Method for monitoring heating of stainless steel seamless tube in heat treatment furnace

Abstract

The invention discloses a heating monitoring method for a stainless steel seamless tube in a heat treatment furnace, which belongs to the technical field of metal heat treatment and specifically comprises the following steps: acquiring an electromagnetic induction signal of a steel tube in rotation advancing in real time and binding spatio-temporal information; kinematics inversion is carried out on the spatio-temporal information based on the movement speed of the steel pipe, and an electromagnetic parameter evolution track of each physical point on the surface is reconstructed; continuously deviated abnormal points are identified based on the evolution trajectory and clustered to extract electromagnetic characteristics of the heating abnormal area, temperature deviation is obtained through a preset electromagnetic-temperature mapping model, and a compensation instruction is generated; and predicting space-time coordinates of the abnormal area reaching the next heating area, and driving the corresponding independent heating unit to execute dynamic energy compensation in the matched time window. Real-time, global and accurate sensing and closed-loop regulation and control of the heating uniformity of the moving workpiece are achieved, the uniformity and stability of heat treatment quality are remarkably improved, and energy consumption is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of metal heat treatment, in particular to a stainless steel seamless pipe heating monitoring method in a heat treatment furnace. BACKGROUND

[0002] Heat treatment is a key process in the production of stainless steel seamless pipes, and the uniformity and accuracy of the heating process directly determine the final microstructure performance, residual stress level and dimensional accuracy of the product. Traditional heat treatment furnaces usually adopt a zoning temperature control strategy and rely on a number of thermocouples at fixed positions in the furnace to monitor the furnace temperature. However, for a steel pipe that continuously rotates and advances in the furnace, the thermal history experienced by each point on its surface is dynamically different, and fixed furnace temperature monitoring cannot truly reflect the real-time temperature field distribution of the steel pipe body, especially its surface and near-surface area in three-dimensional space.

[0003] Currently, there have been some technical explorations for temperature monitoring of moving workpieces. For example, non-contact infrared thermal imagers are used to scan and measure the temperature of local surfaces, or fixed sensors installed at specific positions are used to intermittently measure workpieces passing through their field of view. However, first, methods such as infrared thermal imaging are easily disturbed by high-temperature radiation background, smoke, and observation angle in the complex furnace environment, making it difficult to achieve stable and high-precision full-field measurement. Second, intermittent measurement based on fixed points cannot construct a continuous and complete temperature evolution trajectory of the steel pipe surface, and cannot accurately identify local small or moving heating abnormal areas. Third, most monitoring methods only stop at the "perception" level and fail to form an efficient and accurate closed-loop control link with the execution mechanism of the heat treatment furnace, resulting in that the identified temperature deviation cannot be accurately compensated in real time and space.

[0004] Therefore, in actual production, the heat treatment process control has been in a "black box" or "semi-blind" state for a long time, mainly relying on fixed heating curves and operating experience for extensive adjustment, making it difficult to achieve dynamic fine-tuning based on the real state of the workpiece body, and restricting the further improvement of product quality. SUMMARY

[0005] The purpose of the present application is to provide a stainless steel seamless pipe heating monitoring method in a heat treatment furnace, which solves the following technical problems: In actual production, the heat treatment process control has been in a "black box" or "semi-blind" state for a long time, mainly relying on fixed heating curves and operating experience for extensive adjustment, making it difficult to achieve dynamic fine-tuning based on the real state of the workpiece body.

[0006] The purpose of the present application can be achieved by the following technical solutions: A stainless steel seamless pipe heating monitoring method in a heat treatment furnace, comprising the following steps: S1, collecting electromagnetic induction signals of a rotating steel pipe in a heat treatment furnace through a circumferential electromagnetic detection array in real time, and synchronously binding the electromagnetic induction signals with corresponding time stamps and detection array unit coordinates to obtain a raw signal set; S2, obtaining a steel pipe rotation angular velocity and a forward linear velocity, and performing kinematic inversion calculation on the raw signal set to obtain an evolution track of electromagnetic parameters of any physical point on a steel pipe surface continuously changing over time; S3, calculating a dynamic change rate of each physical point based on the evolution track, and comparing the dynamic change rate with a local background field composed of change rates of physical points spatially adjacent to the physical point to obtain an abnormal point set continuously deviating from the local background field; S4, performing spatial clustering on the abnormal point set to obtain a heating abnormal area, extracting electromagnetic parameters corresponding to each physical point constituting the heating abnormal area, and inputting the electromagnetic parameters into a preset electromagnetic-temperature mapping model to obtain a temperature compensation instruction; S5, predicting a space-time coordinate of the heating abnormal area reaching a next heating section based on real-time rotation and forward speed of the steel pipe, determining an independent heating unit to be started in the next heating section based on the space-time coordinate, and driving the independent heating unit to perform dynamic energy compensation in combination with the temperature compensation instruction.

[0007] As a further scheme of the application: in the S2, the specific acquisition process of the evolution track is: obtaining a real-time rotation angular velocity and a forward linear velocity of the steel pipe, a known radius and a pre-installed axis position in a furnace; based on the rotation angular velocity, the forward linear velocity, the known radius and the pre-installed axis position in the furnace, modeling a surface of the steel pipe as a cylindrical surface, and assigning an identification composed of an initial circumferential angle and an initial axial position to a physical point on the cylindrical surface; according to the rotation angular velocity and the forward linear velocity, calculating a circumferential angle offset and an axial position offset of the physical point from the initial identification changing over time, and determining a theoretical space coordinate of the physical point relative to a fixed space of the furnace at any time; for each induction signal with a time stamp and a detection unit space coordinate in the raw signal set, matching the theoretical space coordinate with the detection unit space coordinate to determine whether the theoretical space coordinate is located in an effective induction area of the detection unit at a time corresponding to the signal time stamp; when the determination is yes, associating the induction signal to the corresponding physical point as a state observation value of the physical point at the time; after traversing all the induction signals, each physical point obtains a discrete state observation value sequence sorted by time stamps; smoothing and curve fitting the discrete state observation value sequence to obtain an evolution track of electromagnetic parameters of the physical point continuously changing over time.

[0008] As a further scheme of the present application: in the S3, the specific process of obtaining the abnormal point set is: Calculate the instantaneous change rate of the evolution track of each physical point on the surface of the steel pipe, and determine the spatial adjacent physical points of each physical point as a candidate neighboring point set; Calculate the statistical distribution of the instantaneous change rate of the candidate neighboring point set; based on the statistical distribution, set a preliminary judgment threshold, and remove the candidate points whose instantaneous change rate exceeds the preliminary judgment threshold from the candidate neighboring point set to obtain a purified neighboring point set; Calculate the statistical mean and statistical fluctuation range based on the instantaneous change rate of the purified neighboring point set; and set a stability judgment threshold based on the statistical fluctuation range; Calculate the difference between the instantaneous change rate of each physical point and the statistical mean to obtain a purified deviation, and determine the physical points whose purified deviation continuously exceeds the stability judgment threshold as abnormal physical points, and collect the abnormal physical points to form an abnormal point set.

[0009] As a further scheme of the present application: in the S4, the specific construction process of the preset electromagnetic-temperature mapping model is: A plurality of pipe segment specimens with different characteristic temperature intervals are obtained in advance, and the pipe segment specimens are heated according to a preset temperature rising curve in a controlled experimental thermal environment; during the heating process, the circumferential electromagnetic detection array is used to synchronously collect the induction signals of each pipe segment specimen at a plurality of characteristic temperature points, and a contact temperature measuring device is used to synchronously measure the actual temperature values of each pipe segment specimen at the characteristic temperature points; Demodulate and calculate the characteristic quantity of each induction signal, extract the signal amplitude variation and phase shift, and use the electromagnetic parameters as the independent variable, and use the actual temperature values strictly paired with the induction signals in space and time as the dependent variable to form a calibration data pair; use the least square method to regress all the calibration data pairs, and fit a continuous mapping function from the independent variable to the dependent variable; define the continuous mapping function as the preset electromagnetic-temperature mapping model.

[0010] As a further scheme of the present application: in the S4, the specific process of obtaining the temperature compensation instruction is: Extract a plurality of electromagnetic characteristic parameter data corresponding to the heating abnormal area and calculate the average value to obtain the electromagnetic parameter characteristic value of the heating abnormal area; obtain a plurality of electromagnetic characteristic parameter data corresponding to other areas in the same axial cross section of the steel pipe as the heating abnormal area and calculate the average value to obtain an electromagnetic parameter reference value; input the electromagnetic parameter characteristic value into the preset electromagnetic temperature mapping model to obtain a temperature estimation value of the heating abnormal area; input the electromagnetic parameter reference value into the preset electromagnetic temperature mapping model to obtain a temperature reference value; calculate a difference value between the temperature estimation value and the temperature reference value to obtain a temperature deviation value; on the basis of the absolute value of the temperature deviation value, define a heating uniformity index, compare the heating uniformity index with a preset uniformity index threshold range, if the heating uniformity index exceeds the preset uniformity index threshold range, map the heating abnormal area to a specific spatial position in the hearth of the heat treatment furnace, and determine the specific spatial position as a to-be-regulated area; determine the positive and negative of the temperature deviation value, when the temperature deviation value is positive, set the temperature adjustment direction of the to-be-regulated area as increasing energy flow input, and when the temperature deviation value is negative, set the adjustment direction as decreasing energy flow input; According to a preset energy flow adjustment step, generate a temperature compensation instruction for stepwise adjustment of the output power of the independent heating unit corresponding to the to-be-regulated area along the adjustment direction.

[0011] As a further scheme of the present application: further comprising the specific definition process of the other area in the same axial cross section of the steel pipe is: obtain the real-time rotational angular velocity and forward linear velocity of the steel pipe, the known radius and the preset installation axis position in the hearth; based on the preset installation axis position in the hearth and the direction of the forward linear velocity, the direction of the forward linear velocity is calibrated as the axial positive direction, and the geometric center point of the first spatial position fixed circumferential electromagnetic detection array is defined as the origin of the hearth space cylindrical coordinate system along the axial positive direction; the direction perpendicular to the origin pointing to the top of the hearth is calibrated as the circumferential angle zero point direction; for each physical point, according to its identification composed of the initial circumferential angle and the initial axial position, combined with the real-time rotational angular velocity, the forward linear velocity, the known radius and the preset installation axis position in the hearth, calculate the absolute circumferential angle and the absolute axial position of the physical point at the current time; according to the absolute circumferential angle, the absolute axial position, the known radius and the preset installation axis position in the hearth, calculate the specific spatial coordinates of the physical point in the hearth space cylindrical coordinate system; obtain the specific spatial coordinates of each physical point constituting the heating abnormal area; extract the axial coordinate component in the specific spatial coordinates; determine the minimum value and the maximum value in the axial coordinate component; define the interval between the minimum value and the maximum value as the current target axial cross section range; From all physical points on the surface of the steel pipe, physical points whose axial coordinate component of specific spatial coordinates is within the current target axial section range and whose circumferential coordinate component is outside the circumferential coverage range of the heating abnormal area are screened to form a candidate physical point set; the area corresponding to the candidate physical point set is defined as the other area at the same steel pipe axial section.

[0012] As a further scheme of the present application, in S5, the specific process of performing dynamic energy compensation is: The specific spatial coordinates of each physical point constituting the heating abnormal area in the hearth spatial cylindrical coordinate system are obtained; the circumferential coordinate component of each physical point is extracted from the specific spatial coordinates; the maximum value and the minimum value in the circumferential coordinate component are determined, and the difference between the maximum value and the minimum value is taken as the circumferential angular range of the heating abnormal area; based on the real-time rotational angular velocity of the steel pipe and the circumferential angular range, the rotation required time required for the heating abnormal area to rotate through the fixed circumferential action direction of the independent heating unit is calculated; The axial coordinate component of each physical point is extracted from the specific spatial coordinates; the maximum value and the minimum value in the axial coordinate component are determined, and the difference between the maximum value and the minimum value is taken as the axial extension length of the heating abnormal area; based on the real-time forward linear velocity of the steel pipe and the axial extension length, the forward required time required for the heating abnormal area to completely pass through the axial action range of the independent heating unit is calculated; The rotation required time and the forward required time are compared, and the smaller one is determined as the effective action time of the dynamic energy compensation; according to the starting time in the predicted space-time coordinates and the effective action time, an accurate energy compensation window of the independent heating unit is set; the independent heating unit is driven to perform power adjustment according to the temperature compensation instruction within the accurate energy compensation window.

[0013] As a further scheme of the present application, in S5, it further includes that after adjusting the heating unit according to the temperature compensation instruction, the electromagnetic parameters and temperature deviation values of the to-be-controlled area and other control areas are re-acquired and calculated, and the heating uniformity index is updated accordingly; It is judged whether the updated heating uniformity index has returned to the pre-set uniformity index threshold range; if not, the adjustment direction is determined again according to the positive and negative of the current temperature deviation value, and further power step adjustment instructions are generated according to the energy flow adjustment step for iterative adjustment; the process is repeated until the updated heating uniformity index returns to the normal range.

[0014] The present application has the following beneficial effects: 1) The invention first constructs the direct sensing and full-field mapping ability based on the evolution of the intrinsic material properties. It can be understood that the magnetic permeability changes significantly near the critical temperature. Through the circumferentially arranged electromagnetic detection array, the electromagnetic signals induced by the change of the material properties are captured in real time, rather than directly measuring the temperature radiation which is easily disturbed by the environment. Each group of original signals is strictly bound to the electromagnetic state of a small area on the surface of the steel pipe at a specific time. Combined with the precise kinematics parameters of the steel pipe, the time and space discrete observation data are reconstructed into the continuous evolution trajectory of the electromagnetic parameters unique to each physical point on the surface of the steel pipe through inverse calculation. This trajectory is a record of the dynamic response of the material to the heating process. Further, through the mapping relationship strictly calibrated by experiments, the electromagnetic evolution trajectory can be converted into the corresponding temperature evolution information, thereby realizing the anti-interference indirect measurement and visualization of the global temperature field of the rotating workpiece based on physical principles in the harsh industrial furnace environment.

[0015] 2) The invention calculates the instantaneous change rate of the electromagnetic evolution trajectory of any physical point on the surface of the steel pipe in real time, and synchronously counts the distribution of the change rates of all its spatial neighbors, thereby dynamically generating a real-time "normal response background field" applicable only to the local area. It can be understood that any real anomaly caused by microscopic unevenness or heating difference of the material will deviate from its own local background field. This core logic based on "neighborhood comparison" effectively focuses on local relative differences, enabling the diagnosis process to focus on extracting real abnormal signals. At the same time, relying on strict space-time coordinate registration throughout the process, any identified abnormal pattern can be uniquely traced back to the precise three-dimensional spatial location and specific process time point in the furnace, realizing seamless connection from anomaly perception to physical root location, and providing a clear spatial target for subsequent precise intervention.

[0016] 3) The invention establishes a closed-loop dynamic control system from "global state perception" to "spatially accurate execution". Through electromagnetic diagnosis of the abnormal area, it generates quantitative compensation instructions containing adjustment direction and energy flow intensity, predicts the accurate space-time coordinates of the abnormal area reaching the downstream controllable heating unit according to the real-time motion state of the steel pipe, and calculates the energy compensation time window and continuous action time that strictly match it. This enables the independent heating unit to apply the correct dose of energy compensation at the correct time, in the correct local orientation on the workpiece. This "prediction-matching" spatio-temporal synchronous execution mechanism ensures that energy is efficiently and directionally delivered to the moving defect body, avoiding the broad impact on the fixed furnace area, thereby fundamentally shifting the control logic from extensive adjustment of the "static furnace" to real-time feedback and topography repair of the "moving workpiece body state", ultimately improving the extreme uniformity, process stability and energy utilization efficiency of the heat treatment quality at the root. BRIEF DESCRIPTION OF DRAWINGS

[0017] The application will be further described below with reference to the accompanying drawings.

[0018] Figure 1 is a flow chart of a stainless steel seamless pipe heating monitoring method in a heat treatment furnace. DETAILED DESCRIPTION

[0019] The technical solutions in the embodiments of the application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, rather than all the embodiments of the application. Based on the embodiments in the application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the application.

[0020] Please refer to Figure 1 The application is a stainless steel seamless pipe heating monitoring method in a heat treatment furnace, comprising the following steps: S1, collecting electromagnetic induction signals of the rotating steel pipe in real time through a circumferential electromagnetic detection array arranged in the heating section of the heat treatment furnace, and binding each electromagnetic induction signal with an accurate time stamp at the time of collection and spatial coordinates of the detection array unit to generate a raw signal set with space-time information; A circumferential electromagnetic detection array is fixedly installed on the furnace wall at a key heating section (such as the entrance of the soaking zone) of the heat treatment furnace. The array is composed of at least 8 independent detection units uniformly distributed along the circumference of the furnace chamber to ensure complete coverage of the rotating steel pipe. Each detection unit contains an excitation coil and an induction coil, and the working frequency is set to a medium-low frequency band of 1 kHz-10 kHz to balance the penetration depth and sensitivity to the change in magnetic permeability of stainless steel. When the stainless steel seamless pipe rotates and advances and passes through the detection array, each unit continuously collects the induced electromotive force (EMF) signal in the small space region in front of it at a sampling frequency of not less than 100 Hz. The data collection binds three groups of metadata to each raw signal: the collection time stamp (T) accurate to milliseconds, the unique spatial coordinate number (X, Y, Z) of the detection unit. All data are stored in the format of "time stamp-unit ID-raw voltage / current signal", generating a raw signal set with space-time registration information.

[0021] S2, obtaining the rotational angular velocity and forward linear velocity of the steel pipe, and performing kinematic inversion calculation on the raw signal set to obtain the evolution track of the electromagnetic parameters of any physical point on the surface of the steel pipe changing continuously with time; The rotational angular velocity ω (radian / second) and the forward linear velocity v (meter / second) of the steel pipe are acquired from the production line PLC in real time. The steel pipe is regarded as an ideal cylinder with a radius of R, and the theoretical running axis of the steel pipe in the furnace is taken as the reference. For any signal sample in the original signal set, it is known that it is collected by the detection unit with a spatial position of Psensor at time t. A steel pipe surface source point is assigned to the signal by solving the following kinematics inverse problem: a physical point on the surface of the steel pipe is found, whose spatial position at time t just enters the effective sensitive area of the detection unit Psensor. The position of the physical point on the steel pipe can be uniquely identified by the initial circumferential angle θ0 and the axial position z0. By iterative calculation, (θ0, z0) satisfying the spatial position constraint is solved. Repeat the process for all signals, i.e. classify the massive discrete signals, and sort all signals originating from the same physical point (θ0, z0) according to their time stamps to form a discrete time sequence of electromagnetic parameters (such as the normalized amplitude of complex impedance) of the point. Smooth and spline interpolate the sequence, i.e. generate a continuous and smooth electromagnetic parameter evolution track of the physical point, traverse all physical points, and complete the full-field track reconstruction.

[0022] S3, calculate the dynamic change rate of each physical point based on the evolution track of the physical point, and compare the dynamic change rate with a local background field composed of the change rates of physical points spatially adjacent to the physical point, to obtain an abnormal point set continuously deviating from the local background field; The dynamic change rate of each physical point is calculated based on the evolution track of the physical point. Specifically, first, the curve of the electromagnetic parameter of the physical point continuously changing over time is subjected to numerical differentiation operation, thereby obtaining a continuous change rate signal reflecting the instantaneous temperature rise or fall speed of the point. For example, when the curve rises sharply at a certain time, the change rate corresponding thereto presents a positive spike. Subsequently, in order to construct the local background field of the point, a number of physical points spatially adjacent to the point, for example, eight adjacent points directly surrounding the point, are automatically searched and locked from the digitized model of the surface of the steel pipe, the change rate data of the neighbor points at the same time are collected in real time, and a statistical reference value representing the behavior characteristics of the majority of normal points in the local region and a statistical dispersion value measuring the normal fluctuation range of the region are calculated. Next, comparison and determination are performed. The real-time deviation between the change rate of the physical point itself and the statistical reference value of the local background field is continuously calculated, and the deviation is compared with a reasonable fluctuation threshold set based on the statistical dispersion value. If the deviation amplitude of the point continuously exceeds the threshold range in a plurality of sampling periods, for example, the change rate is always significantly lower than the average level of all neighbors during the whole heating section, which indicates that the point has a persistent heating lag. Finally, all the abnormal physical points that pass the above condition determination and may be dispersed in space are analyzed by a spatial clustering algorithm. The algorithm automatically merges the abnormal points with dense positions into one or more continuous abnormal regions with clear boundaries according to the neighbor relationship between the points, for example, all the abnormal points gathered in a 90-degree sector region on the surface of the steel pipe are identified as the same heating abnormal region, thereby completing the conversion from discrete points to structured regions.

[0023] The intrinsic diagnosis mechanism of discovering real anomalies through local self-comparison can completely eliminate global measurement interference caused by inherent unevenness of the overall structure, magnetic field distribution or heating field in the heat treatment furnace, because the method only concerns the relative behavior difference between a point and its immediate environment, and is insensitive to the background fluctuations borne by all points. This enables extremely sensitive identification of uneven heating caused by real defects such as material micro-segregation, original uneven wall thickness or local shielding, without misjudging the inherent unevenness of the furnace itself as a problem of the steel pipe. Through the determination logic of continuous deviation, false signals caused by measurement noise or transient disturbance can be effectively filtered out, ensuring that the captured abnormal pattern has reliable process relevance, providing data support for subsequent steps, making it possible to perform quantitative energy compensation on a specific region, thereby accurately adjusting the quality control from the vague adjustment of the furnace environment to the targeted repair of the defects of the steel pipe body, laying the most critical technical foundation for realizing substantial improvement of heating uniformity.

[0024] S4, performing spatial clustering on the abnormal point set to obtain a heating abnormal area, extracting electromagnetic parameters corresponding to each physical point constituting the heating abnormal area, and inputting the electromagnetic parameters into a preset electromagnetic-temperature mapping model to obtain a temperature compensation instruction; Firstly, spatial clustering analysis is performed on the identified abnormal point set, and spatially adjacent abnormal points are merged into continuous heating abnormal areas. Then, electromagnetic characteristic parameter data corresponding to all physical points constituting the abnormal area are extracted, and the average value of these data is calculated to obtain an electromagnetic parameter characteristic value representing the overall electromagnetic state of the area. At the same time, electromagnetic characteristic parameter data of other areas in the same axial section of the steel pipe but not overlapping in space are obtained, and the average value is also calculated to obtain an electromagnetic parameter reference value, which represents the normal heating level of the section. Then, the electromagnetic parameter characteristic value is input into a preset electromagnetic-temperature mapping model to output a temperature estimation value of the heating abnormal area, and the electromagnetic parameter reference value is input into the same model to obtain a temperature reference value. By calculating the difference between the temperature estimation value and the reference value, an accurate temperature deviation value is obtained. The heating uniformity index is defined based on the absolute value of the deviation value, and compared with the preset uniformity index threshold range. If the index exceeds the threshold range, the heating abnormal area is mapped to the specific spatial coordinates in the furnace of the heat treatment furnace to determine the to-be-regulated area. Further, the positive and negative of the temperature deviation value is judged: if the deviation value is positive, it indicates that the temperature of the area is too high, and the adjustment direction is set to increase the energy flow input; if it is negative, it indicates that the temperature is too low, and the direction is set to reduce the energy flow input. Finally, according to the preset energy flow adjustment step, the output power of the corresponding independent heating unit of the to-be-regulated area is generated for step adjustment of the quantized temperature compensation instruction in the direction.

[0025] The key link from "perception of abnormality" to "execution of compensation" is bridged by transforming the abstract "signal abnormality" detected in the previous step into concrete and executable process control commands. The calculation of the area average and the reference value avoids accidental errors based on single-point data, ensuring the robustness of the judgment; the mapping model converts electromagnetic parameters into temperature quantities, making the instructions based on direct process targets; then, by calculating the temperature deviation and constructing the uniformity index to compare with the preset threshold, the automatic and objective decision of "whether to intervene" is realized, avoiding excessive or insufficient control; only significant non-uniformity beyond the process tolerance will trigger control, ensuring the stability of production rhythm and the effectiveness of intervention. Then, mapping the abnormal area to the specific location of the furnace and determining the control direction is the key operation of accurately anchoring the conclusion in the "data space" to the "physical space", which ensures that the compensation energy will be delivered to the correct spatial location, and according to the positive and negative deviation intelligently decides whether to heat or cool, finally, generating a hierarchical adjustment instruction according to the preset step size is a robust and easy-to-implement control strategy, which approaches the target through gradual and exploratory adjustment, preventing over-adjustment or under-adjustment, leaving room for fine-tuning according to feedback, realizing dynamic and accurate correction of steel pipe heating uniformity, ensuring that the heat treatment quality is transformed from the "open-loop" mode relying on fixed process parameters to the "adaptive" intelligent control mode based on real-time state feedback of the workpiece.

[0026] S5, based on the real-time rotation and forward speed of the steel pipe, predicting the spatio-temporal coordinates of the heating abnormal area to the next heating section, determining the independent heating unit to be started in the next heating section based on the spatio-temporal coordinates and combining the temperature compensation instructions, driving the independent heating unit to execute dynamic energy compensation.

[0027] First, the precise rotational angular velocity and forward linear velocity of the steel pipe are read from the production line control unit in real time, and then combined with the precise geometric center coordinates of the heating abnormal area on the digitized model of the steel pipe surface, such as an elliptical area located in the middle of the steel pipe and with a circumferential angle of one hundred and twenty degrees, the geometric center of the area is calculated by the built-in kinematic model to calculate how long it will take for the area to move to the starting boundary position of the downstream heating section with independent control ability at the current speed. At the same time, according to the rotational speed, the specific circumferential direction of the center point of the area at that moment is calculated, so as to obtain a set of space-time coordinates containing the precise arrival time and specific circumferential angle. Then, based on the predicted space-time coordinates, the independent heating units that need to be started in the next heating section are determined, which will call the equipment layout diagram of the heating section, compare the predicted circumferential direction with the coverage range of the positions of all independent heating units in the diagram, for example, match to the four adjacent burner units numbered twelve to fifteen in the section, which are exactly responsible for the ninety-degree sector direction, and determine these units as the actuators for this compensation. Finally, combined with the temperature compensation instruction, drive these independent heating units to perform dynamic energy compensation, which will issue the power adjustment direction and amplitude specified in the compensation instruction, such as requiring a five percent increase in power output, to the control valves of the above-mentioned burner units together with the calculated compensation action start time and duration; these units will be started simultaneously at the moment when the abnormal area is about to enter their range of action, adjust the flame intensity or power output according to the instruction, and restore to the original state after the abnormal area completely passes through their range of action, thereby completing a dynamic energy spraying on the moving target.

[0028] The steel pipe in the heat treatment furnace is in continuous motion, and the identified heating abnormal area also moves with the rotation and advancement of the steel pipe. If compensation is simply made on the spot where the abnormality is found, or if the entire downstream heating section is fixedly adjusted in a general manner, energy cannot be accurately delivered to the moving target body. By predicting the space-time coordinates, the "space-time synchronization" of the compensation action and the moving target is achieved, ensuring that energy is applied at the correct time and in the correct position in the furnace, thereby acting exactly on the moving abnormal area. The core benefit is to realize the paradigm shift from "heating a fixed area" to "tracking and heating a moving target", making energy compensation object-oriented and time-space accurate. This avoids interference with normal areas or insufficient compensation for abnormal areas, greatly improving the accuracy and efficiency of control. Ultimately, this mechanism ensures that the entire method forms a complete "perception-decision-accurate execution" closed loop, and all monitoring, identification and diagnostic analysis in the previous steps are applied to the actual and immediate process optimization of the workpiece body, dynamically eliminating temperature unevenness of the steel pipe during heat treatment, thereby stably improving the microstructure performance and quality consistency of the final product.

[0029] In a preferred embodiment of the present application, the specific acquisition process of the evolution track in S2 is as follows: The real-time rotational angular velocity and advancing linear velocity of the steel pipe, the known radius, and the preset installation axis position in the furnace are obtained; based on the rotational angular velocity, the advancing linear velocity, the known radius, and the preset installation axis position in the furnace, the surface of the steel pipe is modeled as a cylindrical surface, and a physical point on the cylindrical surface is assigned a unique identifier consisting of an initial circumferential angle and an initial axial position; According to the rotational angular velocity and the advancing linear velocity, the circumferential angle offset and the axial position offset of the physical point from the initial identifier over time are calculated, and its theoretical spatial coordinates at any time relative to the fixed space of the furnace are determined; For each time-stamped and probe unit spatial coordinate sensing signal in the original signal set, the theoretical spatial coordinates are matched with the probe unit spatial coordinates to determine whether the theoretical spatial coordinates are located in the effective sensing area of the probe unit at the time corresponding to the signal timestamp; when it is determined to be yes, the sensing signal is associated to the corresponding physical point as the state observation value of the physical point at that time; After traversing all the sensing signals, each physical point obtains a discrete state observation value sequence sorted by timestamp; the discrete state observation value sequence is smoothed and curve-fitted to obtain the evolution track of the electromagnetic parameter of the physical point over time.

[0030] First, the rotational angular velocity and advancing linear velocity of the steel pipe are obtained from the real-time data bus of the production line, and the preset steel pipe radius parameter and the three-dimensional coordinates of the furnace installation axis are called; based on these parameters, a virtual cylindrical surface digital model corresponding to the physical steel pipe is established internally, and each addressable position on the surface of the model is assigned a unique identifier consisting of an initial circumferential angle (e.g. 0 to 360 degrees) and an initial axial position (e.g. millimeters from the entry end); for example, a point can be identified as "axial 1500 mm, circumferential 90 degrees". Then, for any identified physical point, according to the obtained real-time angular velocity and linear velocity, the initial time is integrated to calculate the circumferential angle cumulative change and axial position cumulative displacement of the point over time, thereby determining its accurate theoretical position at any future or past time relative to the fixed three-dimensional spatial coordinate system with the furnace as the reference.

[0031] Then, the massive discrete data in the original signal set is processed: for each recorded induction signal, the data packet records information such as "collected by the No. 3 probe unit at 12:00:01.235"; the set of theoretical spatial coordinates corresponding to the signal timestamp is called, and whether the theoretical coordinates of any physical point fall in the preset effective induction cubic space in front of the No. 3 probe unit at the precise time is determined through geometric calculation; once a match is found, for example, it is found that the point identified as "axial 1500 mm, circumferential 90 degrees" is located directly in front of the No. 3 unit at that moment, the amplitude, phase and other core information of the signal are regarded as the state snapshot of the physical point at that moment, and are firmly associated and stored, so that each physical point obtains a series of discrete observation values from different detectors arranged in chronological order; finally, filtering algorithm is applied to the like-discontinuous observation value sequence to remove pulse noise, and spline curve fitting technology is used to smoothly connect the discrete points, thereby forming a complete, continuous and delicate change curve reflecting how the electromagnetic parameters of the point evolve over time from entering the monitoring area to leaving, i.e. the evolution trajectory.

[0032] By strict kinematic inversion, the fragmented signals captured by the fixed sensor network throughout the hearth at different times and different places are reassembled to restore the complete life history of each point on the moving object, which is equivalent to providing each inch of the steel pipe surface with a virtual, exclusive data recorder that moves with it. The purpose of this method is to completely abandon the dependence on idealized uniform heating field or absolute coordinate system, and directly reconstruct the reliable individual evolution history from the most original and objective observation data through physical and geometric rules. Only when the independent, continuous and true evolution trajectory of each physical point is obtained, can all the precision analysis in the subsequent steps, such as calculating the change rate, locally comparing with neighbors and diagnosing abnormalities, become possible.

[0033] In another preferred embodiment of the present application, the specific process of obtaining the abnormal point set in S3 is as follows: The instantaneous change rate of the evolution trajectory of each physical point on the surface of the steel pipe is calculated, and the spatial neighboring physical points of each physical point are determined as a candidate neighboring point set; The statistical distribution of the instantaneous change rate of the candidate neighboring point set is calculated; a preliminary judgment threshold is set based on the statistical distribution, points with instantaneous change rates exceeding the preliminary judgment threshold in the candidate neighboring point set are regarded as candidate points, the candidate points are removed from the candidate neighboring point set, and a purified neighboring point set is obtained; The statistical mean and statistical fluctuation range of the instantaneous change rate of the purified neighboring point set are calculated; a stability judgment threshold is set based on the statistical fluctuation range; The instantaneous change rate of each physical point is calculated, and the difference between the statistical mean value is obtained, and the purified deviation is obtained, and the physical point which is continuously more than the stability judgment threshold is judged as an abnormal physical point, and the abnormal physical point is collected to form an abnormal point set.

[0034] First, the electromagnetic parameter evolution trajectory of each physical point on the surface of the steel pipe is subjected to numerical differentiation operation, and the instantaneous change speed of the trajectory at each sampling time, i.e. the change rate, is calculated. Next, according to the three-dimensional coordinates of each physical point on the digitized steel pipe surface model, its immediately surrounding points in space are automatically found and determined, for example, two on each side in the circumferential direction, two in front and back in the axial direction, a total of eight closest physical points are defined as an initial candidate neighbor set. Subsequently, the instantaneous change rates of all points in the candidate neighbor set at the current sampling time are calculated, and the statistical distribution characteristics of the data are analyzed, and according to the overall shape and dispersion degree of the distribution, a threshold limit for preliminary screening is intelligently set; the extreme points whose change rate values are obviously outside the threshold limit are marked out, and these extreme points are temporarily excluded from the candidate neighbor set, so as to obtain a purified neighbor point set which can better represent the normal behavior of the local area. Then, based on the change rates of all points in the purified neighbor set, two key statistical quantities are calculated: one is the statistical mean value which can represent the change rate center level of the local area, and the other is the statistical fluctuation range which can represent the normal fluctuation tolerance of the area; and according to the fluctuation range, a more stringent threshold for final stability judgment is set. Then, the difference between the instantaneous change rate of the center physical point itself and the statistical mean value of the purified neighbor set is calculated to obtain the purified deviation; the purified deviation of the center physical point is continuously tracked within a certain process time, and if the deviation continuously exceeds the stability judgment threshold set based on the normal fluctuation range of the neighbor, the physical point is finally judged as an abnormal point. After traversing all physical points and completing the above judgment, all points marked as abnormal are collected to form the final abnormal point set.

[0035] In another preferred embodiment of the present application, the specific construction process of the preset electromagnetic-temperature mapping model in S4 is: A plurality of pipe segment specimens with different characteristic temperature intervals are obtained in advance, and the pipe segment specimens are heated according to a preset temperature rising curve in a controlled experimental thermal environment; during the heating process, the circumferential electromagnetic detection array is used to synchronously collect the induction signals of each pipe segment specimen at a plurality of characteristic temperature points, and a contact temperature measuring device is used to synchronously measure the actual temperature values of each pipe segment specimen at the characteristic temperature points; Demodulate and characteristic quantity calculate each induction signal, extract its signal amplitude variation and phase shift, take the amplitude variation and the phase shift as electromagnetic parameters; take the electromagnetic parameters as independent variables, take the actual temperature value strictly paired with the induction signal in space and time as dependent variables, and form a calibration data pair; adopt least square method to regress and calculate all the calibration data pairs, and fit a continuous mapping function from the independent variables to the dependent variables; define the continuous mapping function as the preset electromagnetic-temperature mapping model.

[0036] In another preferred embodiment of the present application, in the S4, the specific process of obtaining the temperature compensation instruction is: Extract a plurality of electromagnetic characteristic parameter data corresponding to the heating abnormal area and calculate the average value to obtain an electromagnetic parameter characteristic value of the heating abnormal area; obtain a plurality of electromagnetic characteristic parameter data corresponding to other regions in the same steel pipe axial section as the heating abnormal area and calculate the average value to obtain an electromagnetic parameter reference value; Input the electromagnetic parameter characteristic value into the preset electromagnetic temperature mapping model to obtain a temperature estimation value of the heating abnormal area; input the electromagnetic parameter reference value into the preset electromagnetic temperature mapping model to obtain a temperature reference value; calculate the difference between the temperature estimation value and the temperature reference value to obtain a temperature deviation value; Based on the absolute value of the temperature deviation value, define a heating uniformity index, compare the heating uniformity index with a preset uniformity index threshold range, and if the heating uniformity index exceeds the preset uniformity index threshold range, map the heating abnormal area to a specific spatial position in the hearth of the heat treatment furnace and determine it as a region to be regulated; Determine the positive and negative of the temperature deviation value, and when the temperature deviation value is positive, set the temperature adjustment direction of the region to be regulated as increasing energy flow input, and when the temperature deviation value is negative, set the adjustment direction as reducing energy flow input; According to a preset energy flow adjustment step, generate a temperature compensation instruction for stepwise adjustment of the output power of the independent heating unit corresponding to the region to be regulated in the adjustment direction.

[0037] In another preferred embodiment of the present application, the specific definition process of the other regions in the same steel pipe axial section is also included: Obtain the real-time rotation angular velocity and forward linear velocity of the steel pipe, the known radius, and the preset installation axis position in the hearth; Based on the preset installation axis position in the hearth and the advancing linear velocity direction, the advancing linear velocity direction is calibrated as an axial positive direction, and a geometric center point of a first circumferential electromagnetic detection array with a fixed spatial position is defined as an origin of a hearth spatial cylindrical coordinate system along the axial positive direction; a direction vertically pointing to the top of the hearth is calibrated as a circumferential angle zero point direction; For each physical point, according to its identification composed of an initial circumferential angle and an initial axial position, in combination with the real-time rotating angular velocity of the steel pipe, the advancing linear velocity, the known radius and the preset installation axis position in the hearth, the absolute circumferential angle and the absolute axial position of the physical point at the current time are calculated; according to the absolute circumferential angle, the absolute axial position, the known radius and the preset installation axis position in the hearth, the specific spatial coordinates of the physical point in the hearth spatial cylindrical coordinate system are calculated; The specific spatial coordinates of each physical point constituting the heating abnormal region are acquired; the axial coordinate component in the specific spatial coordinates is extracted; the minimum value and the maximum value in the axial coordinate component are determined; and the interval delimited by the minimum value and the maximum value is defined as a current target axial cross-section range; Among all the physical points on the surface of the steel pipe, the physical points whose axial coordinate component of the specific spatial coordinates is located in the current target axial cross-section range and whose circumferential coordinate component is located outside the circumferential coverage range of the heating abnormal region are screened out to form a candidate physical point set; and the region corresponding to the candidate physical point set is defined as the other region of the same steel pipe axial cross-section.

[0038] By strictly limiting the comparison region in the same axial cross-section, it is ensured that the compared “abnormal region” and “reference region” are in the same in-furnace heating section and experience almost the same external thermal history, so as to exclude the interference of the temperature gradient inherent in the steel pipe axial position, so that the calculated temperature deviation purely reflects the non-uniformity of circumferential heating. This accurate spatial delimitation method makes the electromagnetic parameter reference value or the temperature reference value calculated from the normal region have high representativeness and accuracy, as if the abnormal region finds a “mirror” in the same environment, so that the abnormality of the abnormal region can be clearly reflected and quantified. It can be understood that only based on a normal region which is adjacent in space and has highly similar heating conditions, the generated compensation instruction is really for the “non-uniformity” itself, rather than other mixed factors, so as to ensure that the compensation energy is used to correct the real local defects, and finally the limit and real uniformity of the heat treatment in the circumferential and axial directions is effectively guaranteed and improved.

[0039] In another preferred embodiment of the present application, the specific process of performing dynamic energy compensation in S5 is: acquire specific space coordinates of each physical point constituting the heating abnormal area in a cylindrical coordinate system of a hearth space; extract a circumferential coordinate component of each physical point from the specific space coordinates; determine a maximum value and a minimum value in the circumferential coordinate component, and take a difference between the maximum value and the minimum value as a circumferential angular range of the heating abnormal area; based on a real-time rotating angular velocity of the steel pipe and the circumferential angular range, calculate a rotating required time required for the heating abnormal area to rotate through a fixed circumferential action position of the independent heating unit; extract an axial coordinate component of each physical point from the specific space coordinates; determine a maximum value and a minimum value in the axial coordinate component, and take a difference between the maximum value and the minimum value as an axial extension length of the heating abnormal area; based on a real-time advancing linear velocity of the steel pipe and the axial extension length, calculate an advancing required time required for the heating abnormal area to completely pass through an axial action range of the independent heating unit; compare the rotating required time and the advancing required time, and determine a smaller one as an effective action time of the dynamic energy compensation; set an accurate energy compensation window of the independent heating unit according to a starting time in the predicted space-time coordinates and the effective action time; and drive the independent heating unit to perform power adjustment according to the temperature compensation instruction within the accurate energy compensation window.

[0040] Firstly, the established spatial database is called to obtain the specific three-dimensional coordinates of all physical points constituting the heating abnormal area (for example, these points can be distributed in an elliptical patch) in the cylindrical coordinate system of the furnace space; from these coordinate data, the circumferential coordinate component (a set of numerical values in degrees) representing the specific orientation of each point in the annular direction is specially extracted. Through traversal and sorting algorithm, the maximum and minimum values are found from this set of component values, for example, the maximum value is 185 degrees and the minimum value is 155 degrees, and the difference between the two, 30 degrees, is determined as the coverage range of the abnormal area in the circumferential direction of the steel pipe, i.e. the circumferential angular range. Next, the current rotational angular velocity of the steel pipe (for example, 1.5 degrees per second) is read from the real-time data stream of the production line, and the circumferential angular range is divided by this angular velocity to accurately calculate how many seconds the abnormal area needs to rotate to completely sweep the flame coverage area of an independent heating unit (for example, a burner) fixed on the side wall of the furnace, and this calculation result is the rotation required time. At the same time, the axial coordinate component (i.e. the position value along the length direction of the steel pipe) of each physical point is extracted from the same set of three-dimensional coordinates, and the maximum and minimum values are also found, and the difference between them is defined as the size of the abnormal area in the length direction, i.e. the axial extension length. Based on the real-time forward linear velocity of the steel pipe (for example, 10 mm per second), the axial extension length is divided by the forward linear velocity to calculate how many seconds the region needs to completely pass through the effective heating band of the independent heating unit in the length direction, and the forward required time is obtained. Then, the rotation required time and the forward required time are compared, and the smaller one (for example, rotation requires 20 seconds and forward requires 15 seconds, then 15 seconds is selected) is determined as the effective action time of this dynamic energy compensation, which ensures that the heating action only occurs when the region is completely within the effective coverage range of the heating unit. Finally, the starting time of the region predicted before is combined with the effective action time to set an accurate energy compensation window with clear start and end times, and to drive the specified independent heating unit to perform compensation operation according to the power adjustment direction and amplitude required by the temperature compensation instruction strictly within this time window.

[0041] It can be understood that the energy of the heating unit effectively acts on the steel pipe, and two space conditions must be met at the same time: in the circumferential direction, the abnormal area must be rotated to face the action direction of the heating unit; in the axial direction, the abnormal area must be located within the limited action length of the heating unit. Therefore, the real effective compensation period can only be the intersection time when the two conditions are met at the same time. Selecting the smaller one of the "rotation required time" and the "forward required time" is the key operation to accurately define this intersection period - it marks that once this shorter time is exceeded, the abnormal area is either partially rotated out of the heating range in the circumferential direction or partially moved out of the action interval in the axial direction, and continuing to apply energy will lead to misheating of non-target areas or energy waste. The direct purpose of this is to realize instantaneous and accurate focusing of energy, to concentrate the limited compensation energy to the only target area passing by with the highest space-time density and no waste, to ensure the absolute accuracy of the compensation action, to avoid interfering with the heat treatment state of adjacent normal areas due to excessive compensation, and to maintain the stability of the whole process; in terms of economy, it maximizes the compression of the duration of high-power output, realizes the goal of local correction with the least energy cost, and significantly improves energy utilization efficiency.

[0042] In another preferred embodiment of the present application, the S5 further includes re-acquiring and calculating the electromagnetic parameters and temperature deviation values of the to-be-regulated area and other reference areas after adjusting the heating unit according to the temperature compensation instruction, and updating the heating uniformity index according to the temperature compensation instruction; determining whether the updated heating uniformity index has returned to the pre-set uniformity index threshold range; if not, determining the adjustment direction again according to the positive and negative of the current temperature deviation value, and generating further power sub-range adjustment instructions according to the energy flow adjustment step for iterative adjustment; repeat the process until the updated heating uniformity index returns to the normal range.

[0043] The above describes one embodiment of the present application in detail, but the content described is only a preferred embodiment of the present application and cannot be considered as limiting the scope of the present application. Any equivalent changes and improvements made within the scope of the present application should still belong to the patent coverage range of the present application.

Claims

1. A method for monitoring the heating of seamless stainless steel tubes inside a heat treatment furnace, characterized in that, Includes the following steps: S1, the electromagnetic induction signal of the rotating steel pipe in the heat treatment furnace is collected in real time by the circumferential electromagnetic detection array, and the electromagnetic induction signal is synchronously bound with the corresponding timestamp and the coordinates of the detection array unit to obtain the original signal set; S2, obtain the rotational angular velocity and forward linear velocity of the steel pipe, and perform kinematic inversion calculation on the original signal set to obtain the evolution trajectory of the electromagnetic parameters of any physical point on the surface of the steel pipe as a function of time. S3, calculate the dynamic rate of change of each physical point based on its evolution trajectory, and compare the dynamic rate of change with the local background field composed of the rates of change of the physical points that are spatially adjacent to the physical point, to obtain the set of abnormal points whose rates of change continuously deviate from the local background field; S4, perform spatial clustering on the abnormal point set to obtain the heating abnormal region, extract the electromagnetic parameters corresponding to each physical point constituting the heating abnormal region, and input the electromagnetic parameters into the preset electromagnetic-temperature mapping model to obtain the temperature compensation command. S5. Based on the real-time rotation and forward speed of the steel pipe, predict the spatiotemporal coordinates of the heating anomaly area to reach the next heating section. Based on the spatiotemporal coordinates, determine the independent heating unit that needs to be started in the next heating section and, in conjunction with the temperature compensation command, drive the independent heating unit to perform dynamic energy compensation.

2. The method for monitoring the heating of seamless stainless steel tubes in a heat treatment furnace according to claim 1, characterized in that, In S2, the specific process of obtaining the evolutionary trajectory is as follows: The real-time rotational angular velocity and forward linear velocity of the steel pipe, the known radius, and the preset installation axis position inside the furnace are obtained; based on the rotational angular velocity, forward linear velocity, known radius, and preset installation axis position inside the furnace, the surface of the steel pipe is modeled as a cylindrical surface, and the physical points on the cylindrical surface are assigned labels consisting of initial circumferential angles and initial axial positions; Based on the rotational angular velocity and the forward linear velocity, calculate the circumferential angular offset and axial position offset of the physical point from the initial mark over time, and determine its theoretical spatial coordinates relative to the fixed space of the furnace at any time. For each sensing signal with a timestamp and detection unit spatial coordinates in the original signal set, the theoretical spatial coordinates are matched with the detection unit spatial coordinates to determine whether the theoretical spatial coordinates are located within the effective sensing area of ​​the detection unit at the time corresponding to the signal timestamp. When the determination is yes, the sensing signal is associated with the corresponding physical point and used as the state observation value of the physical point at that moment. After traversing all induced signals, a discrete state observation sequence ordered by timestamp is obtained for each physical point; the discrete state observation sequence is smoothed and curve-fitted to obtain the evolution trajectory of the electromagnetic parameters of the physical point as a function of time.

3. The method for monitoring the heating of seamless stainless steel tubes in a heat treatment furnace according to claim 1, characterized in that, In S3, the specific process of obtaining the anomaly set is as follows: Calculate the instantaneous rate of change of the evolution trajectory of each physical point on the surface of the steel pipe and determine the spatially adjacent physical points of each physical point as a candidate neighbor set; Calculate the statistical distribution of the instantaneous change rate of the candidate neighbor point set; based on the statistical distribution, set a preliminary judgment threshold, and select points in the candidate neighbor point set whose instantaneous change rate exceeds the preliminary judgment threshold as candidate points, and remove the candidate points from the candidate neighbor point set to obtain a purified neighbor point set; Calculate the statistical mean and statistical fluctuation range based on the instantaneous change rate of the purified neighbor point set; set a stability judgment threshold based on the statistical fluctuation range; The difference between the instantaneous rate of change of each physical point and the statistical mean is calculated to obtain the purification deviation. Physical points whose purification deviation continuously exceeds the stability judgment threshold are identified as abnormal physical points, and the abnormal physical points are collected to form an abnormal point set.

4. The method for monitoring the heating of seamless stainless steel tubes in a heat treatment furnace according to claim 1, characterized in that, In step S4, the specific construction process of the preset electromagnetic-temperature mapping model is as follows: Multiple pipe section specimens with different characteristic temperature ranges are pre-acquired and heated in a controlled experimental thermal environment according to a preset heating curve. During the heating process, the circumferential electromagnetic detection array is used to synchronously collect the induction signals of each pipe section specimen at multiple characteristic temperature points, and a contact temperature measuring device is used to synchronously measure the actual temperature value of each pipe section specimen at the characteristic temperature point. For each induced signal, demodulation and feature quantity calculation are performed to extract its signal amplitude change and phase shift, which are then used together as electromagnetic parameters. The electromagnetic parameters are used as independent variables, and the actual temperature value, which is strictly paired with the induced signal in time and space, is used as the dependent variable to form calibration data pairs. The least squares method is used to perform regression calculations on all the calibration data pairs to fit a continuous mapping function from the independent variable to the dependent variable. The continuous mapping function is defined as the preset electromagnetic-temperature mapping model.

5. The method for monitoring the heating of seamless stainless steel tubes in a heat treatment furnace according to claim 1, characterized in that, In step S4, the specific process of obtaining the temperature compensation command is as follows: Extract multiple electromagnetic characteristic parameter data corresponding to the heating abnormal area and calculate their average value to obtain the electromagnetic parameter characteristic value of the heating abnormal area; obtain multiple electromagnetic characteristic parameter data corresponding to other areas in the same axial section of the steel pipe as the heating abnormal area and calculate their average value to obtain the electromagnetic parameter reference value; The electromagnetic parameter characteristic values ​​are input into the preset electromagnetic temperature mapping model to obtain the temperature estimate of the heating anomaly region; the electromagnetic parameter reference values ​​are input into the preset electromagnetic temperature mapping model to obtain the temperature reference values. The temperature deviation value is obtained by calculating the difference between the estimated temperature value and the reference temperature value. Based on the absolute value of the temperature deviation, a heating uniformity index is defined. The heating uniformity index is compared with a preset uniformity index threshold range. If the heating uniformity index exceeds the preset uniformity index threshold range, the abnormal heating area is mapped to a specific spatial location within the furnace chamber of the heat treatment furnace and determined as the area to be controlled. The sign of the temperature deviation value is determined. When the temperature deviation value is positive, the direction of temperature adjustment for the region to be controlled is set to increase the energy flow input. When the temperature deviation value is negative, the direction of adjustment is set to decrease the energy flow input. According to the preset energy flow adjustment step size, a temperature compensation command is generated along the adjustment direction to adjust the output power of the independent heating unit corresponding to the region to be controlled in stages.

6. The method for monitoring the heating of seamless stainless steel tubes in a heat treatment furnace according to claim 5, characterized in that, The specific process for defining other regions within the same axial cross-section of the steel pipe is as follows: Obtain the real-time rotational angular velocity and forward linear velocity of the steel pipe, the known radius, and the pre-set installation axis position inside the furnace; Based on the preset installation axis position and forward linear velocity direction inside the furnace, the forward linear velocity direction is calibrated as the positive axial direction, and the geometric center point of the first spatially fixed circumferential electromagnetic detection array along the positive axial direction is defined as the origin of the furnace space cylindrical coordinate system; the direction perpendicular to the top of the furnace is calibrated as the circumferential angle zero point direction. For each physical point, based on its identifier consisting of an initial circumferential angle and an initial axial position, and combined with the real-time rotational angular velocity, forward linear velocity, known radius, and the preset installation axis position within the furnace, the absolute circumferential angle and absolute axial position of the physical point at the current moment are calculated; based on the absolute circumferential angle, absolute axial position, known radius, and the preset installation axis position within the furnace, its specific spatial coordinates in the cylindrical coordinate system of the furnace space are calculated; Obtain the specific spatial coordinates of each physical point constituting the heating anomaly region; extract the axial coordinate components from the specific spatial coordinates; determine the minimum and maximum values ​​of the axial coordinate components; define the interval defined by the minimum and maximum values ​​as the current target axial cross-sectional range; Among all physical points on the surface of the steel pipe, physical points whose axial coordinate components are located within the current target axial section and whose circumferential coordinate components are located outside the circumferential coverage of the heating anomaly area are selected to form a set of candidate physical points; the area corresponding to the set of candidate physical points is defined as other areas within the same axial section of the steel pipe.

7. The method for monitoring the heating of seamless stainless steel tubes in a heat treatment furnace according to claim 6, characterized in that, In S5, the specific process of performing dynamic energy compensation is as follows: Obtain the specific spatial coordinates of each physical point constituting the heating anomaly region in the cylindrical coordinate system of the furnace space; extract the circumferential coordinate components of each physical point from the specific spatial coordinates; determine the maximum and minimum values ​​of the circumferential coordinate components, and use the difference between the maximum and minimum values ​​as the circumferential angle range of the heating anomaly region; based on the real-time rotational angular velocity of the steel pipe and the circumferential angle range, calculate the rotation time required for the heating anomaly region to rotate and sweep across the fixed circumferential action position of the independent heating unit. Extract the axial coordinate components of each physical point from the specific spatial coordinates; determine the maximum and minimum values ​​of the axial coordinate components, and use the difference between the maximum and minimum values ​​as the axial extension length of the heating anomaly region; based on the real-time forward linear velocity of the steel pipe and the axial extension length, calculate the time required for the heating anomaly region to completely pass through the axial range of the independent heating unit. The time required for rotation is compared with the time required for forward movement, and the smaller value is determined as the effective time of the dynamic energy compensation; the precise energy compensation window of the independent heating unit is set according to the start time in the spatiotemporal coordinates and the effective time; the independent heating unit is driven to perform power adjustment according to the temperature compensation command within the precise energy compensation window.

8. A method for monitoring the heating of seamless stainless steel tubes in a heat treatment furnace according to claim 5, characterized in that, S5 further includes adjusting the heating unit according to the temperature compensation command, then re-collecting and calculating the electromagnetic parameters and temperature deviation values ​​of the area to be controlled and other control areas, and updating the heating uniformity index accordingly. Determine whether the updated heating uniformity index has returned to the preset uniformity index threshold range; If the temperature does not return to normal, the adjustment direction is determined again based on the sign of the current temperature deviation value, and further power grading adjustment instructions are generated according to the energy flow adjustment step size for iterative adjustment. Repeat this process until the updated heating uniformity index returns to the normal range.

Images