Intelligent control system for long-axis metal workpiece heat treatment equipment

Abstract

The invention relates to the technical field of metal workpiece heat treatment, in particular to an intelligent control system for long-axis metal workpiece heat treatment equipment. The method comprises the following steps: firstly, acquiring temperature data and strain data of each measuring point on a workpiece at each monitoring moment; then, at each monitoring moment, the heating characteristic coefficient of each measuring point is obtained, and the thermal strain influence index of the workpiece is obtained by further combining the historical change correlation between the temperature data and the strain data of each measuring point, the strain data of each measuring point and the distance between each measuring point and the heating source; and according to the difference of the temperature data between the measuring points and the thermal strain influence index, obtaining a thermal treatment abnormal coefficient of each measuring point, thereby adjusting equipment parameters. By quantifying the influence degree of the position on the surface temperature of the workpiece in the heat treatment process, the parameters of the heat treatment equipment are adjusted, the heat treatment effect on the long-axis workpiece is improved, and the heat stress difference of the long-axis metal workpiece in heat treatment is reduced.

Description

Technical Field

[0001] This invention relates to the field of heat treatment technology for metal workpieces, and more specifically to an intelligent control system for heat treatment equipment for long-shaft metal workpieces. Background Technology

[0002] Heat treatment of metals is a process that adjusts the microstructure of metals through heating, holding, and cooling. By properly controlling heat treatment parameters such as temperature and time, the properties of metal materials can be optimized, service life can be extended, and the quality of metal products can be improved. Therefore, proper control of heat treatment of metal workpieces is of paramount importance.

[0003] Traditional heat treatment equipment uses relatively simple heating methods, such as common resistance heating, where heat is mainly transferred through radiation and convection. However, due to the structural characteristics of long-shaft metal workpieces, it is difficult for different parts to be heated and cooled evenly during the heat treatment process. The parts of the workpiece closer to the heating source will heat up faster, while the parts of the workpiece relatively far from the heating source may heat up relatively slowly. Uneven heating may cause large deformation of the workpiece, resulting in poor heat treatment effect for long-shaft metal workpieces. Summary of the Invention

[0004] To address the technical problem of poor heat treatment results for long-shaft workpieces, the present invention aims to provide an intelligent control system for heat treatment equipment for long-shaft metal workpieces. The specific technical solution adopted is as follows:

[0005] An intelligent control system for heat treatment equipment for long-shaft metal workpieces, the system comprising:

[0006] Process data acquisition module: used to acquire temperature and strain data at each measuring point on the workpiece at each monitoring time;

[0007] The workpiece heat analysis module is used to obtain the heating characteristic coefficient of each measuring point at each monitoring time based on the historical trend of temperature data at each measuring point and the historical changes in the discrete characteristics of temperature data at all measuring points; to obtain the thermal strain influence index of the workpiece based on the historical correlation between temperature data and strain data at each measuring point and the heating characteristic coefficient, combined with the strain data of each measuring point and its distance from the heating source; and to obtain the heat treatment anomaly coefficient of each measuring point based on the difference in temperature data between each measuring point and adjacent measuring points, and the thermal strain influence index.

[0008] Heat treatment control module: used to adjust equipment parameters at each monitoring time based on the heat treatment anomaly coefficient of each measuring point.

[0009] Furthermore, the method for obtaining the heating characteristic coefficient includes:

[0010] For each measuring point, at each monitoring time, a temperature change curve is fitted based on the temperature data of all historical monitoring times during the historical heat treatment process, and the temperature change rate parameter is obtained according to the change trend of the temperature change curve.

[0011] During the historical heat treatment process, at each historical monitoring moment, the variance of the temperature data at all measuring points is used as the temperature non-uniformity parameter. Based on the temperature non-uniformity parameter at all historical monitoring moments, a temperature non-uniformity change curve is fitted, and the uniform heating parameter of the workpiece is obtained according to the change trend of the temperature non-uniformity change curve.

[0012] By weighting the temperature change rate parameter with the uniform heating parameter, the heating characteristic coefficient of each measuring point is obtained.

[0013] Furthermore, the method for obtaining the temperature change rate parameter includes:

[0014] At each monitoring moment, the slope of each temperature change curve is used as the first rate parameter, and the negative correlation mapping result between the temperature data and the preset target temperature is used as the second rate parameter.

[0015] By combining the first rate parameter and the second rate parameter, the temperature change rate parameter is obtained.

[0016] Furthermore, the method for obtaining the uniform heating parameters includes:

[0017] The negative correlation mapping result of the slope value of the temperature non-uniformity change curve is used as the uniform heating parameter.

[0018] Furthermore, the method for obtaining the thermal strain influence index includes:

[0019] For each measuring point, at each monitoring time, based on the temperature and strain data from all historical monitoring times, a temperature time series and a strain time series are fitted, and the thermal strain correlation parameters are determined based on the Pearson correlation coefficient between the two series.

[0020] At each monitoring time, the heating characteristic coefficient, the thermal strain correlation parameter, and the maximum strain value in the strain time sequence of each measuring point are integrated to obtain the thermal strain characteristic parameter.

[0021] The measuring points are sorted in ascending order based on their distance from the heating source in the heat treatment equipment. The thermal strain characteristic parameter curve is fitted based on the sorting order of the measuring points, and the thermal strain influence index is obtained according to the rate of change of the thermal strain characteristic parameter curve.

[0022] Furthermore, based on the rate of change of the thermal strain characteristic parameter curve, the thermal strain influence index of the workpiece is obtained, including:

[0023] The negative correlation mapping result of the slope of the thermal strain characteristic parameter curve is used as the thermal strain influence index.

[0024] Furthermore, the method for setting up the measuring points includes:

[0025] In the axial direction of a long-shaft metal workpiece, measuring points are evenly distributed on opposite sides of the workpiece surface to obtain two rows of measuring points. The two rows of measuring points are axially symmetrical along the center line of the workpiece.

[0026] Furthermore, the method for obtaining the heat treatment anomaly coefficient includes:

[0027] For each measuring point, at each monitoring time, the temperature gradient is obtained based on the difference in temperature data between it and the adjacent measuring points in the axial direction, and the temperature transmission influence parameter is obtained based on the temperature gradient difference between the measuring point and the other measuring points.

[0028] At each monitoring moment, the thermal strain influence index, the temperature transmission influence parameter of each measuring point, and the temperature gradient are integrated to obtain the heat treatment anomaly coefficient of the corresponding measuring point.

[0029] Furthermore, the method for obtaining the temperature gradient includes:

[0030] For each measuring point, at each monitoring time, two measuring points closest to it in its axial direction are determined as reference measuring points, and the average absolute value of the difference between the temperature data of the measuring point and the reference measuring points is taken as the temperature gradient.

[0031] Furthermore, the equipment parameters are adjusted according to the heat treatment anomaly coefficient at each measuring point, including:

[0032] The equipment parameters include at least the rotational speed of the stage and the heating temperature of the heat treatment equipment;

[0033] All pairs of opposite measuring points between two sets of measuring points are obtained, and the opposite heat treatment deviation is obtained based on the difference between the heat treatment anomaly coefficients of each pair of opposite measuring points; the normalized value of the opposite heat treatment deviation is added to a constant 1 to obtain the rotational speed adjustment weight; the rotational speed of the stage at the monitoring time is weighted using the rotational speed adjustment weight to obtain the adjusted stage rotational speed.

[0034] Based on the discrete characteristics of the heat treatment anomaly coefficients at all measuring points, the heat treatment non-uniformity parameter is obtained. The difference between the constant 1 and the normalized value of the heat treatment non-uniformity parameter is multiplied by a preset sensitive parameter to obtain the temperature adjustment weight. The heating temperature at the monitoring time is weighted using the temperature adjustment weight to obtain the adjusted heating temperature.

[0035] The present invention has the following beneficial effects:

[0036] This invention first acquires temperature and strain data at each measuring point on the workpiece at each monitoring time, providing a foundation for subsequent analysis of the heat treatment process and adjustment of equipment parameters. Then, at each monitoring time, based on the historical trend of temperature data at each measuring point and the historical variation of the discrete characteristics of temperature data at all measuring points, a heating characteristic coefficient is obtained for each measuring point. This heating characteristic coefficient reflects the heating effect at the measuring point, preparing for subsequent evaluation of heat treatment anomalies in conjunction with workpiece strain information. Based on the historical correlation between temperature and strain data at each measuring point and the heating characteristic coefficient, combined with the strain data at each measuring point and its distance from the heating source, a thermal strain influence index is obtained for the workpiece. This thermal strain influence index initially reflects the influence of the measuring point location on thermal deformation. Furthermore, by combining the differences in temperature data between each measuring point and adjacent measuring points, a heat treatment anomaly coefficient is obtained for each measuring point. This heat treatment anomaly coefficient quantifies the probability of heat treatment deviation at the corresponding measuring point relative to other measuring points, thereby adjusting equipment parameters based on the heat treatment anomaly coefficient for each measuring point. This invention improves the heat treatment effect on long-shaft workpieces by quantifying the degree of influence of location on the surface temperature of the workpiece during heat treatment, thereby reducing the thermal stress differences of long-shaft metal workpieces during heat treatment. Attached Figure Description

[0037] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0038] Figure 1 A system module diagram of an intelligent control system for a heat treatment equipment for long-shaft metal workpieces, provided in one embodiment of the present invention;

[0039] Figure 2 This is a flowchart illustrating a method for obtaining heating characteristic coefficients according to an embodiment of the present invention. Detailed Implementation

[0040] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of an intelligent control system for a heat treatment equipment for long-axis metal workpieces proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0041] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0042] The following description, in conjunction with the accompanying drawings, details a specific solution for an intelligent control system for heat treatment equipment of long-shaft metal workpieces provided by the present invention.

[0043] Please see Figure 1 The diagram illustrates a system block diagram of an intelligent control system for a heat treatment equipment for long-shaft metal workpieces according to an embodiment of the present invention. The system includes a process data acquisition module 101, a workpiece heat analysis module 102, and a heat treatment control module 103.

[0044] Process data acquisition module 101: used to acquire temperature and strain data of each measuring point on the workpiece at each monitoring time.

[0045] It should be noted that the embodiments of the present invention are aimed at long-axis metal workpieces, referred to as workpieces; the stage of the heat treatment equipment targeted by the embodiments of the present invention has a rotation function, which can rotate during the heat treatment process to improve the uniformity of the workpiece heating; the analysis and control method of the heat treatment process for each workpiece is the same, and only one workpiece is used as an example for analysis and description here.

[0046] In one embodiment of the present invention, before the workpiece enters the heat treatment equipment, several measuring points are set on the surface of the workpiece, and a sensor is installed at each measuring point to collect temperature data and strain data of the workpiece surface, thereby analyzing the heat treatment effect of the workpiece in real time, and preparing for subsequent real-time adjustment of equipment parameters to achieve uniform heating and reduce deformation.

[0047] Preferably, in one embodiment of the present invention, considering that the uniform heating of the workpiece in the heat treatment equipment is limited by the position of the heating source, the measuring point layout scheme is determined in combination with the structural characteristics of the workpiece; the measuring point layout method includes:

[0048] In the axial direction of a long-shaft metal workpiece, measuring points are evenly distributed on opposite sides of the workpiece surface to obtain two rows of measuring points. The two rows of measuring points are axially symmetrical along the center line of the workpiece.

[0049] Specifically, taking a cylindrical workpiece as an example, a measuring point is set up at any position 0.2m from the bottom on the side surface of the workpiece, and this measuring point is used as the first measuring point. In the axial direction of the long shaft metal workpiece, the remaining measuring points are evenly arranged at intervals of 0.2m to obtain the first column of measuring points. On the opposite side of the first column of measuring points, the second column of measuring points is obtained in the same way, so that the two columns of measuring points are axially symmetrical along the center line of the cylindrical workpiece. That is, the straight-line distance between a set of opposite measuring points every 0.2m on the side surface of the workpiece is equal to the bottom diameter of the cylindrical workpiece. The implementer can also adjust the measuring point layout scheme according to the shape and length of the workpiece, such as adjusting the number of columns of measuring points and the interval between adjacent measuring points in each column.

[0050] After determining the measurement point layout plan, high-precision thermocouples (temperature sensors) are installed at the measurement points to collect temperature data. The temperature sensors are connected to the data acquisition card through high-temperature resistant shielded cables. The data acquisition card converts the analog signals from the sensors into digital signals and transmits them to the data center via wired connection. Foil strain gauges (strain sensors) are installed at the measurement points to collect strain data. The strain gauges are connected to the strain acquisition module through dedicated wires. The strain acquisition module amplifies and filters the weak electrical signals output by the strain gauges and converts them into digital signals for transmission to the data center.

[0051] It should be noted that when installing the sensors, the oxide layer and oil stains on the surface of the measuring points need to be removed to ensure a firm adhesion; the acquisition frequency of all sensors should be set to once per second, and acquisition should be carried out synchronously after the self-heating treatment begins; the implementer can also adjust it himself; all temperature and strain data received by the data center should be cleaned and dimensionless for subsequent analysis and calculation.

[0052] The workpiece heat analysis module 102 is used to obtain the heating characteristic coefficient of each measuring point at each monitoring time based on the historical trend of temperature data at each measuring point and the historical changes of the discrete characteristics of temperature data at all measuring points; to obtain the thermal strain influence index of the workpiece based on the historical correlation between temperature data and strain data at each measuring point and the heating characteristic coefficient, combined with the strain data of each measuring point and its distance from the heating source; and to obtain the heat treatment anomaly coefficient of each measuring point based on the difference in temperature data between each measuring point and adjacent measuring points, as well as the thermal strain influence index.

[0053] It should be noted that the analysis and control methods for the heat treatment process of the workpiece are the same at each monitoring moment. Here, we will only take any monitoring moment as an example for analysis and description, and will not go into detail again.

[0054] Considering that the distribution and changes in workpiece temperature are crucial during the heat treatment process, analyzing the workpiece temperature distribution can provide a preliminary assessment of the uniformity of heating. The temperature change trend at each measuring point on the workpiece reflects the local thermal inertia of the workpiece, i.e., its sensitivity to heat. Both can be used to prepare for subsequent assessment of heat treatment anomalies in conjunction with workpiece strain information in order to adjust the relevant parameters of the heat treatment equipment.

[0055] Based on this, the embodiments of the present invention will obtain the heating characteristic coefficient of each measuring point according to the historical change trend of temperature data at each measuring point and the historical change of discrete characteristics of temperature data at all measuring points.

[0056] Preferably, in one embodiment of the present invention, the method for obtaining the heating characteristic coefficient includes:

[0057] Please see Figure 2 The diagram illustrates a flowchart of a method for obtaining a heating characteristic coefficient according to an embodiment of the present invention, specifically including:

[0058] Step S201: For each measuring point, at each monitoring time, fit the temperature change curve based on the temperature data of all historical monitoring times during the historical heat treatment process, and obtain the temperature change rate parameter according to the change trend of the temperature change curve.

[0059] For each measuring point, the trend of temperature data during the historical heat treatment process at each monitoring moment can reflect the local temperature change rate of the workpiece. At the same time, the closer the temperature data at that monitoring moment is to the set target temperature, the faster the temperature change rate and the higher the heating efficiency. This prepares for further evaluation of the heating effect and determination of heating characteristic parameters by combining the synchronous temperature changes at all measuring points.

[0060] In a preferred embodiment of the present invention, the method for obtaining the temperature change rate parameter includes:

[0061] At each monitoring moment, the slope of each temperature change curve is used as the first rate parameter, and the negative correlation mapping result between the temperature data and the preset target temperature is used as the second rate parameter; the first rate parameter and the second rate parameter are fused to obtain the temperature change rate parameter.

[0062] Specifically, for each measuring point, firstly, during the historical heat processing at each monitoring moment, the temperature data of all historical monitoring moments are used as data points. The temperature change curve is fitted based on the least squares method. Then, the slope between the first and last temperature data points of the temperature change curve is calculated based on the two-point method to obtain the first rate parameter. Then, the absolute value of the difference between the temperature data at this monitoring moment and the preset target temperature is mapped to the exponential function exp(-x) with the natural constant e as the base to obtain the second rate parameter. The first rate parameter and the second rate parameter are multiplied to obtain the temperature change rate parameter.

[0063] It should be noted that during the heat treatment process, the surface temperature of the workpiece cannot be lower than the initial surface temperature when it enters the heat treatment equipment, so the first rate parameter cannot be negative. The least squares fitting curve, the two-point slope calculation, and the negative correlation mapping method are all well-known techniques and will not be described in detail here. In other embodiments, the implementer may also use other negative correlation mapping methods, or may use an additive approach to fuse the two rate parameters.

[0064] Step S202: At each historical monitoring moment during the historical heat treatment process, the variance of the temperature data at all measuring points is used as the temperature non-uniformity parameter. Based on the temperature non-uniformity parameter at all historical monitoring moments, a temperature non-uniformity change curve is fitted, and the uniform heating parameter is obtained according to the change trend of the temperature non-uniformity change curve.

[0065] Under normal circumstances, due to the location limitations of the heating source, the heating rate of the measuring point far from the heating source may be lower than that of the measuring point close to the heating source, resulting in certain differences in temperature data at different measuring points. However, as the heat released by the heating source is rapidly transferred to the surface of the workpiece and then conducted into the interior, the temperature of each measuring point of the workpiece shows a rapid upward trend, and the temperature difference at each measuring point should gradually decrease, and the workpiece tends to be heated uniformly.

[0066] Furthermore, considering that the variance of temperature data at all measuring points at the same monitoring time can reflect discrete characteristics, the larger the variance, the more uneven the workpiece heating and heat conduction. If the uneven heating and heat conduction of the workpiece does not improve as the heat treatment process progresses, it indicates that the uniform heating is poor. Therefore, the uniform heating parameters of the workpiece can be obtained at each monitoring time. The uniform heating parameters further reflect the heating effect of the workpiece, preparing for the subsequent comprehensive evaluation of heating characteristic parameters in combination with the temperature change rate parameters.

[0067] Specifically, firstly, during the historical heat processing at each monitoring moment, the variance of the temperature data at all measuring points at each historical monitoring moment is used as the temperature non-uniformity parameter; then, the temperature non-uniformity parameter at all historical monitoring moments is used as the data points, and the temperature non-uniformity change curve is fitted based on the least squares method; this is a well-known technique and will not be elaborated further.

[0068] Considering that the temperature unevenness should improve and decrease as the heat treatment process progresses, and that the slope can reflect the trend of change, in a preferred embodiment of the present invention, the negative correlation mapping result of the slope value of the temperature unevenness change curve is used as the uniform heating parameter.

[0069] Specifically, based on the slope of the change between the first and last two temperature non-uniformity parameters of the two-point calculation temperature non-uniformity change curve, the slope is mapped to the exponential function exp(-x) with the natural constant e as the base to obtain the uniform heating parameters. These are all well-known techniques, and implementers can also use other negative correlation mapping methods.

[0070] When the slope of the change is negative and the corresponding absolute value is larger, the downward trend of the temperature unevenness change curve is more obvious, the improvement of the workpiece heating unevenness is greater, and the uniform heating parameter is larger.

[0071] Step S203: The heating characteristic coefficient of each measuring point is obtained by weighting the temperature change rate parameter with the uniform heating parameter.

[0072] When the workpiece is uniformly heated, the faster the temperature change rate, the better the heating effect at that measuring point. Therefore, the heating characteristic coefficient of each measuring point is obtained by multiplying the temperature change rate parameter of each measuring point with the uniform heating parameter of the workpiece.

[0073] At this point, the heating characteristic coefficients of each measuring point are obtained.

[0074] Considering that the atomic arrangement inside the metal changes with temperature, leading to workpiece deformation, for each measuring point on the workpiece surface, the greater the correlation between the historical changes in temperature and strain data, the more likely the strain at that measuring point is caused by temperature changes. Furthermore, the larger the strain data at that measuring point, the greater its sensitivity to temperature-induced deformation. Considering that higher heating effects can avoid the situation where strain is not obvious at low temperatures, thus improving the correlation analysis between temperature and strain, and further combining the distance between the measuring point and the heating source, the relationship between the thermal deformation sensitivity of the measuring point on the workpiece and the distance can be accurately analyzed, and the influence of the measuring point location on thermal deformation can be evaluated.

[0075] Based on this, according to the historical correlation between temperature data and strain data at each measuring point and the heating characteristic coefficient, combined with the strain data at each measuring point and its distance from the heating source, the thermal strain influence index of the workpiece is obtained; the thermal strain influence index reflects the possibility that the workpiece may still deform due to uneven heating caused by structural limitations during the heat treatment process.

[0076] Preferably, in one embodiment of the present invention, considering that the heating characteristic coefficient can reflect the heat treatment effect, the Pearson correlation coefficient can reflect the correlation of data changes, and the maximum strain data can reflect the deformation limit of the measuring point in the historical heat treatment process, the larger the strain data, the greater the degree of influence of temperature, and thus the sensitivity of the measuring point to deformation caused by temperature can be assessed, and the thermal strain characteristic parameters can be determined; then the relationship between the thermal strain characteristic parameters of the measuring point on the workpiece and the distance is analyzed. When the distance of the measuring point is farther and the thermal strain characteristic parameter is smaller, it indicates that the position of the measuring point has a greater influence on the thermal deformation, and thus the thermal strain influence index can be assessed; based on this, the method for obtaining the thermal strain influence index includes:

[0077] For each measuring point, at each monitoring time, based on the temperature and strain data from all historical monitoring times, a temperature time series and a strain time series are fitted, and the thermal strain correlation parameters are determined based on the Pearson correlation coefficient between the two series.

[0078] At each monitoring moment, the heating characteristic coefficients, thermal strain correlation parameters, and maximum strain values ​​in the strain time series of each measuring point are integrated to obtain thermal strain characteristic parameters.

[0079] The measuring points are sorted in ascending order based on their distance from the heating source in the heat treatment equipment. The thermal strain characteristic parameter curve is fitted based on the sorting order of the measuring points, and the thermal strain influence index is obtained according to the rate of change of the thermal strain characteristic parameter curve.

[0080] Specifically, for each measuring point, during the historical heat processing at each monitoring moment, the temperature data from all historical monitoring moments are used as sequence elements and fitted in chronological order to form a temperature time series. Similarly, a strain time series is fitted. The Pearson correlation coefficient between the two series is used as the thermal strain correlation parameter. The closer the Pearson correlation coefficient is to 1, the stronger the correlation between changes. Therefore, the Pearson correlation coefficient is mapped to... Adjust the value range to 0-1 to obtain the thermal strain correlation parameters;

[0081] Then, at each monitoring time, the heating characteristic coefficient, thermal strain correlation parameter, and maximum strain value in the strain time series of each measuring point are multiplied and combined to obtain the thermal strain characteristic parameter. The larger the thermal strain characteristic parameter, the greater the sensitivity of the measuring point to deformation caused by temperature under higher heating effect.

[0082] Then, the distance between the measuring points and the heating source in the heat treatment equipment (Euclidean distance in three-dimensional space) is calculated, and the measuring points are sorted in ascending order of distance, with the smaller the distance, the earlier the point is sorted. Then, the thermal strain characteristic parameters of each measuring point are sorted according to the sorting order of the measuring points, and the thermal strain characteristic parameters are used as data points to fit the thermal strain characteristic parameter curve based on the least squares method.

[0083] In a preferred embodiment of the present invention, considering that when the distance between the measuring points is greater and the thermal strain characteristic parameter is smaller, that is, when the thermal strain characteristic parameter curve shows a downward trend, it indicates that the measuring point position has a greater influence on the thermal deformation, the negative correlation mapping result of the slope of the thermal strain characteristic parameter curve is used as the thermal strain influence index.

[0084] Specifically, the slope of the thermal strain characteristic parameter curve is calculated using a two-point method. The slope is then mapped to an exponential function exp(-x) with the natural constant e as the base, resulting in the thermal strain influence index. The greater the thermal strain influence index, the more the thermal strain characteristic parameter curve shows a downward trend.

[0085] Considering that the greater the temperature difference between each measuring point and its neighboring measuring points at each monitoring moment, it provides a further lateral reference for the influence of position on workpiece deformation due to temperature. When the thermal strain influence index is larger and the temperature difference between measuring points is larger, it indicates that the heat treatment effect of that measuring point is worse, and it is more likely that the heating will deviate from other measuring points due to positional limitations, resulting in local deformation. Based on this, the embodiments of the present invention will obtain the heat treatment anomaly coefficient of each measuring point according to the temperature data difference between each measuring point and its neighboring measuring points, as well as the thermal strain influence index, in order to prepare for subsequent adjustment of heat treatment equipment parameters to improve the heat treatment effect.

[0086] Preferably, in one embodiment of the present invention, considering that the axial temperature distribution on long-shaft workpieces better reflects the influence of position on thermal strain, the heat transfer of the workpiece can be evaluated at each monitoring moment based on the temperature data difference between the measuring point and adjacent measuring points in the axial direction. When the thermal strain influence index of the workpiece is large, the larger the temperature transfer influence parameter, the worse the heat treatment effect at that measuring point, and the larger the heat treatment anomaly coefficient. The method for obtaining the heat treatment anomaly coefficient includes:

[0087] For each measuring point, at each monitoring time, the temperature gradient is obtained based on the difference in temperature data between it and its adjacent measuring points in the axial direction, and the temperature transmission influence parameters are obtained based on the temperature gradient difference between the measuring point and the other measuring points.

[0088] At each monitoring moment, the thermal strain influence index, temperature transmission influence parameters and temperature gradient of each measuring point are integrated to obtain the heat treatment anomaly coefficient of the corresponding measuring point.

[0089] In a preferred embodiment of the present invention, the method for obtaining the temperature gradient includes:

[0090] For each measuring point, at each monitoring time, two measuring points closest to it in its axial direction are determined as reference measuring points, and the average absolute value of the temperature difference between the measuring point and the reference measuring points is taken as the temperature gradient.

[0091] At each monitoring time, after acquiring the temperature gradient of each measuring point, the absolute value of the difference between the temperature gradient of each measuring point and all other measuring points is calculated. The average of the absolute values ​​of the difference is taken as the temperature transmission influence parameter at that measuring point. The larger the temperature transmission influence parameter, the more abnormal the temperature transmission at that measuring point. Then, the thermal strain influence index, the temperature transmission influence parameter and the temperature gradient of each measuring point are multiplied and combined to obtain the heat treatment anomaly coefficient of the corresponding measuring point.

[0092] Thus, the heat treatment anomaly coefficient for each measuring point was obtained.

[0093] Heat treatment control module 103: used to adjust equipment parameters at each monitoring time according to the heat treatment anomaly coefficient of each measuring point.

[0094] Considering the distribution of heat treatment anomaly coefficients based on measuring points can help assess the distribution of heat treatment effects on workpieces, and thus help adjust the parameters of heat treatment equipment in order to obtain better heat treatment results for workpieces.

[0095] Preferably, in one embodiment of the present invention, considering that adjusting the rotation speed of the stage can help the air convection in the heat treatment equipment, thereby improving the uniformity of heat distribution, so that the workpiece is heated evenly and the possibility of local deformation is reduced; while the heat treatment anomaly coefficient of the measuring points on both sides of the workpiece can help evaluate the deviation of the heat treatment effect on the opposite side. When the deviation is larger, it indicates that the heat treatment effect is not good due to the position restriction on one side, and the rotation speed of the stage can be adjusted to improve the heat treatment effect.

[0096] Furthermore, considering that adjusting the heating temperature can indirectly adjust the rate of change of the heat source temperature, thereby adjusting the heating rate and heat conduction rate of different measuring points, for example, a lower heating rate can reduce the difference in the rate of change of temperature at different measuring points, avoiding localized heat deformation of the workpiece caused by a high heating rate; the more discrete the heat treatment anomaly coefficient of the measuring points on the workpiece, the greater the possibility of uneven heat treatment of the workpiece, and the more the temperature change rate should be appropriately reduced to improve the overall heat treatment effect of the workpiece.

[0097] Based on this, the equipment parameters are adjusted according to the heat treatment anomaly coefficient at each measuring point, including:

[0098] The equipment parameters should at least include the rotational speed of the stage and the heating temperature of the heat treatment equipment;

[0099] All pairs of opposite measuring points between two sets of measuring points are obtained, and the opposite heat treatment deviation is obtained based on the difference between the heat treatment anomaly coefficients of each pair of opposite measuring points. The normalized value of the opposite heat treatment deviation is added to a constant 1 to obtain the speed adjustment weight. The speed adjustment weight is used to weight the stage speed at the monitoring time to obtain the adjusted stage speed.

[0100] Based on the discrete characteristics of the heat treatment anomaly coefficients at all measuring points, the heat treatment non-uniformity parameter is obtained. The difference between the constant 1 and the normalized value of the heat treatment non-uniformity parameter is multiplied by the preset sensitive parameter to obtain the temperature adjustment weight. The heating temperature at the monitoring time is weighted using the temperature adjustment weight to obtain the adjusted heating temperature.

[0101] Specifically, in the two columns of measuring points on the workpiece, each cross section of the workpiece, such as two measuring points on the cross section corresponding to the bottom 0.2m away, is taken as a group of opposite measuring points; the difference is measured by the absolute value of the difference, and the absolute values ​​of the differences between the heat treatment abnormality coefficients of each group of opposite measuring points are summed to obtain the opposite heat treatment deviation; the opposite heat treatment deviation is mapped to the sigmoid function and the value range is adjusted to 0-1, and then the mapping result is added with a constant 1 to obtain the speed adjustment weight; and the set stage speed at each monitoring moment is obtained based on the monitoring system of the heat treatment equipment itself, and then the stage speed is multiplied by the speed adjustment weight to obtain the adjusted stage speed, which is set as the stage speed for the next monitoring moment;

[0102] The variance is used to measure discrete characteristics. The variance of the heat treatment anomaly coefficients at all measuring points is used as the heat treatment non-uniformity parameter. The heat treatment non-uniformity parameter is mapped to the sigmoid function and its value range is adjusted to 0-1. Then, the heat treatment non-uniformity parameter is subtracted from the constant 1, and the difference is multiplied by a preset sensitivity parameter such as 0.2 to obtain the temperature adjustment weight. The implementer can also customize it to adjust the temperature change range and avoid large temperature fluctuations from affecting the heat treatment effect. The heating temperature set at each monitoring time is obtained based on the monitoring system of the heat treatment equipment itself. Then, the heating temperature is multiplied by the temperature adjustment weight to obtain the adjusted heating temperature, which is set as the heating temperature for the next monitoring time.

[0103] In another embodiment of the present invention, the implementer may also collect a large number of process parameters of historical workpieces that have passed heat treatment during the heat treatment process, such as the time-series variation curve of the thermal strain anomaly coefficient at each measuring point and the time-series variation curve of various equipment parameters; use the time-series variation curve of the thermal strain anomaly coefficient at each measuring point of each historical workpiece as feature data, and use the time-series variation curve of various equipment parameters as labels for the feature data, thereby constructing a training sample set to train the neural network model; then at each monitoring time, input the time-series variation curve of the thermal strain anomaly coefficient at each measuring point up to that monitoring time into the trained neural network model, and the model can automatically output the prediction curve of each equipment parameter, thereby determining the equipment parameters for the next monitoring time for adjustment.

[0104] It should be noted that the training and application of neural network models are well-known technologies and will not be elaborated upon further.

[0105] In summary, this invention first acquires temperature and strain data at each measuring point on the workpiece at each monitoring time. Then, at each monitoring time, it acquires the heating characteristic coefficient of each measuring point. Further, by combining the historical correlation between temperature and strain data at each measuring point, the strain data at each measuring point, and its distance from the heating source, it acquires the thermal strain influence index of the workpiece. Based on the difference in temperature data between each measuring point and adjacent measuring points, and the thermal strain influence index, it acquires the heat treatment anomaly coefficient for each measuring point. At each monitoring time, it adjusts the equipment parameters based on the heat treatment anomaly coefficient for each measuring point. This invention improves the heat treatment effect on long-shaft workpieces by quantifying the degree of influence of location on the surface temperature of the workpiece during heat treatment, thereby reducing the thermal stress differences of long-shaft metal workpieces during heat treatment.

[0106] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0107] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. An intelligent control system for heat treatment equipment of long shaft metal workpieces, characterized in that, The system includes: Process data acquisition module: used to acquire temperature and strain data at each measuring point on the workpiece at each monitoring time; The workpiece heat analysis module is used to obtain the heating characteristic coefficient of each measuring point at each monitoring time based on the historical trend of temperature data at each measuring point and the historical changes in the discrete characteristics of temperature data at all measuring points; to obtain the thermal strain influence index of the workpiece based on the historical correlation between temperature data and strain data at each measuring point and the heating characteristic coefficient, combined with the strain data of each measuring point and its distance from the heating source; and to obtain the heat treatment anomaly coefficient of each measuring point based on the difference in temperature data between each measuring point and adjacent measuring points, and the thermal strain influence index. Heat treatment control module: used to adjust equipment parameters at each monitoring time based on the heat treatment anomaly coefficient of each measuring point.

2. The intelligent control system for heat treatment equipment of long shaft metal workpieces according to claim 1, characterized in that, The method for obtaining the heating characteristic coefficient includes: For each measuring point, at each monitoring time, a temperature change curve is fitted based on the temperature data of all historical monitoring times during the historical heat treatment process, and the temperature change rate parameter is obtained according to the change trend of the temperature change curve. During the historical heat treatment process, at each historical monitoring moment, the variance of the temperature data at all measuring points is used as the temperature non-uniformity parameter. Based on the temperature non-uniformity parameter at all historical monitoring moments, a temperature non-uniformity change curve is fitted, and the uniform heating parameter of the workpiece is obtained according to the change trend of the temperature non-uniformity change curve. By weighting the temperature change rate parameter with the uniform heating parameter, the heating characteristic coefficient of each measuring point is obtained.

3. The intelligent control system for heat treatment equipment of long shaft metal workpieces according to claim 2, characterized in that, The method for obtaining the temperature change rate parameter includes: At each monitoring moment, the slope of each temperature change curve is used as the first rate parameter, and the negative correlation mapping result between the temperature data and the preset target temperature is used as the second rate parameter. By combining the first rate parameter and the second rate parameter, the temperature change rate parameter is obtained.

4. The intelligent control system for heat treatment equipment of long shaft metal workpieces according to claim 2, characterized in that, The method for obtaining the uniform heating parameters includes: The negative correlation mapping result of the slope value of the temperature non-uniformity change curve is used as the uniform heating parameter.

5. The intelligent control system for heat treatment equipment of long shaft metal workpieces according to claim 1, characterized in that, The method for obtaining the thermal strain influence index includes: For each measuring point, at each monitoring time, based on the temperature and strain data from all historical monitoring times, a temperature time series and a strain time series are fitted, and the thermal strain correlation parameters are determined based on the Pearson correlation coefficient between the two series. At each monitoring time, the heating characteristic coefficient, the thermal strain correlation parameter, and the maximum strain value in the strain time sequence of each measuring point are integrated to obtain the thermal strain characteristic parameter. The measuring points are sorted in ascending order based on their distance from the heating source in the heat treatment equipment. The thermal strain characteristic parameter curve is fitted based on the sorting order of the measuring points, and the thermal strain influence index is obtained according to the rate of change of the thermal strain characteristic parameter curve.

6. The intelligent control system for heat treatment equipment of long shaft metal workpieces according to claim 5, characterized in that, Based on the rate of change of the thermal strain characteristic parameter curve, the thermal strain influence index of the workpiece is obtained, including: The negative correlation mapping result of the slope of the thermal strain characteristic parameter curve is used as the thermal strain influence index.

7. The intelligent control system for heat treatment equipment for long-shaft metal workpieces according to claim 1, characterized in that, The method for setting up the measuring points includes: In the axial direction of a long-shaft metal workpiece, measuring points are evenly distributed on opposite sides of the workpiece surface to obtain two rows of measuring points. The two rows of measuring points are axially symmetrical along the center line of the workpiece.

8. The intelligent control system for heat treatment equipment for long-shaft metal workpieces according to claim 7, characterized in that, The method for obtaining the heat treatment anomaly coefficient includes: For each measuring point, at each monitoring time, the temperature gradient is obtained based on the difference in temperature data between it and the adjacent measuring points in the axial direction, and the temperature transmission influence parameter is obtained based on the temperature gradient difference between the measuring point and the other measuring points. At each monitoring moment, the thermal strain influence index, the temperature transmission influence parameter of each measuring point, and the temperature gradient are integrated to obtain the heat treatment anomaly coefficient of the corresponding measuring point.

9. The intelligent control system for heat treatment equipment of long shaft metal workpieces according to claim 8, characterized in that, The method for obtaining the temperature gradient includes: For each measuring point, at each monitoring time, two measuring points closest to it in its axial direction are determined as reference measuring points, and the average absolute value of the difference between the temperature data of the measuring point and the reference measuring points is taken as the temperature gradient.

10. The intelligent control system for heat treatment equipment of long shaft metal workpieces according to claim 7, characterized in that, Adjust the equipment parameters according to the heat treatment anomaly coefficient at each measuring point, including: The equipment parameters include at least the rotational speed of the stage and the heating temperature of the heat treatment equipment; All pairs of opposite measuring points between two sets of measuring points are obtained, and the opposite heat treatment deviation is obtained based on the difference between the heat treatment anomaly coefficients of each pair of opposite measuring points; the normalized value of the opposite heat treatment deviation is added to a constant 1 to obtain the rotational speed adjustment weight; the rotational speed of the stage at the monitoring time is weighted using the rotational speed adjustment weight to obtain the adjusted stage rotational speed. Based on the discrete characteristics of the heat treatment anomaly coefficients at all measuring points, the heat treatment non-uniformity parameter is obtained. The difference between the constant 1 and the normalized value of the heat treatment non-uniformity parameter is multiplied by a preset sensitive parameter to obtain the temperature adjustment weight. The heating temperature at the monitoring time is weighted using the temperature adjustment weight to obtain the adjusted heating temperature.

Images