Annealing furnace temperature parameter control method and system based on multi-source data

Abstract

The application discloses a kind of based on multi-source data's annealing furnace temperature parameter control method and system, it is related to annealing furnace temperature parameter control technical field, the method includes the following steps: data acquisition is carried out to the operation process of annealing furnace, generates annealing process record;Temperature sensor is laid in annealing furnace, and real-time acquisition is carried out to temperature in furnace, the uniformity of temperature field in furnace is measured by calculating temperature equalization degree coefficient, and the time parameter for compensating heat conduction lag effect is determined according to the material characteristics and thickness parameters of workpiece to be handled;Based on the temperature equalization state and process requirement of real-time monitoring, the annealing process is divided into control stage;Through the analysis of temperature equalization degree and cooling rate uniformity at each moment of annealing process, the comprehensive uniformity index is calculated, and whether the annealing furnace control stage is abnormal is determined according to the fluctuation amplitude of the index at each moment does not exceed the preset multiple of the average value of historical uniformity index of same type workpiece, and the application realizes annealing furnace temperature parameter control.

Description

Technical Field

[0001] The present invention relates to the technical field of annealing furnace temperature parameter control, and in particular to an annealing furnace temperature parameter control method and system based on multi-source data. Background Art

[0002] As the manufacturing industry continues to increase its requirements for the performance of metal materials, the annealing process, as a key link in determining the microstructure and mechanical properties of the material, the accuracy of its temperature parameter control, dynamic adaptability and multi-dimensional coordination capabilities affect the quality consistency and production efficiency of the workpiece. Traditional temperature control technology has become difficult to adapt to the modern production needs of multiple varieties and high precision.

[0003] However, traditional annealing furnace temperature control methods often face the following problems when dealing with multi-source data fusion, heat conduction lag compensation and dynamic adaptation of process stages: First, the control dimension is single, and traditional PID control only uses average temperature as feedback, resulting in large deviations in temperature field uniformity when processing different materials or thickness changes, affecting the consistency of phase change structure; second, the lack of heat conduction lag compensation does not consider the influence of workpiece thickness and material thermal diffusion constant on temperature conduction, resulting in excessive temperature overshoot during stage switching, especially when transitioning from the soaking stage to the rapid cooling stage. The lag misjudgment caused by thermal inertia often causes quenching cracks in the workpiece; in addition, the process stage division is extensive and relies on a fixed time-temperature curve, and cannot be dynamically adjusted according to the real-time temperature balance coefficient and cooling rate uniformity. When the temperature difference in the furnace exceeds the allowable range, the traditional method cannot promptly extend the soaking time or adjust the heating power, resulting in structural defects such as coarse grains. Summary of the Invention

[0004] The object of the present invention is to provide a method and system for controlling the temperature parameters of an annealing furnace based on multi-source data, so as to solve the problems raised in the prior art.

[0005] To achieve the above object, the present invention provides the following technical solution: a method for controlling annealing furnace temperature parameters based on multi-source data, the method comprising the following steps:

[0006] Collect real-time data of the annealing furnace operation process and generate annealing process records with time stamps;

[0007] Temperature sensors are placed in the annealing furnace to collect the temperature in real time. The uniformity of the temperature field in the furnace is measured by calculating the temperature balance coefficient. The time parameter used to compensate for the heat conduction hysteresis effect is determined based on the material properties and thickness parameters of the workpiece to be processed.

[0008] Based on the real-time monitoring of temperature equilibrium status and process requirements, the annealing process is divided into control stages;

[0009] The comprehensive uniformity index is calculated by analyzing the temperature balance and cooling rate uniformity at each moment of the annealing process. Whether the annealing furnace control stage is abnormal is determined based on the fact that the fluctuation amplitude of the index at each moment does not exceed the preset multiple of the historical uniformity index average value of the same type of workpiece.

[0010] Real-time data collection of the annealing furnace operation process is performed to generate a time-stamped annealing process temperature correlation record. The specific steps include:

[0011] When the workpiece to be processed triggers the photoelectric switch at the feed end, the unique identifier of the workpiece is obtained. Starting from the above moment, according to the preset sampling period T, multi-source parameters such as temperature, heating power, workpiece material / thickness, furnace gas concentration, and equipment operating status are synchronously collected at discrete times t1, t2, ..., tn. Each sampling generates a structured data record D(ti), which contains the timestamp ti, all the collected parameter values, and the unique identifier of the current workpiece. ti represents the actual time when the corresponding i-th sampling occurred.

[0012] Continue to collect data until the workpiece triggers the discharge detection switch and leaves the furnace area. Then sort all data records {D(t1), D(t2), ..., D(tn)} belonging to the same workpiece unique identifier by timestamp ti to form a complete annealing process time series record of the workpiece, where D(t1), D(t2), ..., D(tn) represent the multi-source parameter data collected at the corresponding time t1, t2, ..., tn respectively.

[0013] By comparing the deviation between the time intervals of adjacent data points and the preset sampling period, combined with the upper and lower thresholds of temperature and equipment operating parameters, abnormal data points are identified and marked.

[0014] Temperature sensors are placed in the annealing furnace to collect the temperature in real time. The uniformity of the temperature field in the furnace is measured by calculating the temperature balance coefficient. The time parameter used to compensate for the heat conduction hysteresis effect is determined based on the material properties and thickness parameters of the workpiece to be processed. The specific steps include:

[0015] m temperature sensors are arranged in the annealing furnace to collect the temperature values ​​of each point in real time and construct the temperature balance coefficient, which is defined as follows: TUC(t)=1-(maxj(Tj(t))-minj(Tj(t))) / ΔTref; where TUC(t) represents the temperature balance coefficient at time t; Tj(t) represents the temperature value collected by the j-th temperature sensor at time t; maxj(Tj(t)) and minj(Tj(t)) represent the highest and lowest temperatures of all sensors at time t, respectively; j represents the number index of the temperature sensor, indicating the j-th temperature sensor; j=1,2,...,m; ΔTref represents the reference temperature difference, which is the maximum temperature fluctuation range allowed in this stage;

[0016] Calculate the hysteresis compensation time, which is defined as follows: τ=k*δ 2 ; Wherein, τ represents the hysteresis compensation time; k represents the material-related thermal diffusion time constant; δ represents the thickness of the workpiece to be processed.

[0017] Based on the real-time monitoring of the temperature equilibrium state and process requirements, the annealing process is divided into control stages. The specific steps include:

[0018] By real-time monitoring of the equilibrium state of the temperature field in the furnace and combining it with process requirements, the annealing process is divided into q control stages based on the temperature balance coefficient and hysteresis compensation time. The specific process is as follows: real-time collection of the temperature of each sensor in the soaking zone, calculation of the current temperature balance coefficient and hysteresis time, and evaluation of the stage state. When it is detected that the temperature balance coefficient reaches the threshold of the next stage, the stage is not switched immediately, but the hysteresis compensation time is waited. After the hysteresis compensation time, the temperature balance coefficient is re-evaluated. If the threshold is still met, the stage is switched. If not, the current stage is maintained and an alarm is issued. When it is detected that the temperature balance coefficient does not reach the threshold of the next stage, the current stage is extended or the control parameters are adjusted.

[0019] The comprehensive uniformity index is calculated by analyzing the temperature balance and cooling rate uniformity at each moment of the annealing process. The fluctuation range of the index at each moment does not exceed the preset multiple of the historical uniformity index average value of the same type of workpiece to determine whether the annealing furnace control stage is abnormal. The specific steps include:

[0020] The comprehensive uniformity index is calculated by analyzing the temperature balance coefficient at each moment of the annealing process and the uniformity of the cooling rate, and is defined as follows:

[0021] ;

[0022] Where CUI(t) represents the comprehensive uniformity index at time t; w1 and w2 represent dynamic weight coefficients; v j (t) represents the cooling rate of the jth sensor position at time t, It represents the average cooling rate of all sensors; m represents the total number of temperature sensors; Vref represents the standard cooling rate required by the process;

[0023] Analyze the uniformity index at each moment. If the fluctuation range of the uniformity index at the current moment does not exceed the preset multiple of the historical uniformity index average value of the same type of workpieces to be processed, it means that the annealing furnace process is normal at the current moment. Analyze the uniformity index corresponding to the moment of the current stage one by one to determine whether the annealing furnace control stage is normal.

[0024] An annealing furnace temperature parameter control system based on multi-source data comprises: a multi-source data acquisition module, a temperature balance and hysteresis compensation module, a control stage division module, and an abnormality determination module. The multi-source data acquisition module is used to perform real-time data acquisition on the operation process of the annealing furnace and generate an annealing process record with a time stamp. The temperature balance and hysteresis compensation module is used to arrange temperature sensors in the annealing furnace to collect the temperature in the furnace in real time, measure the uniformity of the temperature field in the furnace by calculating the temperature balance coefficient, and determine the time parameter for compensating for the heat conduction hysteresis effect based on the material properties and thickness parameters of the workpiece to be processed. The control stage division module is used to divide the annealing process into control stages based on the real-time monitored temperature balance state and process requirements. The abnormality determination module is used to calculate a comprehensive uniformity index by analyzing the temperature balance and cooling rate uniformity at each moment of the annealing process, and determine whether the annealing furnace control stage is abnormal based on the fluctuation amplitude of the index at each moment not exceeding a preset multiple of the average value of the historical uniformity index of the same type of workpiece.

[0025] The multi-source data acquisition module includes a data acquisition unit and an abnormal data processing unit. The data acquisition unit is used to trigger the binding of the workpiece unique identifier and synchronously collect multi-source parameters such as temperature, heating power, workpiece material / thickness, furnace gas concentration and equipment operating status according to a preset cycle; the abnormal data processing unit is used to identify and mark abnormal data points by comparing the deviation between the time interval of adjacent data points and the preset sampling cycle, combined with the upper and lower limit thresholds of temperature and equipment operating parameters. The output end of the data acquisition unit is connected to the input end of the abnormal data processing unit, and the output end of the abnormal data processing unit is connected to the input end of the temperature balance and hysteresis compensation module.

[0026] The temperature balance and hysteresis compensation module includes a temperature balance calculation unit and a hysteresis compensation time calculation unit; the temperature balance calculation unit is used to calculate the temperature balance coefficient according to the sensor data; the hysteresis compensation time calculation unit is used to calculate the hysteresis compensation time according to the formula; the output end of the temperature balance and hysteresis compensation module is connected to the input end of the control stage division module.

[0027] The control stage division module includes a stage division strategy unit, a state evaluation unit and a stage switching control unit; the stage division strategy unit is used to preset different control stages according to process requirements and define the temperature balance coefficient threshold of each stage; the state evaluation unit is used to calculate the current temperature balance coefficient and the hysteresis compensation time in real time to evaluate whether the stage switching conditions are met; the stage switching control unit is used to wait for the hysteresis compensation time to re-evaluate when the temperature balance coefficient meets the standard, and switch the stage if it meets the standard, otherwise alarm and maintain the current stage, the output end of the stage division strategy unit is connected to the input end of the state evaluation unit, the output end of the state evaluation unit is connected to the input end of the stage switching control unit, and the output end of the stage switching control unit is connected to the input end of the abnormality judgment module.

[0028] The abnormality judgment module includes a cooling rate analysis unit, a comprehensive uniformity index calculation unit and a real-time fluctuation evaluation unit; the cooling rate analysis unit is used to calculate the cooling rate of each sensor; the comprehensive uniformity index calculation unit is used to calculate the comprehensive uniformity index by analyzing the temperature balance coefficient and the uniformity of the cooling rate at each moment of the annealing process; the real-time fluctuation evaluation unit is used to analyze the uniformity index at each moment, and the fluctuation amplitude of the uniformity index at the current moment does not exceed the preset multiple of the historical uniformity index average value of the same type of workpiece to be processed, indicating that the annealing furnace process is normal at the current moment, and the uniformity index corresponding to the moment of the current stage is analyzed one by one to determine whether the annealing furnace control stage is normal, the output end of the cooling rate analysis unit is connected to the input end of the comprehensive uniformity index calculation unit, and the output end of the comprehensive uniformity index calculation unit is connected to the input end of the real-time fluctuation evaluation unit.

[0029] Compared with the prior art, the present invention has the following beneficial effects:

[0030] 1. By integrating multiple parameters such as the temperature balance coefficient and cooling rate uniformity, a comprehensive uniformity index is constructed. Unlike the single-dimensional method in the existing technology that only uses average temperature as the control target, this invention captures the relationship between temperature field distribution, heat conduction hysteresis and cooling dynamics to achieve multi-dimensional coordinated control;

[0031] 2. This invention introduces a hysteresis compensation mechanism and a dynamic stage division module based on a material thermal diffusion model. This automatically adjusts the process stage switching logic based on real-time temperature balance assessment results. Unlike the static control mode of fixed time-temperature curves in existing technologies, this method calculates the hysteresis compensation time in real time based on parameters such as workpiece thickness and material thermal diffusion constant, thus avoiding stage misjudgment caused by heat conduction delays.

[0032] 3. Relying on multi-source data structured collection and anomaly identification technology, the present invention establishes a time-series workpiece archive containing parameters such as temperature, power, and atmosphere concentration. Through the historical uniformity index benchmark library and real-time fluctuation assessment, the full-cycle quality traceability and anomaly warning of the annealing process are achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 Schematic diagram of a flow chart of a method for controlling temperature parameters of an annealing furnace based on multi-source data according to the present invention;

[0034] Figure 2 The present invention is a structural schematic diagram of an annealing furnace temperature parameter control system based on multi-source data. DETAILED DESCRIPTION

[0035] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0036] In the embodiment: Figure 1-Figure 2 As shown, the present invention provides a technical solution, a method for controlling annealing furnace temperature parameters based on multi-source data, the method comprising the following steps:

[0037] Collect real-time data of the annealing furnace operation process and generate annealing process records with time stamps;

[0038] Temperature sensors are placed in the annealing furnace to collect the temperature in real time. The uniformity of the temperature field in the furnace is measured by calculating the temperature balance coefficient. The time parameter used to compensate for the heat conduction hysteresis effect is determined based on the material properties and thickness parameters of the workpiece to be processed.

[0039] Based on the real-time monitoring of temperature equilibrium status and process requirements, the annealing process is divided into control stages;

[0040] The comprehensive uniformity index is calculated by analyzing the temperature balance and cooling rate uniformity at each moment of the annealing process. Whether the annealing furnace control stage is abnormal is determined based on the fact that the fluctuation amplitude of the index at each moment does not exceed the preset multiple of the historical uniformity index average value of the same type of workpiece.

[0041] Real-time data collection of the annealing furnace operation process is performed to generate a time-stamped annealing process temperature correlation record. The specific steps include:

[0042] When the workpiece to be processed triggers the photoelectric switch at the feed end, the unique identifier of the workpiece is obtained. Starting from the above moment, according to the preset sampling period T, multi-source parameters such as temperature, heating power, workpiece material / thickness, furnace gas concentration, and equipment operating status are synchronously collected at discrete times t1, t2, ..., tn. Each sampling generates a structured data record D(ti), which contains the timestamp ti, all the collected parameter values, and the unique identifier of the current workpiece. ti represents the actual time when the corresponding i-th sampling occurred.

[0043] Continue to collect data until the workpiece triggers the discharge detection switch and leaves the furnace area. Then sort all data records {D(t1), D(t2), ..., D(tn)} belonging to the same workpiece unique identifier by timestamp ti to form a complete annealing process time series record of the workpiece, where D(t1), D(t2), ..., D(tn) represent the multi-source parameter data collected at the corresponding time t1, t2, ..., tn respectively.

[0044] By comparing the deviation between the time intervals of adjacent data points and the preset sampling period, combined with the upper and lower thresholds of temperature and equipment operating parameters, abnormal data points are identified and marked.

[0045] Specifically, the workpiece material to be processed is 45# steel (thermal diffusion constant k=0.05m² / h), the thickness is 10mm, and the process goal is complete annealing. Five temperature sensors are arranged in the annealing furnace, and the sampling period is 1 minute.

[0046] The workpiece triggers the photoelectric switch at the feeding end, generates UID=20250625-001, and starts sampling;

[0047] Data is collected synchronously at discrete time instants t1 = 1 min, t2 = 2 min, …, t10 = 10 min. For example, at time t5, D(t5) = {timestamp: 2025-06-25T09:05:00, temperature: [820°C, 822°C, 818°C, 825°C, 815°C], heating power: 75 kW, material / thickness: 45# steel / 10 mm, furnace atmosphere: N2 concentration 99.5%, equipment status: fan speed 1200 rpm};

[0048] The temperature data at t3 = 3 min were detected [750°C, 820°C, 815°C, 822°C, 818°C]. It was found that the temperature of the first sensor, 750°C, was lower than the lower limit of 800°C (ΔT = 50°C). It was marked as an abnormal point and corrected to 817°C using linear interpolation of adjacent points.

[0049] Temperature sensors are placed in the annealing furnace to collect the temperature in real time. The uniformity of the temperature field in the furnace is measured by calculating the temperature balance coefficient. The time parameter used to compensate for the heat conduction hysteresis effect is determined based on the material properties and thickness parameters of the workpiece to be processed. The specific steps include:

[0050] m temperature sensors are arranged in the annealing furnace to collect the temperature values ​​of each point in real time and construct the temperature balance coefficient, which is defined as follows: TUC(t)=1-(maxj(Tj(t))-minj(Tj(t))) / ΔTref; where TUC(t) represents the temperature balance coefficient at time t; Tj(t) represents the temperature value collected by the j-th temperature sensor at time t; maxj(Tj(t)) and minj(Tj(t)) represent the highest and lowest temperatures of all sensors at time t, respectively; j represents the number index of the temperature sensor, indicating the j-th temperature sensor; j=1,2,...,m; ΔTref represents the reference temperature difference, which is the maximum temperature fluctuation range allowed in this stage;

[0051] Calculate the hysteresis compensation time, which is defined as follows: τ=k*δ 2 ; Wherein, τ represents the hysteresis compensation time; k represents the material-related thermal diffusion time constant; δ represents the thickness of the workpiece to be processed.

[0052] Specifically, the measured temperatures are 848°C, 852°C, 850°C, 847°C and 851°C, respectively. The reference temperature difference is 10°C, and the temperature balance coefficient is calculated to be 0.5. The hysteresis compensation time is calculated to be 1.08s based on the hysteresis compensation time. At the same time, the temperature balance coefficient and hysteresis compensation time at other times can be calculated.

[0053] Based on the real-time monitoring of the temperature equilibrium state and process requirements, the annealing process is divided into control stages. The specific steps include:

[0054] By real-time monitoring of the equilibrium state of the temperature field in the furnace and combining it with process requirements, the annealing process is divided into q control stages based on the temperature balance coefficient and hysteresis compensation time. The specific process is as follows: real-time collection of the temperature of each sensor in the soaking zone, calculation of the current temperature balance coefficient and hysteresis time, and evaluation of the stage state. When it is detected that the temperature balance coefficient reaches the threshold of the next stage, the stage is not switched immediately, but the hysteresis compensation time is waited. After the hysteresis compensation time, the temperature balance coefficient is re-evaluated. If the threshold is still met, the stage is switched. If not, the current stage is maintained and an alarm is issued. When it is detected that the temperature balance coefficient does not reach the threshold of the next stage, the current stage is extended or the control parameters are adjusted.

[0055] Specifically, the target for the soaking section is 0.8, and the current value is 0.5 < 0.8, indicating that the target is not met.

[0056] Adjustment strategy: Extend the soaking time, increase the heating power from 75kW to 80kW, and start the furnace circulation fan at 1500rpm;

[0057] Second evaluation (t=40min), at this time the temperature balance coefficient is 0.6<0.8, which means it still does not meet the standard and the time is further extended;

[0058] Evaluation three times (t=50min): At this time, the temperature balance coefficient is 0.8, which meets the standard. After waiting for the lag compensation time to reach 1.08s, re-evaluation is performed. The temperature balance coefficient is still 0.8, and the process switches to the next stage.

[0059] The comprehensive uniformity index is calculated by analyzing the temperature balance and cooling rate uniformity at each moment of the annealing process. The fluctuation range of the index at each moment does not exceed the preset multiple of the historical uniformity index average value of the same type of workpiece to determine whether the annealing furnace control stage is abnormal. The specific steps include:

[0060] The comprehensive uniformity index is calculated by analyzing the temperature balance coefficient at each moment of the annealing process and the uniformity of the cooling rate, and is defined as follows:

[0061] ;

[0062] Where CUI(t) represents the comprehensive uniformity index at time t; w1 and w2 represent dynamic weight coefficients; v j (t) represents the cooling rate of the jth sensor position at time t, It represents the average cooling rate of all sensors; m represents the total number of temperature sensors; Vref represents the standard cooling rate required by the process;

[0063] Analyze the uniformity index at each moment. If the fluctuation range of the uniformity index at the current moment does not exceed the preset multiple of the historical uniformity index average value of the same type of workpieces to be processed, it means that the annealing furnace process is normal at the current moment. Analyze the uniformity index corresponding to the moment of the current stage one by one to determine whether the annealing furnace control stage is normal.

[0064] Specifically, the weights w1=0.3 and w2=0.7 are set, and the calculated comprehensive uniformity index is 0.799. For the historical average comprehensive uniformity index = 0.85, the preset fluctuation multiple is 1.5, and the allowable lower limit is 0.7225. The current CUI=0.799>0.7225, indicating that the process is normal.

[0065] An annealing furnace temperature parameter control system based on multi-source data comprises: a multi-source data acquisition module, a temperature balance and hysteresis compensation module, a control stage division module, and an abnormality determination module. The multi-source data acquisition module is used to perform real-time data acquisition on the operation process of the annealing furnace and generate an annealing process record with a time stamp. The temperature balance and hysteresis compensation module is used to arrange temperature sensors in the annealing furnace to collect the temperature in the furnace in real time, measure the uniformity of the temperature field in the furnace by calculating the temperature balance coefficient, and determine the time parameter for compensating for the heat conduction hysteresis effect based on the material properties and thickness parameters of the workpiece to be processed. The control stage division module is used to divide the annealing process into control stages based on the real-time monitored temperature balance state and process requirements. The abnormality determination module is used to calculate a comprehensive uniformity index by analyzing the temperature balance and cooling rate uniformity at each moment of the annealing process, and determine whether the annealing furnace control stage is abnormal based on the fluctuation amplitude of the index at each moment not exceeding a preset multiple of the average value of the historical uniformity index of the same type of workpiece.

[0066] The multi-source data acquisition module includes a data acquisition unit and an abnormal data processing unit. The data acquisition unit is used to trigger the binding of the workpiece unique identifier and synchronously collect multi-source parameters such as temperature, heating power, workpiece material / thickness, furnace gas concentration and equipment operating status according to a preset cycle; the abnormal data processing unit is used to identify and mark abnormal data points by comparing the deviation between the time interval of adjacent data points and the preset sampling cycle, combined with the upper and lower limit thresholds of temperature and equipment operating parameters. The output end of the data acquisition unit is connected to the input end of the abnormal data processing unit, and the output end of the abnormal data processing unit is connected to the input end of the temperature balance and hysteresis compensation module.

[0067] The temperature balance and hysteresis compensation module includes a temperature balance calculation unit and a hysteresis compensation time calculation unit; the temperature balance calculation unit is used to calculate the temperature balance coefficient according to the sensor data; the hysteresis compensation time calculation unit is used to calculate the hysteresis compensation time according to the formula; the output end of the temperature balance and hysteresis compensation module is connected to the input end of the control stage division module.

[0068] The control stage division module includes a stage division strategy unit, a state evaluation unit and a stage switching control unit; the stage division strategy unit is used to preset different control stages according to process requirements and define the temperature balance coefficient threshold of each stage; the state evaluation unit is used to calculate the current temperature balance coefficient and the hysteresis compensation time in real time to evaluate whether the stage switching conditions are met; the stage switching control unit is used to wait for the hysteresis compensation time to re-evaluate when the temperature balance coefficient meets the standard, and switch the stage if it meets the standard, otherwise alarm and maintain the current stage, the output end of the stage division strategy unit is connected to the input end of the state evaluation unit, the output end of the state evaluation unit is connected to the input end of the stage switching control unit, and the output end of the stage switching control unit is connected to the input end of the abnormality judgment module.

[0069] The abnormality judgment module includes a cooling rate analysis unit, a comprehensive uniformity index calculation unit and a real-time fluctuation evaluation unit; the cooling rate analysis unit is used to calculate the cooling rate of each sensor; the comprehensive uniformity index calculation unit is used to calculate the comprehensive uniformity index by analyzing the temperature balance coefficient and the uniformity of the cooling rate at each moment of the annealing process; the real-time fluctuation evaluation unit is used to analyze the uniformity index at each moment, and the fluctuation amplitude of the uniformity index at the current moment does not exceed the preset multiple of the historical uniformity index average value of the same type of workpiece to be processed, indicating that the annealing furnace process is normal at the current moment, and the uniformity index corresponding to the moment of the current stage is analyzed one by one to determine whether the annealing furnace control stage is normal, the output end of the cooling rate analysis unit is connected to the input end of the comprehensive uniformity index calculation unit, and the output end of the comprehensive uniformity index calculation unit is connected to the input end of the real-time fluctuation evaluation unit.

[0070] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above and that the invention can be embodied in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims, not the foregoing description, and all variations within the meaning and range of equivalents of the claims are intended to be included therein. Any reference sign in a claim should not be construed as limiting the claim to which it relates.

Claims

1. A method for controlling annealing furnace temperature parameters based on multi-source data, characterized in that: The method comprises the following steps: Collect real-time data of the annealing furnace operation process and generate annealing process records with time stamps; Temperature sensors are placed in the annealing furnace to collect the temperature in real time. The uniformity of the temperature field in the furnace is measured by calculating the temperature balance coefficient. The time parameter used to compensate for the heat conduction hysteresis effect is determined based on the material properties and thickness parameters of the workpiece to be processed. m temperature sensors are arranged in the annealing furnace to collect the temperature values ​​of each point in real time and construct the temperature balance coefficient, which is defined as follows: TUC(t)=1-(maxj(Tj(t))-minj(Tj(t))) / ΔTref; where TUC(t) represents the temperature balance coefficient at time t; Tj(t) represents the temperature value collected by the j-th temperature sensor at time t; maxj(Tj(t)) and minj(Tj(t)) represent the highest and lowest temperatures of all sensors at time t, respectively; j represents the number index of the temperature sensor, indicating the j-th temperature sensor; j=1,2,...,m; ΔTref represents the reference temperature difference, which is the maximum temperature fluctuation range allowed in this stage; Calculate the hysteresis compensation time, which is defined as follows: τ=k*δ 2 ; Wherein, τ represents the hysteresis compensation time; k represents the material-related thermal diffusion time constant; δ represents the thickness of the workpiece to be processed; Based on the real-time monitoring of temperature equilibrium status and process requirements, the annealing process is divided into control stages; By real-time monitoring of the equilibrium state of the temperature field in the furnace, combined with process requirements, the annealing process is divided into q control stages based on the temperature balance coefficient and hysteresis compensation time. The specific process is as follows: real-time acquisition of the temperature of each sensor in the soaking zone, calculation of the current temperature balance coefficient and hysteresis time, and evaluation of the stage state. When it is detected that the temperature balance coefficient reaches the threshold of the next stage, the stage is not switched immediately, but the hysteresis compensation time is waited. After the hysteresis compensation time, the temperature balance coefficient is re-evaluated. If the threshold is still met, the stage is switched. If not, the current stage is maintained and an alarm is issued. When it is detected that the temperature balance coefficient does not reach the threshold of the next stage, the current stage is extended or the control parameters are adjusted. By analyzing the temperature balance and cooling rate uniformity at each moment of the annealing process, the comprehensive uniformity index is calculated. If the fluctuation range of the index at each moment does not exceed the preset multiple of the historical uniformity index average value of the same type of workpiece, it is determined whether the annealing furnace control stage is abnormal; The comprehensive uniformity index is calculated by analyzing the temperature balance coefficient at each moment of the annealing process and the uniformity of the cooling rate, and is defined as follows: ； Where CUI(t) represents the comprehensive uniformity index at time t; w1 and w2 represent dynamic weight coefficients; v j (t) represents the cooling rate of the jth sensor position at time t, It represents the average cooling rate of all sensors; m represents the total number of temperature sensors; Vref represents the standard cooling rate required by the process; Analyze the uniformity index at each moment. If the fluctuation range of the uniformity index at the current moment does not exceed the preset multiple of the historical uniformity index average value of the same type of workpieces to be processed, it means that the annealing furnace process is normal at the current moment. Analyze the uniformity index corresponding to the moment of the current stage one by one to determine whether the annealing furnace control stage is normal.

2. The method for controlling annealing furnace temperature parameters based on multi-source data according to claim 1, characterized in that: Real-time data collection of the annealing furnace operation process is performed to generate a time-stamped annealing process temperature correlation record. The specific steps include: When the workpiece to be processed triggers the photoelectric switch at the feed end, the unique identifier of the workpiece is obtained. Starting from the above moment, according to the preset sampling period T, multi-source parameters such as temperature, heating power, workpiece material / thickness, furnace gas concentration, and equipment operating status are synchronously collected at discrete times t1, t2, ..., tn. Each sampling generates a structured data record D(ti), which contains the timestamp ti, all the collected parameter values, and the unique identifier of the current workpiece. ti represents the actual time when the corresponding i-th sampling occurred. Continue to collect data until the workpiece triggers the discharge detection switch and leaves the furnace area. Then sort all data records {D(t1), D(t2), ..., D(tn)} belonging to the same workpiece unique identifier by timestamp ti to form a complete annealing process time series record of the workpiece, where D(t1), D(t2), ..., D(tn) represent the multi-source parameter data collected at the corresponding time t1, t2, ..., tn respectively. By comparing the deviation between the time intervals of adjacent data points and the preset sampling period, combined with the upper and lower thresholds of temperature and equipment operating parameters, abnormal data points are identified and marked.

3. An annealing furnace temperature parameter control system based on multi-source data, applied to the annealing furnace temperature parameter control method based on multi-source data according to any one of claims 1-2, characterized in that: The system includes: a multi-source data acquisition module, a temperature balance and hysteresis compensation module, a control stage division module and an abnormality judgment module. The multi-source data acquisition module is used to collect real-time data of the annealing furnace operation process and generate an annealing process record with a time stamp; the temperature balance and hysteresis compensation module is used to arrange temperature sensors in the annealing furnace to collect the temperature in the furnace in real time, measure the uniformity of the temperature field in the furnace by calculating the temperature balance coefficient, and determine the time parameter for compensating for the heat conduction hysteresis effect according to the material properties and thickness parameters of the workpiece to be processed; the control stage division module is used to divide the annealing process into control stages based on the real-time monitored temperature balance status and process requirements; the abnormality judgment module is used to calculate a comprehensive uniformity index by analyzing the temperature balance and cooling rate uniformity at each moment of the annealing process, and determine whether the annealing furnace control stage is abnormal based on the fluctuation amplitude of the index at each moment not exceeding a preset multiple of the historical uniformity index average value of the same type of workpiece.

4. The annealing furnace temperature parameter control system based on multi-source data according to claim 3, characterized in that: The multi-source data acquisition module includes a data acquisition unit and an abnormal data processing unit. The data acquisition unit is used to trigger the binding of the workpiece unique identifier and synchronously collect multi-source parameters such as temperature, heating power, workpiece material / thickness, furnace gas concentration and equipment operating status according to a preset cycle; the abnormal data processing unit is used to identify and mark abnormal data points by comparing the deviation between the time interval of adjacent data points and the preset sampling cycle, combined with the upper and lower limit thresholds of temperature and equipment operating parameters. The output end of the data acquisition unit is connected to the input end of the abnormal data processing unit, and the output end of the abnormal data processing unit is connected to the input end of the temperature balance and hysteresis compensation module.

5. The annealing furnace temperature parameter control system based on multi-source data according to claim 4, characterized in that: The temperature balance and hysteresis compensation module includes a temperature balance calculation unit and a hysteresis compensation time calculation unit; the temperature balance calculation unit is used to calculate the temperature balance coefficient according to the sensor data; the hysteresis compensation time calculation unit is used to calculate the hysteresis compensation time according to the formula; the output end of the temperature balance and hysteresis compensation module is connected to the input end of the control stage division module.

6. The annealing furnace temperature parameter control system based on multi-source data according to claim 5, characterized in that: The control stage division module includes a stage division strategy unit, a state evaluation unit and a stage switching control unit; the stage division strategy unit is used to preset different control stages according to process requirements and define the temperature balance coefficient threshold of each stage; the state evaluation unit is used to calculate the current temperature balance coefficient and the hysteresis compensation time in real time to evaluate whether the stage switching conditions are met; the stage switching control unit is used to wait for the hysteresis compensation time to re-evaluate when the temperature balance coefficient meets the standard, and switch the stage if it meets the standard, otherwise alarm and maintain the current stage, the output end of the stage division strategy unit is connected to the input end of the state evaluation unit, the output end of the state evaluation unit is connected to the input end of the stage switching control unit, and the output end of the stage switching control unit is connected to the input end of the abnormality judgment module.

7. The annealing furnace temperature parameter control system based on multi-source data according to claim 6, characterized in that: The abnormality judgment module includes a cooling rate analysis unit, a comprehensive uniformity index calculation unit and a real-time fluctuation evaluation unit; the cooling rate analysis unit is used to calculate the cooling rate of each sensor; the comprehensive uniformity index calculation unit is used to calculate the comprehensive uniformity index by analyzing the temperature balance coefficient and the uniformity of the cooling rate at each moment of the annealing process; the real-time fluctuation evaluation unit is used to analyze the uniformity index at each moment, and the fluctuation amplitude of the uniformity index at the current moment does not exceed the preset multiple of the historical uniformity index average value of the same type of workpiece to be processed, indicating that the annealing furnace process is normal at the current moment, and the uniformity index corresponding to the moment of the current stage is analyzed one by one to determine whether the annealing furnace control stage is normal, the output end of the cooling rate analysis unit is connected to the input end of the comprehensive uniformity index calculation unit, and the output end of the comprehensive uniformity index calculation unit is connected to the input end of the real-time fluctuation evaluation unit.

Images