and control on the temperature of the heat treatment furnace.

Description

Technical Field

[0001] The invention relates to the technical field of heat treatment furnace control, and in particular to a heat treatment furnace temperature adaptive control method. Background Art

[0002] As a key link in the field of material processing, heat treatment technology plays an irreplaceable role in improving material performance, improving organizational structure and meeting specific usage requirements. As the core equipment for executing this process, the accuracy and stability of the temperature control of the heat treatment furnace are directly related to the quality and production efficiency of the heat-treated products. However, the temperature control system of the heat treatment furnace in the prior art often has problems such as slow response speed, insufficient adjustment accuracy, and difficulty in adaptive adjustment according to actual working conditions. These problems lead to large temperature fluctuations during the heat treatment process, which in turn affects the mechanical properties of the material and the consistency of processing. In addition, traditional temperature control methods usually rely on preset parameters or a single feedback signal for control, lack the ability to comprehensively analyze and adjust historical temperature control data and real-time working conditions, and are difficult to meet the precise temperature control requirements under complex process conditions. Summary of the invention

[0003] The present application provides a method for adaptively controlling the temperature of a heat treatment furnace, which solves the technical problem in the prior art that it is difficult to adjust the temperature of a heat treatment furnace according to actual conditions.

[0004] In view of the above problems, the present application provides a method for adaptively controlling the temperature of a heat treatment furnace.

[0005] The present application provides a method for adaptively controlling the temperature of a heat treatment furnace, the method comprising: Acquire Q temperature control points of the target heat treatment furnace, collect the temperatures of the Q temperature control points in a preset monitoring window, and determine a sequence of temperature values ​​of the Q temperature control points, where Q is an integer greater than or equal to 1; perform intensive temperature value analysis based on the Q temperature control point temperature value sequence to determine the intensive temperature values ​​of the temperature control points; obtain the calibrated processing temperature of the target heat treatment process, and perform preliminary identification of the equipment temperature control parameter group in combination with the intensive temperature values ​​of the temperature control points to obtain the initial equipment temperature control parameter group; interact with the historical control log set of the target heat treatment furnace, use the temperature control point attenuation coefficient and the equipment temperature control parameter group as mapping synchronization retrieval items, and perform Q temperature control on the historical control log set The data of the points are synchronously retrieved to obtain a mapping data set of Q temperature control point attenuation coefficients and equipment temperature control parameter groups; the mean of the temperature value sequences of the Q temperature control points is traversed and calculated to obtain the mean temperature of the Q temperature control points, and the initial equipment temperature control parameter group is subjected to dual-item optimization in combination with the calibration processing temperature and the Q temperature control point attenuation coefficients and equipment temperature control parameter group mapping data set to obtain a target equipment temperature control parameter group, wherein the goal of the dual-item optimization is to reduce the difference of the attenuation coefficients of the Q temperature control points and to reduce the temperature adjustment time of the target heat treatment furnace; the temperature of the target heat treatment furnace is adaptively controlled based on the target equipment temperature control parameter group.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages: First, obtain Q temperature control points of the target heat treatment furnace, collect the temperatures of the Q temperature control points in the preset monitoring window, and determine the temperature value sequence of the Q temperature control points, where Q is an integer greater than or equal to 1. Next, perform intensive temperature value analysis based on the temperature value sequence of the Q temperature control points to determine the intensive temperature values ​​of the temperature control points. Further, obtain the calibrated processing temperature of the target heat treatment process, and perform preliminary identification of the equipment temperature control parameter group in combination with the intensive temperature values ​​of the temperature control points to obtain the initial equipment temperature control parameter group. Next, interact with the historical control log set of the target heat treatment furnace, use the temperature control point attenuation coefficient and the equipment temperature control parameter group as the mapping synchronization retrieval items, perform data synchronization retrieval of the Q temperature control points on the historical control log set, and obtain the Q temperature control point attenuation coefficient-equipment temperature control parameter group mapping data set. Then, the mean of the temperature value sequence of Q temperature control points is calculated by traversal to obtain the mean temperature of Q temperature control points. The initial equipment temperature control parameter group is optimized by combining the calibration processing temperature and the Q temperature control point attenuation coefficient-equipment temperature control parameter group mapping data set to obtain the target equipment temperature control parameter group, wherein the goal of the two-item optimization is to reduce the difference of the attenuation coefficients of the Q temperature control points and to reduce the temperature adjustment time of the target heat treatment furnace. Finally, the temperature of the target heat treatment furnace is adaptively controlled based on the target equipment temperature control parameter group. The technical problem that it is difficult for the heat treatment furnace to adjust the temperature according to the actual situation in the prior art is solved, and the technical effect of optimizing the heat treatment effect is achieved by adaptively controlling the temperature of the heat treatment furnace. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0008] Figure 1 A schematic diagram of a method for adaptively controlling the temperature of a heat treatment furnace provided in an embodiment of the present application; Figure 2 A schematic diagram of a process for determining dense temperature values ​​of temperature control points in a method for adaptively controlling the temperature of a heat treatment furnace provided in an embodiment of the present application. DETAILED DESCRIPTION

[0009] The present application solves the technical problem in the prior art that it is difficult to adjust the temperature of a heat treatment furnace according to actual conditions by providing a method for adaptively controlling the temperature of a heat treatment furnace.

[0010] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0011] It should be noted that the terms "including" and "having" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or are inherent to these processes, methods, products or devices.

[0012] Examples, such as Figure 1 As shown, the embodiment of the present application provides a method for adaptively controlling the temperature of a heat treatment furnace, wherein the method comprises: Acquire Q temperature control points of the target heat treatment furnace, collect the temperatures of the Q temperature control points in a preset monitoring window, and determine a temperature value sequence of the Q temperature control points, where Q is an integer greater than or equal to 1.

[0013] Select Q temperature control points (Q is an integer greater than or equal to 1) from the target heat treatment furnace. These temperature control points are monitoring locations distributed in different areas of the furnace for collecting temperature data. By collecting the temperature data of these temperature control points within the preset monitoring time window, a temperature value sequence of Q temperature control points is formed to reflect the dynamic changes of temperature during the heat treatment process.

[0014] Based on the temperature value sequences of the Q temperature control points, a temperature value intensive analysis is performed to determine the intensive temperature values ​​of the temperature control points.

[0015] The temperature value intensive analysis is performed on the collected temperature value sequence of Q temperature control points to find the temperature distribution law between the temperature control points and determine the intensive temperature value of the temperature control points, that is, the key temperature parameters extracted after statistical analysis of the temperature data of multiple temperature control points, which are used to reflect the main temperature distribution characteristics in the heat treatment furnace.

[0016] Furthermore, if Figure 2 As shown, based on the temperature value sequences of the Q temperature control points, a temperature value intensive analysis is performed to determine the intensive temperature values ​​of the temperature control points, including: Traverse the Q temperature control point temperature value sequences to perform temperature value fluctuation analysis and obtain Q sequence fluctuation coefficients; when the Q sequence fluctuation coefficients are greater than or equal to a preset sequence fluctuation coefficient threshold, use the temperature control point temperature values ​​in the corresponding Q temperature control point temperature value sequences as an analysis space point, and add them into a dense analysis space; when the Q sequence fluctuation coefficients are less than the preset sequence fluctuation coefficient threshold, calculate the mean of the temperature control point temperature values ​​of the corresponding Q temperature control point temperature value sequences, and use the calculation results as an analysis space point, and add them into a dense analysis space; perform dense analysis on multiple analysis space points in the dense analysis space to determine the dense temperature values ​​of the temperature control points.

[0017] Specifically, the temperature value sequences of the Q temperature control points of the target heat treatment furnace are traversed, and the temperature value fluctuation analysis is performed on each sequence. The sequence fluctuation coefficient can be obtained by extracting all the temperature values ​​in the temperature value sequence of the temperature control points and calculating the variance; when the sequence fluctuation coefficient is greater than or equal to the preset threshold, each temperature value in the corresponding temperature value sequence is regarded as an independent analysis space point and added one by one to the dense analysis space; when the sequence fluctuation coefficient is less than the preset threshold, the mean temperature value of the corresponding temperature control point temperature value sequence is calculated, and the mean is taken as a separate analysis space point and added to the dense analysis space; a dense analysis is performed on all the analysis space points in the dense analysis space, and the high-density area of ​​the temperature value of the temperature control point is determined by statistical and clustering methods, and the central value of the dense area is extracted as the final dense temperature value of the temperature control point.

[0018] Furthermore, performing dense analysis on a plurality of analysis space points in the dense analysis space to determine the dense temperature values ​​of the temperature control points includes: Extract the central analysis space point of the dense analysis space, iterate the central analysis space point according to a preset iteration step, and determine the iterative analysis space point; determine whether the density of the iterative analysis space point is greater than or equal to the density of the central analysis space point, and if so, iterate the iterative analysis space point according to a preset iteration step until a preset number of iterations is met, and use the temperature control point temperature value or the average of the temperature control point temperature values ​​corresponding to the iterative analysis space point obtained in the last iteration as the dense temperature value of the temperature control point.

[0019] Specifically, a central analysis space point is extracted from the dense analysis space as the core point of the initial dense analysis; the temperature value of the temperature control point of the central analysis space point is iteratively calculated according to the preset iteration step to generate a new iterative analysis space point; it is determined whether the density of the current iterative analysis space point is greater than or equal to the density of the central analysis space point, wherein the density is the ratio of the number of space points in the area constructed with the iterative analysis space point as the center and the preset iteration step as the radius to the area of ​​the upper area; if the density meets the conditions, the current iterative analysis space point is continued as the new center, and the iterative calculation is continued according to the preset iteration step to generate a new iterative analysis space point, and this process continues until the preset maximum number of iterations is reached; the temperature value of the temperature control point of the iterative analysis space point obtained in the final iteration or its mean is used as the final temperature control point dense temperature value.

[0020] The calibrated processing temperature of the target heat treatment process is obtained, and the equipment temperature control parameter adjustment group is preliminarily identified in combination with the dense temperature values ​​of the temperature control points to obtain the initial equipment temperature control parameter adjustment group.

[0021] The calibrated processing temperature of the target heat treatment process is obtained and used as the target temperature control reference value. According to the calibrated processing temperature of the heat treatment process and the temperature control point intensive temperature value, a parameter adjustment group for equipment temperature control, namely the initial equipment temperature control parameter adjustment group, is used. The initial equipment temperature control parameter adjustment group includes initial parameter configurations for adjusting the temperature, such as fan speed, heating power, etc.

[0022] Furthermore, the calibrated processing temperature of the target heat treatment process is obtained, and the equipment temperature control parameter group is preliminarily identified in combination with the dense temperature values ​​of the temperature control points to obtain the initial equipment temperature control parameter group, including: Acquire multiple historical dense temperature values ​​of temperature control points, multiple historical calibration processing temperatures, and multiple historical initial equipment temperature control parameter groups as sample data sets; use the sample data sets to supervise the training of the network layer built based on the convolutional neural network, learn the mapping relationship between the dense temperature values ​​of temperature control points and the calibration processing temperatures, and the initial equipment temperature control parameter group until convergence, and obtain a trained parameter group identification network layer; use the parameter group identification network layer to identify the calibration processing temperature and the dense temperature values ​​of the temperature control points, and obtain the initial equipment temperature control parameter group.

[0023] Specifically, multiple historical dense temperature values ​​of temperature control points, historical calibration processing temperatures, and historical initial equipment temperature control parameter groups are obtained from the database as sample data sets, and the sample data sets are used to supervise the training of the parameter group identification network layer constructed based on the convolutional neural network, and the nonlinear mapping relationship between the dense temperature values ​​of temperature control points and the calibration processing temperatures and the initial equipment temperature control parameter group is learned. The network weights are adjusted through iterative optimization until the network output error meets the convergence conditions, and the training of the network layer is completed; the calibration processing temperature and the dense temperature value of the temperature control point of the target heat treatment process are input into the trained network layer, and the learned mapping relationship is used for identification, and the initial equipment temperature control parameter group is automatically generated, providing accurate basic parameter configuration for subsequent optimization.

[0024] The historical control log set of the target heat treatment furnace is interacted with, and the temperature control point attenuation coefficient and the equipment temperature control parameter group are used as mapping synchronization retrieval items. The data of Q temperature control points are synchronously retrieved for the historical control log set to obtain the Q temperature control point attenuation coefficient-equipment temperature control parameter group mapping data set.

[0025] By interacting with the historical control log set of the target heat treatment furnace, the temperature control point attenuation coefficient and the equipment temperature control parameter group (including heating power, cooling rate, holding time, etc.) are used as mapping synchronization retrieval items, and the relevant data of Q temperature control points in the historical control log set are synchronously retrieved; specifically, during the retrieval process, based on the attenuation coefficient of each temperature control point, the corresponding historical equipment parameter group is found, and a complete mapping relationship is established through matching and association analysis; finally, all retrieval results are integrated to form a Q temperature control point attenuation coefficient-equipment temperature control parameter group mapping data set to provide data support for subsequent parameter optimization.

[0026] The mean of the temperature value sequence of the Q temperature control points is traversed and calculated to obtain the mean temperature of the Q temperature control points, and the initial equipment temperature control parameter group is subjected to dual-item optimization in combination with the calibration processing temperature and the Q temperature control point attenuation coefficient-equipment temperature control parameter group mapping data set to obtain a target equipment temperature control parameter group, wherein the goal of the dual-item optimization is to reduce the difference of the attenuation coefficients of the Q temperature control points and to reduce the temperature adjustment time of the target heat treatment furnace.

[0027] Traverse and calculate the mean of the temperature value sequence of the Q temperature control points of the target heat treatment furnace to obtain the temperature mean of each temperature control point; compare these means with the calibrated treatment temperature of the target heat treatment process, and combine the Q temperature control point attenuation coefficient-equipment temperature control parameter group mapping data set to perform a two-item optimization on the initial equipment temperature control parameter group. Specifically, by adjusting the parameters of the equipment parameter group, the difference in the attenuation coefficient of each temperature control point is gradually reduced to ensure the consistency of the temperature control point response. At the same time, the equipment parameter settings are optimized to reduce the adjustment time required for the heat treatment furnace to reach the target temperature. Finally, the target equipment temperature control parameter group is generated after two-item optimization to ensure that the parameter group can better adapt to the actual process requirements and improve the temperature control efficiency and accuracy.

[0028] Further, the mean of the temperature value sequences of the Q temperature control points is traversed and calculated to obtain the mean temperature of the Q temperature control points, and the initial device temperature control parameter group is optimized in two items in combination with the calibration processing temperature and the Q temperature control point attenuation coefficient-device temperature control parameter group mapping data set to obtain the target device temperature control parameter group, including: Based on the temperature mean values ​​of the Q temperature control points, the calibration processing temperature and the Q temperature control point attenuation coefficients-device temperature control parameter group mapping data set, the initial device temperature control parameter group is subjected to fitness analysis to obtain the initial fitness; the initial device temperature control parameter group is subjected to multiple random parameter adjustments according to the preset adjustment range to obtain multiple adjusted device temperature control parameter groups, and the multiple adjusted device temperature control parameter groups are subjected to fitness analysis to obtain multiple adjusted fitnesses; the adjusted device temperature control parameter group corresponding to the maximum value among the multiple adjusted fitnesses is selected as the direction group, and the direction group is used as the adjustment direction, and the remaining multiple adjusted device temperature control parameter groups are subjected to the preset adjustment range. Adjustment is performed to obtain multiple temperature control parameter groups of follow-up adjustment devices; fitness analysis is performed on the multiple temperature control parameter groups of follow-up adjustment devices to obtain multiple follow-up adjustment fitnesses; it is determined whether the maximum value of the multiple follow-up adjustment fitnesses is greater than or equal to the adjustment fitness of the direction group, and if so, the temperature control parameter group of the follow-up adjustment device corresponding to the maximum value of the multiple follow-up adjustment fitnesses is updated as the direction group, and the remaining multiple temperature control parameter groups of the follow-up adjustment devices are continuously adjusted according to the preset adjustment range, and after multiple adjustments until the maximum number of adjustments is reached, the temperature control parameter group of the follow-up adjustment device corresponding to the direction group updated for the last time is used as the temperature control parameter group of the target device.

[0029] Specifically, the mean of the temperature value sequence of the Q temperature control points of the target heat treatment furnace is traversed and calculated to obtain the temperature mean of each temperature control point. The initial equipment temperature control parameter group is analyzed for fitness, and its matching degree with the target state is evaluated. The initial fitness is calculated and obtained. Subsequently, according to the preset parameter adjustment range, the initial equipment temperature control parameter group is subjected to multiple random parameter adjustments to generate multiple adjusted equipment temperature control parameter groups, and the fitness analysis of these adjusted parameter groups is performed one by one to obtain the fitness. Get the corresponding adjustment fitness; select the adjustment device temperature control parameter group corresponding to the maximum fitness value as the direction group, use this direction group as the adjustment direction, and make directional adjustments to the remaining adjustment device temperature control parameter groups according to the preset adjustment range, generate multiple follow-up adjustment device temperature control parameter groups, and analyze their fitness; determine whether the maximum values ​​of these follow-up adjustment fitness values ​​are greater than or equal to the fitness of the direction group. If the conditions are met, update the follow-up adjustment device temperature control parameter group corresponding to the maximum fitness value to the new direction group, and continue to adjust other parameter groups according to the directional adjustment strategy. After multiple iterative adjustments until the maximum number of adjustments is reached, the follow-up adjustment device temperature control parameter group corresponding to the final updated direction group is determined as the target device temperature control parameter group to ensure that it is optimal in terms of fitness and efficiency.

[0030] Further, performing fitness analysis on the initial device temperature control parameter group based on the mean temperature values ​​of the Q temperature control points, the calibration processing temperature and the Q temperature control point attenuation coefficient-device temperature control parameter group mapping data set to obtain the initial fitness includes: Acquire the temperature control point attenuation analysis function; use the initial device temperature control parameter group as the index, perform interpolation retrieval on the Q temperature control point attenuation coefficient-device temperature control parameter group mapping data set, and obtain Q initial temperature control point attenuation coefficients; use the temperature control point attenuation analysis function to analyze the Q temperature control point temperature mean, calibration processing temperature and Q initial temperature control point attenuation coefficients, and obtain Q initial temperature control point adjustment times; calculate the difference of the Q initial temperature control point attenuation coefficients to obtain the initial difference; extract the maximum value of the Q initial temperature control point adjustment times, perform weighted calculation based on the initial difference, and determine the initial fitness.

[0031] Specifically, a temperature control point attenuation analysis function for analyzing the attenuation characteristics of the temperature control points is obtained, and the initial device temperature control parameter group is used as an index to perform interpolation retrieval in the Q temperature control point attenuation coefficient-device temperature control parameter group mapping data set to extract the initial temperature control point attenuation coefficient corresponding to each temperature control point; then, the attenuation analysis function is used to calculate the mean temperature of the Q temperature control points, the calibration processing temperature and the Q initial temperature control point attenuation coefficients, respectively, to obtain the initial temperature control point adjustment time of each temperature control point under the initial device parameter adjustment conditions; further, the difference (variance) of the attenuation coefficients of all temperature control points is calculated, and the consistency of the attenuation coefficients between different temperature control points is quantified to obtain the initial difference; the maximum value of all the initial temperature control point adjustment times is extracted as the key reference for the global adjustment time, and combined with the initial difference for weighted calculation, and finally the initial fitness is determined. The fitness value reflects the adjustment performance of the initial device temperature control parameter group under the current temperature control conditions, and provides a basic evaluation indicator for subsequent optimization.

[0032] Furthermore, the temperature control point attenuation analysis function is: ;in, To calibrate the processing temperature, is the mean temperature of the temperature control point, It is the temperature attenuation coefficient of the temperature control point under the control of the equipment temperature control parameter group. It is the adjustment time required for the temperature control point to reach the calibrated processing temperature under the control of the equipment temperature control parameter adjustment group.

[0033] Input the mean temperature of the temperature control point, the calibration processing temperature and the initial temperature control point attenuation coefficient into the temperature control point attenuation analysis function Calculate and obtain the initial temperature control point adjustment time of each temperature control point under the initial equipment parameter adjustment conditions, where: To calibrate the processing temperature, is the mean temperature of the temperature control point, It is the temperature attenuation coefficient of the temperature control point under the control of the equipment temperature control parameter group. It is the adjustment time required for the temperature control point to reach the calibrated processing temperature under the control of the equipment temperature control parameter adjustment group.

[0034] The temperature of the target heat treatment furnace is adaptively controlled based on the target equipment temperature control parameter adjustment group.

[0035] Load the parameters in the temperature control parameter group of the target device (such as heating power, fan speed, etc.) into the control system of the heat treatment furnace as the initial control configuration; start the heat treatment furnace and monitor the temperature data of Q temperature control points in real time; according to the real-time monitored temperature data, make adaptive adjustments to the device temperature control parameter group. If the temperature of the temperature control point is higher or lower than the calibrated processing temperature, or the temperature fluctuation exceeds the preset range, fine-tune the parameters such as heating power and cooling rate according to the mapping relationship between the temperature control point attenuation coefficient and the device temperature control parameter group, so as to restore the temperature to near the calibrated processing temperature as soon as possible and keep the temperature stable.

[0036] Further, the method comprises: Obtain a preset feedback monitoring time point, wherein the preset feedback monitoring time point is later than the temperature adjustment time corresponding to the temperature control parameter adjustment group of the target device; perform calibration processing temperature verification on Q temperature control points of the target heat treatment furnace at the preset feedback monitoring time point, and obtain early warning information if the verification fails.

[0037] During the temperature control process of the target heat treatment furnace, a preset feedback monitoring time point is first obtained. The time point is set to be later than the temperature adjustment time corresponding to the temperature control parameter group of the target equipment, so as to ensure that the heat treatment furnace enters a stable state after completing the initial temperature adjustment; at the preset feedback monitoring time point, the actual temperatures of the Q temperature control points in the target heat treatment furnace are collected and verified with the calibrated processing temperature; by comparing the actual temperature of each temperature control point with the calibrated processing temperature, it is determined whether the temperature control accuracy requirements are met. If the actual temperature of one or more temperature control points fails to reach the calibrated processing temperature range, it is deemed that the verification has failed, and an early warning message is generated, indicating that the temperature control parameter group of the target equipment needs to be adjusted or the control strategy needs to be re-evaluated to ensure that the temperature accuracy and uniformity of the heat treatment process meet the process requirements.

[0038] In summary, the embodiments of the present application have at least the following technical effects: First, obtain Q temperature control points of the target heat treatment furnace, collect the temperatures of the Q temperature control points in the preset monitoring window, and determine the temperature value sequence of the Q temperature control points, where Q is an integer greater than or equal to 1. Next, perform intensive temperature value analysis based on the temperature value sequence of the Q temperature control points to determine the intensive temperature values ​​of the temperature control points. Further, obtain the calibrated processing temperature of the target heat treatment process, and perform preliminary identification of the equipment temperature control parameter group in combination with the intensive temperature values ​​of the temperature control points to obtain the initial equipment temperature control parameter group. Next, interact with the historical control log set of the target heat treatment furnace, use the temperature control point attenuation coefficient and the equipment temperature control parameter group as the mapping synchronization retrieval items, perform data synchronization retrieval of the Q temperature control points on the historical control log set, and obtain the Q temperature control point attenuation coefficient-equipment temperature control parameter group mapping data set. Then, the mean of the temperature value sequence of Q temperature control points is calculated by traversal to obtain the mean temperature of Q temperature control points. The initial equipment temperature control parameter group is optimized by combining the calibration processing temperature and the Q temperature control point attenuation coefficient-equipment temperature control parameter group mapping data set to obtain the target equipment temperature control parameter group, wherein the goal of the two-item optimization is to reduce the difference of the attenuation coefficients of the Q temperature control points and to reduce the temperature adjustment time of the target heat treatment furnace. Finally, the temperature of the target heat treatment furnace is adaptively controlled based on the target equipment temperature control parameter group. The technical problem that it is difficult for the heat treatment furnace to adjust the temperature according to the actual situation in the prior art is solved, and the technical effect of optimizing the heat treatment effect is achieved by adaptively controlling the temperature of the heat treatment furnace.

[0039] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0040] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0041] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A method for adaptively controlling the temperature of a heat treatment furnace, characterized in that: The method comprises: Acquire Q temperature control points of the target heat treatment furnace, collect the temperatures of the Q temperature control points in a preset monitoring window, and determine a temperature value sequence of the Q temperature control points, where Q is an integer greater than or equal to 1; Performing a temperature value intensive analysis based on the temperature value sequences of the Q temperature control points to determine the intensive temperature values ​​of the temperature control points; Obtaining the calibrated processing temperature of the target heat treatment process, performing preliminary identification of the equipment temperature control parameter adjustment group in combination with the dense temperature values ​​of the temperature control points, and obtaining the initial equipment temperature control parameter adjustment group; Interacting the historical control log set of the target heat treatment furnace, taking the temperature control point attenuation coefficient and the equipment temperature control parameter group as mapping synchronization retrieval items, performing data synchronization retrieval of Q temperature control points on the historical control log set, and obtaining the Q temperature control point attenuation coefficient-equipment temperature control parameter group mapping data set; Traversing and calculating the mean of the temperature value sequences of the Q temperature control points to obtain the mean temperature of the Q temperature control points, and performing a dual-item optimization on the initial device temperature control parameter group in combination with the calibration processing temperature and the Q temperature control point attenuation coefficient-device temperature control parameter group mapping data set to obtain a target device temperature control parameter group, wherein the dual-item optimization aims to reduce the difference of the attenuation coefficients of the Q temperature control points and reduce the temperature adjustment time of the target heat treatment furnace; The temperature of the target heat treatment furnace is adaptively controlled based on the target equipment temperature control parameter adjustment group.

2. A method for adaptively controlling the temperature of a heat treatment furnace according to claim 1, characterized in that: Performing a temperature value intensive analysis based on the Q temperature control point temperature value sequences to determine the temperature control point intensive temperature values ​​includes: Traversing the Q temperature control point temperature value sequences to perform temperature value fluctuation analysis and obtain Q sequence fluctuation coefficients; When the Q sequence fluctuation coefficients are greater than or equal to a preset sequence fluctuation coefficient threshold, the temperature values ​​of the corresponding Q temperature control point temperature value sequences are respectively taken as analysis space points and added into the dense analysis space; When the Q sequence fluctuation coefficients are less than the preset sequence fluctuation coefficient threshold, the mean values ​​of the temperature control point values ​​of the corresponding Q temperature control point temperature value sequences are calculated, and the calculation results are respectively used as analysis space points and added into the dense analysis space; Dense analysis is performed on a plurality of analysis space points in the dense analysis space to determine dense temperature values ​​of the temperature control points.

3. A method for adaptively controlling the temperature of a heat treatment furnace according to claim 2, characterized in that: Performing dense analysis on a plurality of analysis space points in the dense analysis space to determine the dense temperature values ​​of the temperature control points, the method comprising: Extracting a central analysis space point of the dense analysis space, iterating the central analysis space point according to a preset iteration step length, and determining an iterative analysis space point; Determine whether the density of the iterative analysis space points is greater than or equal to the density of the central analysis space points. If so, iterate the iterative analysis space points according to the preset iteration step until the preset number of iterations is met, and use the temperature control point temperature value or the average of the temperature control point temperature values ​​corresponding to the iterative analysis space points obtained in the last iteration as the temperature control point dense temperature value.

4. A method for adaptively controlling the temperature of a heat treatment furnace according to claim 1, characterized in that: The method comprises: traversing and calculating the mean of the temperature value sequences of the Q temperature control points to obtain the mean temperature of the Q temperature control points; combining the calibration processing temperature and the Q temperature control point attenuation coefficient-device temperature control parameter group mapping data set to perform dual-item optimization on the initial device temperature control parameter group to obtain the target device temperature control parameter group. The method comprises: Performing fitness analysis on the initial device temperature control parameter group based on the mean temperature values ​​of the Q temperature control points, the calibration processing temperature, and the Q temperature control point attenuation coefficients-device temperature control parameter group mapping data sets to obtain an initial fitness; Performing multiple random parameter adjustments on the initial device temperature control parameter adjustment group according to a preset adjustment range to obtain multiple adjusted device temperature control parameter adjustment groups, and performing fitness analysis on the multiple adjusted device temperature control parameter adjustment groups to obtain multiple adjustment fitnesses; The temperature control parameter adjustment group of the adjustment device corresponding to the maximum value among the multiple adjustment fitnesses is selected as the direction group, and the direction group is used as the adjustment direction. The remaining multiple temperature control parameter adjustment groups of the adjustment devices are adjusted according to the preset adjustment range to obtain multiple follow-up temperature control parameter adjustment groups of the adjustment devices; Performing fitness analysis on the multiple temperature control parameter adjustment groups of the follow-up adjustment devices to obtain multiple follow-up adjustment fitnesses; Determine whether the maximum value of the multiple follow-up adjustment fitness is greater than or equal to the adjustment fitness of the direction group. If so, update the follow-up adjustment device temperature control parameter group corresponding to the maximum value of the multiple follow-up adjustment fitness to the direction group, and continue to adjust the remaining multiple follow-up adjustment device temperature control parameter groups according to the preset adjustment range. After multiple adjustments until the maximum number of adjustments is reached, the follow-up adjustment device temperature control parameter group corresponding to the last updated direction group is used as the target device temperature control parameter group.

5. A method for adaptively controlling the temperature of a heat treatment furnace according to claim 4, characterized in that: Based on the mean temperature values ​​of the Q temperature control points, the calibration processing temperature and the Q temperature control point attenuation coefficients-device temperature control parameter group mapping data sets, the initial device temperature control parameter group is subjected to fitness analysis to obtain an initial fitness, the method comprising: Get the temperature control point attenuation analysis function; Using the initial device temperature control parameter group as an index, perform interpolation retrieval on the Q temperature control point attenuation coefficients-device temperature control parameter group mapping data set to obtain the Q initial temperature control point attenuation coefficients; The temperature control point attenuation analysis function is used to analyze the mean temperature values ​​of the Q temperature control points, the calibration processing temperature and the attenuation coefficients of the Q initial temperature control points to obtain the adjustment time of the Q initial temperature control points; Calculating the difference of the attenuation coefficients of the Q initial temperature control points to obtain an initial difference; The maximum value of the adjustment time of the Q initial temperature control points is extracted, and a weighted calculation is performed in combination with the initial difference to determine the initial fitness.

6. A method for adaptively controlling the temperature of a heat treatment furnace according to claim 5, characterized in that: The temperature control point attenuation analysis function is: ； in, To calibrate the processing temperature, is the mean temperature of the temperature control point, It is the temperature attenuation coefficient of the temperature control point under the control of the equipment temperature control parameter group. It is the adjustment time required for the temperature control point to reach the calibrated processing temperature under the control of the equipment temperature control parameter adjustment group.

7. A method for adaptively controlling the temperature of a heat treatment furnace according to claim 1, characterized in that: The calibrated processing temperature of the target heat treatment process is obtained, and the equipment temperature control parameter adjustment group is preliminarily identified in combination with the temperature control point dense temperature value to obtain the initial equipment temperature control parameter adjustment group. The method includes: Acquire multiple historical temperature control point intensive temperature values, multiple historical calibration processing temperatures, and multiple historical initial device temperature control parameter adjustment groups as sample data sets; The sample data set is used to perform supervised training on the network layer built based on the convolutional neural network, and the mapping relationship between the dense temperature values ​​of the temperature control points and the calibration processing temperature, and the initial equipment temperature control parameter group is learned until convergence, so as to obtain a trained parameter group identification network layer; The calibration processing temperature and the temperature control point intensive temperature value are identified by using the parameter group identification network layer to obtain the initial equipment temperature control parameter group.

8. A method for adaptively controlling the temperature of a heat treatment furnace according to claim 1, characterized in that: The method comprises: Obtaining a preset feedback monitoring time point, wherein the preset feedback monitoring time point is later than the temperature adjustment time corresponding to the temperature control parameter adjustment group of the target device; At the preset feedback monitoring time point, the Q temperature control points of the target heat treatment furnace are calibrated for temperature verification. If the verification fails, an early warning message is obtained.

Images