Dual-phase steel forming method and system based on critical zone heat treatment

Abstract

The invention discloses a dual-phase steel forming method and system based on critical zone heat treatment, and relates to the technical field of material heat treatment.The dual-phase steel forming method comprises the steps that material characteristics and geometric dimensions of a to-be-treated workpiece are obtained, and a heat treatment temperature control curve is determined; the method comprises the steps that a heating control area, a heat preservation control area and a cooling control area are configured, small-batch machining is conducted on workpieces to be treated, temperature monitoring and microstructure change collection are conducted, and a plurality of actual heat treatment curves, a plurality of microstructure change sequences and a plurality of dual-phase steel workpieces are obtained; generating a target microstructure change prediction model of the to-be-processed workpiece based on the microstructure change general prediction model; and the to-be-treated workpieces are subjected to mass production, real-time prediction control and overall prediction optimization are carried out, and dual-phase steel forming control is carried out. According to the method, the technical problems of low microstructure control precision and poor process consistency in the heat treatment process of the dual-phase steel in the prior art are solved, and the technical effects of precise forming and performance stability of the dual-phase steel workpiece in production are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of material heat treatment, and in particular to a dual-phase steel forming method and system based on critical zone heat treatment. Background Art

[0002] With the increasing demand for high-performance materials in industrial production, dual-phase steel has been widely used in the fields of automobile manufacturing, construction and engineering machinery due to its excellent strength and toughness. In order to fully tap the performance advantages of dual-phase steel, heat treatment technology based on critical zones has become the key to the forming process. However, with the expansion of production scale and the improvement of process requirements, the heat treatment process control of dual-phase steel also faces many challenges. The traditional heat treatment process of dual-phase steel has low microstructure control accuracy and poor process consistency, which makes it difficult to meet the requirements of modern industry for efficient, precise and consistent forming of dual-phase steel. Summary of the invention

[0003] The present application provides a dual-phase steel forming method and system based on critical zone heat treatment, which is used to solve the technical problems of low microstructure control accuracy and poor process consistency in the dual-phase steel heat treatment process in the prior art.

[0004] In view of the above problems, the present application provides a dual-phase steel forming method and system based on critical zone heat treatment.

[0005] In a first aspect of the present application, a dual-phase steel forming method based on intercritical heat treatment is provided, the method comprising: The material properties and geometric dimensions of the workpiece to be processed are obtained, and a heat treatment temperature control curve is determined based on the material properties and the geometric dimensions; the heat treatment temperature control curve is segmented to obtain a heating control curve, a heat preservation control curve and a cooling control curve, and the heating control zone, the heat preservation control zone and the cooling control zone are configured accordingly; according to the configured heating control zone, the heat preservation control zone and the cooling control zone, the workpiece to be processed is processed in small batches, and temperature monitoring and microstructure change collection are performed simultaneously to obtain multiple actual heat treatment curves, multiple microstructure change sequences and multiple dual-phase steel workpieces; based on the multiple actual heat treatment curves, multiple microstructure change sequences and multiple dual-phase steel workpieces, a target microstructure change prediction model of the workpiece to be processed is generated in combination with a general prediction model for microstructure change; the workpiece to be processed is mass-produced, and real-time prediction control and overall prediction optimization of the mass production process are performed through the target microstructure change prediction model to perform dual-phase steel forming control.

[0006] A second aspect of the present application provides a dual-phase steel forming system based on intercritical heat treatment, the system comprising: a temperature control curve determination module, the temperature control curve determination module acquires the material properties and geometric dimensions of the workpiece to be processed, and determines the heat treatment temperature control curve based on the material properties and the geometric dimensions; a curve segmentation module, the curve segmentation module segments the heat treatment temperature control curve, acquires the heating control curve, the insulation control curve and the cooling control curve, and configures the heating control area, the insulation control area and the cooling control area accordingly; a processing data acquisition module, the processing data acquisition module performs small batch processing on the workpiece to be processed according to the configured heating control area, the insulation control area and the cooling control area, Temperature monitoring and microstructure change collection are performed simultaneously to obtain multiple actual heat treatment curves, multiple microstructure change sequences and multiple dual-phase steel workpieces; a prediction model generation module, which generates a target microstructure change prediction model for the workpiece to be processed based on the multiple actual heat treatment curves, multiple microstructure change sequences and multiple dual-phase steel workpieces, combined with a general microstructure change prediction model; a forming control module, which performs mass production of the workpiece to be processed, performs real-time prediction control and overall prediction optimization of the mass production process through the target microstructure change prediction model, and performs dual-phase steel forming control.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages: The present application obtains the material properties and geometric dimensions of the workpiece to be processed, and determines the heat treatment temperature control curve based on the material properties and geometric dimensions; divides the heat treatment temperature control curve to obtain the heating control curve, the insulation control curve and the cooling control curve, and configures the heating control zone, the insulation control zone and the cooling control zone accordingly; according to the configured heating control zone, the insulation control zone and the cooling control zone, the workpiece to be processed is processed in small batches, and temperature monitoring and microstructure change collection are performed simultaneously to obtain multiple actual heat treatment curves, multiple microstructure change sequences and multiple dual-phase steel workpieces; based on the multiple actual heat treatment curves, multiple microstructure change sequences and multiple dual-phase steel workpieces, combined with the general prediction model for microstructure change, a target microstructure change prediction model for the workpiece to be processed is generated; the workpiece to be processed is mass-produced, and the mass production process is real-time predictive control and overall predictive optimization are performed through the target microstructure change prediction model to perform dual-phase steel forming control. The present invention solves the technical problems of low microstructure control accuracy and poor process consistency in the heat treatment process of dual-phase steel in the prior art. An adaptive heat treatment temperature control curve is generated by acquiring the material properties and dimensions of the workpiece, and the heating, insulation and cooling processes are controlled in sections. The actual heat treatment data and microstructure change sequence are collected, and a microstructure change prediction model is generated in combination with a general prediction model. Through real-time prediction control and overall optimization, the technical effect of precise forming and performance stability of dual-phase steel workpieces in production is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0009] Figure 1 A schematic flow chart of a dual-phase steel forming method based on critical zone heat treatment provided in an embodiment of the present application; Figure 2 A schematic diagram of the structure of a dual-phase steel forming system based on critical zone heat treatment provided in an embodiment of the present application.

[0010] Explanation of the reference numerals: temperature control curve determination module 11 , curve segmentation module 12 , processing data acquisition module 13 , prediction model generation module 14 , molding control module 15 . DETAILED DESCRIPTION

[0011] The present application provides a dual-phase steel forming method and system based on critical zone heat treatment, aiming to solve the technical problems of low microstructure control accuracy and poor process consistency in the prior art during the heat treatment of dual-phase steel. An adaptive heat treatment temperature control curve is generated by obtaining the material properties and dimensions of the workpiece, and the heating, insulation and cooling processes are controlled in sections. The actual heat treatment data and microstructure change sequence are collected, and a microstructure change prediction model is generated in combination with a general prediction model. Through real-time predictive control and overall optimization, the technical effect of precise forming and performance stability of dual-phase steel workpieces in production is achieved.

[0012] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0013] It should be noted that any variations of the terms "include" and "have" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or inherent to these processes, methods, products or devices.

[0014] Embodiment 1, as Figure 1 As shown, the present application provides a dual-phase steel forming method based on intercritical heat treatment, the method comprising: Step S100: obtaining material properties and geometric dimensions of a workpiece to be processed, and determining a heat treatment temperature control curve based on the material properties and the geometric dimensions.

[0015] In the embodiment of the present application, the material properties and geometric dimensions of the workpiece to be processed are first obtained. The material properties are pre-determined by the workpiece manufacturer, including the chemical composition of the workpiece (such as carbon content, alloy elements, etc.), grain size, thermal conductivity, phase transition temperature, etc. The geometric dimensions, including the thickness, length, and width of the workpiece, are manually measured and the data is uploaded.

[0016] After obtaining the material properties and geometric dimensions of the workpiece, a temperature control curve for heat treatment is generated based on these data. Specifically, the key data points of material properties and geometric dimensions are searched in the database to find historical heat treatment curves similar to the characteristics of the workpiece to be processed. The closest historical data samples are screened by the first similarity threshold (geometric dimension similarity) and the second similarity threshold (heat treatment curve similarity). Based on the screened historical sample data, a new temperature control curve is generated by applying curve fitting technology.

[0017] Furthermore, in the method provided in the embodiment of the application, the material properties and geometric dimensions of the workpiece to be processed are obtained, and the heat treatment temperature control curve is determined based on the material properties and the geometric dimensions, and further includes: According to the material properties and the geometric dimensions, historical critical zone heat treatment data is retrieved, and a first retrieval sample is obtained in combination with a first similarity threshold, including multiple basic heat treatment temperature control curves, wherein the first similarity threshold is a geometric dimension threshold; through a second similarity threshold, a first extended retrieval is performed on the multiple basic heat treatment temperature control curves respectively to obtain a second retrieval sample, including multiple extended heat treatment temperature control curves, wherein the second similarity threshold is a curve similarity threshold; curve fitting is performed on the multiple basic heat treatment temperature control curves and the multiple extended heat treatment temperature control curves to obtain a heat treatment temperature control curve.

[0018] In an embodiment of the present application, a preliminary screening is first performed in the database based on the material properties and geometric dimensions of the workpiece to be processed. Specifically, the material properties of the workpiece are set as fixed conditions and input into the database retrieval system for screening. Through the multi-condition screening function of the database, only the historical heat treatment data with completely matched material properties are retained to ensure that the screened samples are consistent with the workpiece to be processed in terms of material performance. This process filters out a preliminary data set that meets the material property requirements. Based on the samples with consistent material properties, the samples closest to the workpiece to be processed are screened out according to the geometric dimensions. The geometric dimensions include key parameters such as the thickness, length and width of the workpiece, which determine the heat conduction efficiency and the uniformity of the temperature distribution. To this end, a geometric similarity calculation method is used, such as the Euclidean distance to calculate the geometric dimension similarity of the sample, and the difference in geometric dimensions between each sample and the workpiece to be processed is quantified. Samples with a similarity higher than the preset first similarity threshold are included in the first retrieval sample to form a set of basic heat treatment temperature control curves with the same material properties and similar geometric dimensions.

[0019] Next, an extended search is performed on the basic heat treatment temperature control curve in the first search sample to enrich the data set and obtain more curves with similar temperature change trends. Specifically, a basic heat treatment temperature control curve with the closest geometric dimensions to the workpiece to be processed is selected from the first search sample as the reference curve, and the similarity is compared with other curves. For this purpose, the dynamic time warping algorithm is used to calculate the similarity. The DTW algorithm records the temperature difference between the reference curve and the curve to be compared at each time point by constructing a distance matrix. The value of each matrix position represents the temperature difference between the two time points, thereby reflecting the matching degree at each time point. After the distance matrix is ​​constructed, the cumulative distance matrix is ​​calculated to find the optimal matching path. Each position in the cumulative distance matrix represents the minimum cumulative distance from the start of the sequence to the position. During the calculation process, the cumulative distance of each position is equal to the temperature difference value of the current position plus the minimum cumulative distance value in the adjacent position. The accumulation process starts from the upper left corner of the matrix and gradually accumulates to the lower right corner, thereby obtaining the minimum cumulative distance between the reference curve and the curve to be compared. The smaller the cumulative distance, the more similar the temperature change trends of the two curves are. After obtaining the minimum cumulative distance, it is compared with the preset second similarity threshold, i.e., the curve similarity threshold. If the minimum cumulative distance is less than the threshold, it is considered that the compared curve is similar to the reference curve in temperature change mode, and it is included in the second search sample to form a set of extended heat treatment temperature control curves.

[0020] After obtaining multiple basic heat treatment temperature control curves and extended heat treatment temperature control curves, curve fitting is performed to generate the final temperature control curve. The curve fitting adopts a segmented fitting method to fit the heating, insulation and cooling stages of the heat treatment process separately. Specifically, in each stage, the subtle differences of multiple curves are smoothed using polynomial fitting or spline interpolation methods to generate a comprehensive curve. In order to further ensure the continuity and smoothness of the fitting curve, methods such as moving average or Gaussian smoothing are applied to the fitting results to eliminate the mutation points of the curve, making it more stable in practical applications.

[0021] Finally, the heat treatment temperature control curve is obtained through piecewise fitting and smoothing.

[0022] Step S200: Segment the heat treatment temperature control curve to obtain a heating control curve, a heat preservation control curve and a cooling control curve, and configure the heating control area, the heat preservation control area and the cooling control area accordingly.

[0023] In the embodiment of the present application, the generated heat treatment temperature control curve is first analyzed in sections. The heat treatment temperature control curve is the temperature change trajectory of the entire process, including heating, constant temperature, and cooling stages. In order to accurately divide the control curve of each stage, the curve is analyzed to identify different trends in temperature change. The heating stage is characterized by a steady rise in temperature, the insulation stage is characterized by a stable and constant temperature, and the cooling stage is characterized by a rapid decrease in temperature.

[0024] The temperature control curve is segmented by segmentation technology. Specifically, an inflection point detection algorithm is used to identify the stage turning points of the curve. For example, the first-order derivative method is used to calculate the rate of change of temperature over time, so as to identify the critical points from heating to constant temperature and from constant temperature to cooling. After the inflection point detection, the temperature curve is divided into a heating control curve, a heat preservation control curve and a cooling control curve. The heating control curve represents the temperature change during the heating process, the heat preservation control curve represents the temperature change during the constant temperature period, and the cooling control curve represents the temperature drop during the cooling process. Then these three control curves are respectively configured to the corresponding areas of the heat treatment production line, namely the heating control area, the heat preservation control area and the cooling control area. The heating control area is responsible for heating the workpiece to the required critical zone temperature to ensure that the temperature can be uniformly and gradually increased to the target temperature. The heat preservation control area is responsible for maintaining a stable temperature during the specified constant temperature stage so that austenite can be uniformly formed in the workpiece. The cooling control area controls the rapid cooling of the workpiece, and uses a cooling medium (such as water or oil) to make the workpiece quickly pass the critical cooling rate to form an ideal microstructure.

[0025] Step S300: According to the configured heating control zone, the insulation control zone and the cooling control zone, the workpiece to be processed is processed in small batches, and temperature monitoring and microstructure change collection are performed simultaneously to obtain multiple actual heat treatment curves, multiple microstructure change sequences and multiple dual-phase steel workpieces.

[0026] In an embodiment of the present application, after the heating control area, the insulation control area and the cooling control area are configured, small batch processing of the workpiece to be processed is started. In the heating control area, the temperature data of the workpiece during the heating process is collected in real time, an actual heating curve is generated, and the change image of the microstructure is collected at the same time to form a heating microstructure change subsequence. When the workpiece enters the insulation control area, the temperature is continuously monitored, the actual insulation curve is recorded, and the microstructure change image of the insulation stage is synchronously collected to generate an insulation microstructure change subsequence. After the insulation is completed, the workpiece moves into the cooling control area, the temperature data of the cooling process is recorded, the actual cooling curve is generated, and the microstructure changes in the cooling stage are collected to form a cooling microstructure change subsequence. By summarizing the data of each stage, the actual heat treatment curve and the complete microstructure change sequence of the workpiece are obtained.

[0027] Through the above process, multiple actual heat treatment curves, multiple microstructure change sequences and multiple dual-phase steel workpieces are obtained.

[0028] Furthermore, in the method provided in the embodiment of the application, according to the configured heating control zone, the insulation control zone and the cooling control zone, the workpiece to be processed is processed in small batches, and temperature monitoring and microstructure change collection are performed simultaneously to obtain multiple actual heat treatment curves, multiple microstructure change sequences and multiple dual-phase steel workpieces, and also includes: For the first workpiece to be processed, when entering the heating control zone, the temperature data and microstructure images in the heating process are collected in real time and synchronously to generate a first actual heating curve and a first heating microstructure change subsequence; when entering the insulation control zone, the temperature data and microstructure images in the insulation process are collected in real time and synchronously to generate a first actual insulation curve and a first insulation microstructure change subsequence; when entering the cooling control zone, the temperature data and microstructure images in the cooling process are collected in real time and synchronously to generate a first actual cooling curve and a first cooling microstructure change subsequence to obtain a first dual-phase steel workpiece; the first actual heating curve, the first actual insulation curve and the first actual cooling curve are summarized to generate a first actual heat treatment curve; the first heating microstructure change subsequence, the first insulation microstructure change subsequence and the first cooling microstructure change subsequence are summarized to generate a first microstructure change sequence; the first dual-phase steel workpiece, the first actual heat treatment curve and the first microstructure change sequence are associated and stored, and added to multiple actual heat treatment curves, multiple microstructure change sequences and multiple dual-phase steel workpieces.

[0029] In an embodiment of the present application, during the heat treatment of the first workpiece to be processed, the workpiece sequentially enters the heating control zone, the insulation control zone and the cooling control zone, and a specific method is used to collect real-time data at each stage.

[0030] Specifically, the workpiece first enters the heating control area, and the non-contact temperature sensors distributed around the heating area, such as infrared temperature sensors, collect the changes in the surface temperature of the workpiece in real time. The first actual heating curve is generated through the collection to record the temperature change process of the workpiece during the heating stage. In addition, a high-resolution microscopic imaging device is used to observe the microscopic structure changes of the workpiece in real time. The microscopic system collects the tissue image of the workpiece at a preset position to form the first heating microscopic structure change subsequence, and records in detail the transformation of the microstructure of the workpiece during the heating process.

[0031] When the workpiece reaches the preset temperature, it enters the insulation control area. In this area, the temperature is kept at a constant value, and the temperature of the workpiece is continuously monitored in real time through a non-contact temperature sensor to ensure that the temperature is maintained within the set range during the insulation stage, and the first actual insulation curve is generated. At the same time, the microscopic imaging system continuously collects the microstructural changes of the workpiece under the insulation state, and records its organizational evolution under constant temperature conditions, including the uniform distribution of austenite. The collected image sequence forms the first insulation microstructural change subsequence.

[0032] After the insulation stage, the workpiece is transferred to the cooling control area, where it is rapidly cooled by a cooling medium such as water or oil. The non-contact temperature sensor monitors the temperature change of the workpiece surface in real time during the cooling process, generates the first actual cooling curve, and records the temperature drop of the workpiece during the cooling stage. At the same time, the microscopic imaging system continues to collect the changes in the microstructure, paying special attention to the phase transformation process from austenite to martensite, and generates the first cooling microstructure change subsequence.

[0033] After completing the three stages of heating, heat preservation and cooling, the temperature curve data of the workpiece at each stage are summarized to generate the first actual heat treatment curve, which fully records the temperature change of the workpiece during the entire heat treatment process. At the same time, the microstructure change subsequences of each stage are integrated to generate the first microstructure change sequence, which fully displays the transformation process of the microstructure of the workpiece during the entire heat treatment process.

[0034] Finally, the actual heat treatment curve and microstructure change sequence of the first dual-phase steel workpiece are associated and stored, and added to a data set of multiple actual heat treatment curves, multiple microstructure change sequences and multiple dual-phase steel workpieces in the database.

[0035] Step S400: Based on a plurality of actual heat treatment curves, a plurality of microstructure change sequences and a plurality of dual-phase steel workpieces, in combination with a general prediction model for microstructure change, a target microstructure change prediction model for the workpiece to be processed is generated.

[0036] In the embodiment of the present application, the universal prediction model of microstructure change is a basic model, which already contains the basic laws of microstructure change of common materials during heat treatment. This model is trained by a large amount of microstructure change data under different materials and process conditions, and can predict the microstructure transformation of materials at different temperatures and cooling rates, such as the transformation of austenite to martensite. In the process of applying this universal model, each actual heat treatment curve is first divided according to the sampling time point. For each time point t, the temperature sequence before time t is extracted as the input feature, and the microstructure feature at time t is extracted from the microstructure change sequence as the output label to construct a real-time prediction training sample.

[0037] Next, the constructed training samples are input into the general prediction model of microstructure change, and the time series characteristics of the temperature series are extracted using a recurrent neural network to establish the relationship between the temperature series and the microstructure characteristics. Through multiple rounds of iterative training, the model is gradually adjusted and the parameters are optimized to make it more consistent with the specific heat treatment characteristics of dual-phase steel and gradually adapt to the actual data of the workpiece to be processed.

[0038] Finally, a target microstructure change prediction model for the workpiece to be processed is obtained through the training and optimization of the general model.

[0039] Furthermore, in the method provided in the embodiment of the application, based on multiple actual heat treatment curves, multiple microstructure change sequences and multiple dual-phase steel workpieces, combined with a general prediction model for microstructure change, a target microstructure change prediction model for the workpiece to be processed is generated, and the method also includes: The first actual heat treatment curve is divided according to the sampling time points. For each sampling point t, the temperature sequence before time t is extracted from the actual heat treatment curve as input features, and the microstructure features at time t are extracted from the first microstructure change sequence as output labels to construct a real-time prediction training sample; the real-time prediction training sample is input into the general prediction model for microstructure change, the time series features of the temperature sequence are extracted through a recurrent neural network, and the corresponding relationship between the temperature sequence before time t and the microstructure features at time t is established; the general prediction model for microstructure change is iteratively trained to obtain a target microstructure change prediction model for the workpiece to be processed.

[0040] In an embodiment of the present application, the first actual heat treatment curve is first divided according to the sampling time points to obtain more detailed temperature change data. For each time point t, the temperature sequence before time t is extracted from the actual heat treatment curve as an input feature. At the same time, the microstructural features at time t are extracted from the first microstructural change sequence as the output label of the time point. The microstructural features describe the internal structural state of the workpiece at that moment, such as the distribution and proportion of austenite and ferrite. By recording the organizational state at a specific time point, the precise output label required for model training is formed. Through this segmentation and extraction method, a corresponding relationship between temperature and organizational state is established for each time point, and a real-time prediction training sample containing input features and output labels is constructed.

[0041] Next, the constructed real-time prediction training samples are input into the general prediction model of microstructure changes, which is based on the recurrent neural network architecture and can process time series data. RNN establishes the association between the temperature sequence before time t and the microstructure characteristics at time t by identifying the time series characteristics of the input temperature sequence. In each round of training, the RNN model is iteratively trained by the back propagation algorithm, the error between the current prediction result and the true output label (microstructure characteristics) is calculated, and the error is gradually propagated back to each layer of the network, and the weights and parameters are adjusted so that the model can more accurately predict microstructure changes. Through multiple rounds of iterative training, the model continuously adjusts its internal parameters and gradually optimizes its grasp of the relationship between the input characteristics (temperature sequence) and the output label (microstructure characteristics), making it more in line with the actual heat treatment data. After multiple iterations and optimization training, the general prediction model gradually adapts to the specific data of the workpiece to be processed, and finally generates the target microstructure change prediction model.

[0042] Step S500: mass-produce the workpieces to be processed, and use the target microstructure change prediction model to perform real-time prediction control and overall prediction optimization on the mass production process to perform dual-phase steel forming control.

[0043] In an embodiment of the present application, when the workpiece to be processed is mass-produced, real-time predictive control and overall predictive optimization of the production process are achieved through the target microstructure change prediction model to ensure the quality and stability of dual-phase steel forming. Real-time predictive control uses the prediction model to generate the microstructure state at the current moment based on the temperature data collected in real time, and compares it with the standard microstructure state. When the deviation exceeds the preset range, a temperature control adjustment instruction is generated and sent to the corresponding control area to correct the process deviation in time. In the overall predictive optimization, the standard heat treatment temperature control curve is updated and the final microstructure state of the workpiece is predicted according to the execution effect of the adjustment instruction. If the prediction result does not meet the preset indicators, the remaining process parameters are adjusted according to the current process stage, and the microstructure state is re-predicted until the prediction meets the requirements, and the updated temperature control curve is issued for execution.

[0044] Through the above control measures, dual-phase steel forming control is carried out.

[0045] Furthermore, in the method provided in the embodiment of the application, the workpiece to be processed is mass-produced, and the mass production process is real-time predicted and controlled and the overall predicted and optimized by the target microstructure change prediction model to perform dual-phase steel forming control, and further includes: Determine a standard heat treatment temperature control curve and a standard microstructure change sequence, wherein the standard microstructure change sequence includes a standard microstructure state at each moment; for a target workpiece to be processed in a mass production process, obtain real-time temperature data of the target workpiece to be processed in a heating control zone, a heat preservation control zone, and a cooling control zone to form a target real-time temperature curve of the target workpiece to be processed; input the target real-time temperature curve into the target microstructure change prediction model, predict the microstructure state of the target workpiece to be processed at the current moment in real time, and obtain real-time microstructure prediction data of the target workpiece to be processed; compare the real-time microstructure prediction data with the standard microstructure state at the current moment to calculate the microstructure state deviation; if the microstructure state deviation exceeds a preset deviation range, generate a temperature control adjustment instruction according to the microstructure state deviation, and send it to the corresponding control zone for execution to perform real-time prediction control.

[0046] In the embodiment of the present application, in the process of determining the standard heat treatment temperature control curve and the standard microstructure change sequence, a plurality of dual-phase steel workpieces are first screened, and qualified workpieces that meet the quality standards are selected based on the preset index requirements. Then, temperature data are extracted from a plurality of actual heat treatment curves of these qualified workpieces, and a standard heat treatment temperature control curve is generated by curve fitting. Next, the microstructure data of the qualified workpieces are extracted from the plurality of microstructure change sequences, and the tissue state at each moment is fitted to obtain a standard microstructure change sequence containing the standard microstructure state at each moment.

[0047] For the target workpieces to be processed in the mass production process, the temperature data of each target workpiece to be processed in the heating control area, the insulation control area and the cooling control area are obtained in real time to form a target real-time temperature curve. This temperature curve is input into the target microstructure change prediction model. The model predicts the microstructure state of the workpiece at this moment in real time based on the current temperature data and generates real-time microstructure prediction data.

[0048] After that, the real-time microstructure prediction data is compared with the standard microstructure state hour by hour, and the deviation between the real-time microstructure state and the standard state is obtained through data comparison and deviation calculation. Specifically, the deviation calculation uses the Euclidean distance to quantify the difference between the actual microstructure of the workpiece and the standard. When calculating, at each time point t, the real-time microstructure prediction data of the target workpiece to be processed is obtained through the prediction model, and at the same time, the standard microstructure state corresponding to the time point is extracted from the pre-generated standard microstructure change sequence. Next, the characteristic values ​​of the real-time microstructure prediction data and the standard microstructure state are organized into two vectors respectively. Each vector contains the numerical value of the microstructure feature at that time point, such as the proportion or distribution of each component phase. When calculating the deviation, the distance between the two vectors is calculated by the Euclidean distance formula. The calculated Euclidean distance is used as the deviation value at that time point. If the deviation exceeds the preset allowable range, the temperature control adjustment instruction is automatically generated by the control algorithm, which adjusts the heating temperature, holding time or cooling rate based on the size and nature of the deviation to adjust the process parameters to the appropriate range. The generated adjustment instructions are quickly sent to the corresponding heating, insulation or cooling control areas through the automatic control system to ensure that the temperature curve and microstructure state of the workpiece remain within the standard range.

[0049] After the adjustment command is issued, the temperature change of the workpiece is continuously monitored through the temperature sensor to check whether the adjusted temperature curve meets the expected standard. The effect of the adjustment is continuously evaluated through the feedback mechanism. If the deviation still exists, the parameters are further iterated and adjusted according to the feedback data until the real-time prediction data is consistent with the standard microstructure state. Through this real-time prediction control and feedback adjustment mechanism, the microstructure state of each workpiece is guaranteed to always meet the set standards in mass production, thereby achieving high-quality and consistent dual-phase steel forming control.

[0050] Furthermore, in the method provided in the embodiment of the application, a standard heat treatment temperature control curve and a standard microstructure change sequence are determined, wherein the standard microstructure change sequence includes the standard microstructure state at each moment, and further includes: The plurality of dual-phase steel workpieces are screened based on preset index requirements to obtain a plurality of qualified dual-phase steel workpieces that meet the preset index requirements; the actual heat treatment curves corresponding to the plurality of qualified dual-phase steel workpieces are extracted from a plurality of actual heat treatment curves to obtain a plurality of qualified actual heat treatment curves, and curve fitting is performed to generate a standard heat treatment temperature control curve; the microstructure change sequences corresponding to the plurality of qualified dual-phase steel workpieces are extracted from a plurality of microstructure change sequences to obtain a plurality of qualified microstructure change sequences, and the qualified microstructure states at each moment are fitted to generate a standard microstructure state at each moment to obtain a standard microstructure change sequence.

[0051] In the embodiment of the present application, a plurality of dual-phase steel workpieces are first screened based on preset index requirements. The preset index requirements include strength, toughness and wear resistance, etc. The performance of the workpiece is comprehensively evaluated through hardness testing, impact testing and tensile testing, etc., and the workpieces that meet all index requirements are screened out and marked as qualified dual-phase steel workpieces, thereby obtaining a plurality of qualified dual-phase steel workpieces.

[0052] Next, the actual heat treatment curve of each workpiece is extracted from the heat treatment data of multiple qualified dual-phase steel workpieces. These curves record the temperature changes of the workpiece in the three stages of heating, insulation and cooling, and reflect the specific temperature control and fluctuations in the process. By selecting the temperature curves corresponding to these qualified workpieces from the workpiece heat treatment database, a set of multiple actual heat treatment curves is formed.

[0053] After obtaining multiple actual heat treatment curves, these curves are fitted with polynomials to generate smooth temperature control curves. Fluctuations in the actual data are smoothed by minimizing the error between the data points and the fitted curve. The generated standard heat treatment temperature control curve represents the average temperature change process of all qualified workpieces and becomes the temperature benchmark in mass production.

[0054] At the same time, from multiple microstructure change sequences, the microstructure change sequences corresponding to multiple qualified dual-phase steel workpieces are extracted. The extracted multiple microstructure change sequences record the organizational state of each qualified workpiece at different time points, forming a data set of multiple qualified microstructure change sequences. Next, the data in these qualified microstructure change sequences are spline interpolated and fitted at each moment. At each time point, the microstructure state data of all qualified workpieces are spline interpolated to make the microstructure state at each time point smooth and continuous, and generate the standard microstructure state at that moment. Through the smoothing processing of spline interpolation, the microstructure state at each moment is more stable and suitable for generating a standard state sequence. Finally, the fitting data of all time points are integrated to form a standard microstructure change sequence.

[0055] Through the above process, the standard heat treatment temperature control curve and the standard microstructure change sequence are obtained.

[0056] Furthermore, the method provided in the application embodiment also includes: According to the execution result of the temperature control adjustment instruction, the standard heat treatment temperature control curve is updated to obtain the target heat treatment temperature control curve of the target workpiece to be processed; the target heat treatment temperature control curve is input into the target microstructure change prediction model to predict the final microstructure state of the target workpiece to be processed at the end of the entire heat treatment process; when the final microstructure state does not meet the preset index requirements, based on the current process stage, the temperature control parameters of the remaining process stages are adjusted; the microstructure prediction is re-performed according to the adjusted temperature control parameters, and when the prediction result meets the preset index requirements, an updated heat treatment temperature control curve is generated according to the adjusted temperature control parameters and sent to the corresponding control area for execution.

[0057] In the embodiment of the present application, firstly, according to the execution result of the temperature control adjustment instruction, the standard heat treatment temperature control curve is updated to obtain the target heat treatment temperature control curve of the current workpiece. Specifically, the temperature data after the execution of the adjustment instruction is collected in real time, and compared and analyzed with the standard heat treatment temperature control curve. Based on the difference results, the key parameters of the temperature curve (such as heating rate, holding time, cooling rate) are adjusted by the feedback control method to generate the target heat treatment temperature control curve of the target workpiece to be processed.

[0058] Afterwards, the updated target heat treatment temperature control curve is input into the target microstructure change prediction model to predict the final microstructure state of the current workpiece at the end of heat treatment.

[0059] If the final microstructure state predicted by the model does not meet the preset index requirements, that is, does not meet the preset quality index and microstructure requirements, the temperature control parameters of the remaining process stages are further adjusted. This process uses an adaptive control method to automatically optimize the remaining process parameters according to the current process state. For example, if the prediction shows that the organization is uneven during the insulation stage, the cooling rate is appropriately adjusted or the insulation time is extended during the cooling stage to compensate for the previous temperature deviation. After adjusting the process parameters, the new target heat treatment temperature control curve is input into the target microstructure change prediction model to re-predict the microstructure state. The model uses the adjusted temperature curve to re-evaluate the organizational state of the workpiece at the end of the heat treatment to ensure that the new temperature control curve can enable the workpiece to meet the final quality standards and microstructure requirements. Through this re-prediction process, it is verified whether all adjustments are effective, and the accuracy and consistency of the microstructure state are further ensured.

[0060] When the new prediction results show that the final microstructure state meets the preset standard, an updated heat treatment temperature control curve is generated based on the adjusted temperature control parameters. This curve is used as the final optimization curve and sent to the heating, insulation and cooling control areas on the production line for automatic execution. Through the automated execution system, each heat treatment stage is strictly operated according to the updated curve parameters to ensure that the temperature change of each workpiece is consistent with the optimized target parameters, thereby achieving the best organization and quality control effect.

[0061] In the embodiments of the present application, in summary, the embodiments of the present application have at least the following technical effects: The present application obtains the material properties and geometric dimensions of the workpiece to be processed, and determines the heat treatment temperature control curve based on the material properties and geometric dimensions; divides the heat treatment temperature control curve to obtain the heating control curve, the insulation control curve and the cooling control curve, and configures the heating control zone, the insulation control zone and the cooling control zone accordingly; according to the configured heating control zone, the insulation control zone and the cooling control zone, the workpiece to be processed is processed in small batches, and temperature monitoring and microstructure change collection are performed simultaneously to obtain multiple actual heat treatment curves, multiple microstructure change sequences and multiple dual-phase steel workpieces; based on the multiple actual heat treatment curves, multiple microstructure change sequences and multiple dual-phase steel workpieces, combined with the general prediction model for microstructure change, a target microstructure change prediction model for the workpiece to be processed is generated; the workpiece to be processed is mass-produced, and the mass production process is real-time predictive control and overall predictive optimization are performed through the target microstructure change prediction model to perform dual-phase steel forming control. The present invention solves the technical problems of low microstructure control accuracy and poor process consistency in the heat treatment process of dual-phase steel in the prior art. An adaptive heat treatment temperature control curve is generated by acquiring the material properties and dimensions of the workpiece, and the heating, insulation and cooling processes are controlled in sections. The actual heat treatment data and microstructure change sequence are collected, and a microstructure change prediction model is generated in combination with a general prediction model. Through real-time prediction control and overall optimization, the technical effect of precise forming and performance stability of dual-phase steel workpieces in production is achieved.

[0062] Embodiment 2 is based on the same inventive concept as the dual-phase steel forming method based on critical zone heat treatment in the above embodiment. Figure 2 As shown, the present application provides a dual-phase steel forming system based on critical zone heat treatment, and the system and method embodiments in the embodiments of the present application are based on the same inventive concept. The system includes: a temperature control curve determination module 11, the temperature control curve determination module 11 obtains the material properties and geometric dimensions of the workpiece to be processed, and determines the heat treatment temperature control curve based on the material properties and the geometric dimensions; a curve segmentation module 12, the curve segmentation module 12 segments the heat treatment temperature control curve, obtains the heating control curve, the insulation control curve and the cooling control curve, and configures the heating control area, the insulation control area and the cooling control area accordingly; a processing data acquisition module 13, the processing data acquisition module 13 performs small batch processing on the workpiece to be processed according to the configured heating control area, the insulation control area and the cooling control area. The invention relates to a process for controlling the temperature of the workpiece to be processed and collecting microstructure changes simultaneously, so as to obtain a plurality of actual heat treatment curves, a plurality of microstructure change sequences and a plurality of dual-phase steel workpieces; a prediction model generation module 14, which generates a target microstructure change prediction model of the workpiece to be processed based on the plurality of actual heat treatment curves, a plurality of microstructure change sequences and a plurality of dual-phase steel workpieces in combination with a general prediction model for microstructure changes; a forming control module 15, which performs mass production of the workpiece to be processed, performs real-time prediction control and overall prediction optimization of the mass production process through the target microstructure change prediction model, and performs dual-phase steel forming control.

[0063] Furthermore, the system is also used to implement the following functions: According to the material properties and the geometric dimensions, historical critical zone heat treatment data is retrieved, and a first retrieval sample is obtained in combination with a first similarity threshold, including multiple basic heat treatment temperature control curves, wherein the first similarity threshold is a geometric dimension threshold; through a second similarity threshold, a first extended retrieval is performed on the multiple basic heat treatment temperature control curves respectively to obtain a second retrieval sample, including multiple extended heat treatment temperature control curves, wherein the second similarity threshold is a curve similarity threshold; curve fitting is performed on the multiple basic heat treatment temperature control curves and the multiple extended heat treatment temperature control curves to obtain a heat treatment temperature control curve.

[0064] Furthermore, the system is also used to implement the following functions: For the first workpiece to be processed, when entering the heating control zone, the temperature data and microstructure images in the heating process are collected in real time and synchronously to generate a first actual heating curve and a first heating microstructure change subsequence; when entering the insulation control zone, the temperature data and microstructure images in the insulation process are collected in real time and synchronously to generate a first actual insulation curve and a first insulation microstructure change subsequence; when entering the cooling control zone, the temperature data and microstructure images in the cooling process are collected in real time and synchronously to generate a first actual cooling curve and a first cooling microstructure change subsequence to obtain a first dual-phase steel workpiece; the first actual heating curve, the first actual insulation curve and the first actual cooling curve are summarized to generate a first actual heat treatment curve; the first heating microstructure change subsequence, the first insulation microstructure change subsequence and the first cooling microstructure change subsequence are summarized to generate a first microstructure change sequence; the first dual-phase steel workpiece, the first actual heat treatment curve and the first microstructure change sequence are associated and stored, and added to multiple actual heat treatment curves, multiple microstructure change sequences and multiple dual-phase steel workpieces.

[0065] Furthermore, the system is also used to implement the following functions: The first actual heat treatment curve is divided according to the sampling time points. For each sampling point t, the temperature sequence before time t is extracted from the actual heat treatment curve as input features, and the microstructure features at time t are extracted from the first microstructure change sequence as output labels to construct a real-time prediction training sample; the real-time prediction training sample is input into the general prediction model for microstructure change, the time series features of the temperature sequence are extracted through a recurrent neural network, and the corresponding relationship between the temperature sequence before time t and the microstructure features at time t is established; the general prediction model for microstructure change is iteratively trained to obtain a target microstructure change prediction model for the workpiece to be processed.

[0066] Furthermore, the system is also used to implement the following functions: Determine a standard heat treatment temperature control curve and a standard microstructure change sequence, wherein the standard microstructure change sequence includes a standard microstructure state at each moment; for a target workpiece to be processed in a mass production process, obtain real-time temperature data of the target workpiece to be processed in a heating control zone, a heat preservation control zone, and a cooling control zone to form a target real-time temperature curve of the target workpiece to be processed; input the target real-time temperature curve into the target microstructure change prediction model, predict the microstructure state of the target workpiece to be processed at the current moment in real time, and obtain real-time microstructure prediction data of the target workpiece to be processed; compare the real-time microstructure prediction data with the standard microstructure state at the current moment to calculate the microstructure state deviation; if the microstructure state deviation exceeds a preset deviation range, generate a temperature control adjustment instruction according to the microstructure state deviation, and send it to the corresponding control zone for execution to perform real-time prediction control.

[0067] Furthermore, the system is also used to implement the following functions: According to the execution result of the temperature control adjustment instruction, the standard heat treatment temperature control curve is updated to obtain the target heat treatment temperature control curve of the target workpiece to be processed; the target heat treatment temperature control curve is input into the target microstructure change prediction model to predict the final microstructure state of the target workpiece to be processed at the end of the entire heat treatment process; when the final microstructure state does not meet the preset index requirements, based on the current process stage, the temperature control parameters of the remaining process stages are adjusted; the microstructure prediction is re-performed according to the adjusted temperature control parameters, and when the prediction result meets the preset index requirements, an updated heat treatment temperature control curve is generated according to the adjusted temperature control parameters and sent to the corresponding control area for execution.

[0068] Furthermore, the system is also used to implement the following functions: The plurality of dual-phase steel workpieces are screened based on preset index requirements to obtain a plurality of qualified dual-phase steel workpieces that meet the preset index requirements; the actual heat treatment curves corresponding to the plurality of qualified dual-phase steel workpieces are extracted from a plurality of actual heat treatment curves to obtain a plurality of qualified actual heat treatment curves, and curve fitting is performed to generate a standard heat treatment temperature control curve; the microstructure change sequences corresponding to the plurality of qualified dual-phase steel workpieces are extracted from a plurality of microstructure change sequences to obtain a plurality of qualified microstructure change sequences, and the qualified microstructure states at each moment are fitted to generate a standard microstructure state at each moment to obtain a standard microstructure change sequence.

[0069] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying drawings do not necessarily require the specific order and continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0070] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0071] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A dual-phase steel forming method based on intercritical heat treatment, characterized in that: The method is applied to a heat treatment production line, which includes a heating control area, a heat preservation control area and a temperature reduction control area. The method includes: Acquiring material properties and geometric dimensions of a workpiece to be processed, and determining a heat treatment temperature control curve based on the material properties and the geometric dimensions; Segmenting the heat treatment temperature control curve to obtain a heating control curve, a heat preservation control curve and a cooling control curve, and configuring the heating control area, the heat preservation control area and the cooling control area accordingly; According to the configured heating control zone, the heat preservation control zone and the temperature reduction control zone, the workpiece to be processed is processed in small batches, and temperature monitoring and microstructure change collection are performed simultaneously to obtain multiple actual heat treatment curves, multiple microstructure change sequences and multiple dual-phase steel workpieces; Based on multiple actual heat treatment curves, multiple microstructure change sequences and multiple dual-phase steel workpieces, combined with a general prediction model for microstructure change, a target microstructure change prediction model for the workpiece to be processed is generated; The workpieces to be processed are mass-produced, and real-time prediction control and overall prediction optimization are performed on the mass production process through the target microstructure change prediction model to perform dual-phase steel forming control.

2. The dual-phase steel forming method based on intercritical zone heat treatment according to claim 1, characterized in that: Acquiring material properties and geometric dimensions of a workpiece to be processed, and determining a heat treatment temperature control curve based on the material properties and the geometric dimensions, including: Retrieve historical critical zone heat treatment data according to the material properties and the geometric dimensions, and obtain a first retrieval sample in combination with a first similarity threshold, including a plurality of basic heat treatment temperature control curves, wherein the first similarity threshold is a geometric dimension threshold; Through a second similarity threshold, a first extended search is performed on a plurality of basic heat treatment temperature control curves respectively to obtain a second search sample, including a plurality of extended heat treatment temperature control curves, wherein the second similarity threshold is a curve similarity threshold; Curve fitting is performed on a plurality of basic heat treatment temperature control curves and a plurality of extended heat treatment temperature control curves to obtain a heat treatment temperature control curve.

3. The dual-phase steel forming method based on intercritical zone heat treatment according to claim 1, characterized in that: According to the configured heating control zone, the insulation control zone and the cooling control zone, the workpiece to be processed is processed in small batches, and temperature monitoring and microstructure change collection are performed simultaneously to obtain multiple actual heat treatment curves, multiple microstructure change sequences and multiple dual-phase steel workpieces, including: For the first workpiece to be processed, when entering the heating control zone, temperature data and microstructure images during the heating process are collected synchronously in real time to generate a first actual heating curve and a first heating microstructure change subsequence; When entering the insulation control area, temperature data and microstructure images during the insulation process are collected synchronously in real time to generate a first actual insulation curve and a first insulation microstructure change subsequence; When entering the cooling control zone, temperature data and microstructure images in the cooling process are collected in real time and synchronously, a first actual cooling curve and a first cooling microstructure change subsequence are generated, and a first dual-phase steel workpiece is obtained; Summarizing the first actual heating curve, the first actual heat preservation curve and the first actual cooling curve to generate a first actual heat treatment curve; Summarizing the first heating microstructure change subsequence, the first heat preservation microstructure change subsequence, and the first cooling microstructure change subsequence to generate a first microstructure change sequence; The first dual-phase steel workpiece, the first actual heat treatment curve and the first microstructure change sequence are stored in association and added to multiple actual heat treatment curves, multiple microstructure change sequences and multiple dual-phase steel workpieces.

4. The dual-phase steel forming method based on intercritical zone heat treatment according to claim 1, characterized in that: Based on multiple actual heat treatment curves, multiple microstructure change sequences and multiple dual-phase steel workpieces, combined with the general prediction model of microstructure change, a target microstructure change prediction model of the workpiece to be processed is generated, including: The first actual heat treatment curve is divided according to the sampling time points. For each sampling point t, the temperature sequence before the t time is extracted from the actual heat treatment curve as the input feature, and the microstructure feature at the t time is extracted from the first microstructure change sequence as the output label to construct a real-time prediction training sample; The real-time prediction training samples are input into the universal prediction model for microstructure changes, the time series features of the temperature sequence are extracted through a recurrent neural network, and the corresponding relationship between the temperature sequence before time t and the microstructure features at time t is established; The universal microstructure change prediction model is iteratively trained to obtain a target microstructure change prediction model for the workpiece to be processed.

5. The dual-phase steel forming method based on intercritical zone heat treatment according to claim 1, characterized in that: The workpieces to be processed are mass-produced, and real-time prediction control and overall prediction optimization are performed on the mass production process through the target microstructure change prediction model to perform dual-phase steel forming control, including: Determining a standard heat treatment temperature control curve and a standard microstructure change sequence, wherein the standard microstructure change sequence includes a standard microstructure state at each moment; For a target workpiece to be processed in a mass production process, real-time temperature data of the target workpiece to be processed in a heating control area, a heat preservation control area, and a cooling control area are obtained to form a target real-time temperature curve of the target workpiece to be processed; Inputting the target real-time temperature curve into the target microstructure change prediction model, predicting the microstructure state of the target workpiece to be processed at the current moment in real time, and obtaining real-time microstructure prediction data of the target workpiece to be processed; Compare the real-time microstructure prediction data with the standard microstructure state at the current moment to calculate the microstructure state deviation; If the microstructure state deviation exceeds the preset deviation range, a temperature control adjustment instruction is generated according to the microstructure state deviation and sent to the corresponding control area for execution to perform real-time predictive control.

6. The method for forming dual-phase steel with intercritical heat treatment according to claim 5, characterized in that: The method further comprises: According to the execution result of the temperature control adjustment instruction, the standard heat treatment temperature control curve is updated to obtain the target heat treatment temperature control curve of the target workpiece to be processed; Inputting the target heat treatment temperature control curve into the target microstructure change prediction model to predict the final microstructure state of the target workpiece to be processed at the end of the entire heat treatment process; When the final microstructure state does not meet the preset index requirements, the temperature control parameters of the remaining process stages are adjusted based on the current process stage; The microstructure prediction is performed again according to the adjusted temperature control parameters. When the prediction results meet the preset index requirements, an updated heat treatment temperature control curve is generated according to the adjusted temperature control parameters and sent to the corresponding control area for execution.

7. The dual-phase steel forming method based on intercritical heat treatment according to claim 5, characterized in that: Determine a standard heat treatment temperature control curve and a standard microstructure change sequence, wherein the standard microstructure change sequence includes a standard microstructure state at each moment, including: Screening the plurality of dual-phase steel workpieces based on preset index requirements to obtain a plurality of qualified dual-phase steel workpieces that meet the preset index requirements; Extracting actual heat treatment curves corresponding to the plurality of qualified dual-phase steel workpieces from the plurality of actual heat treatment curves, obtaining a plurality of qualified actual heat treatment curves and performing curve fitting to generate a standard heat treatment temperature control curve; From multiple microstructure change sequences, the microstructure change sequences corresponding to the multiple qualified dual-phase steel workpieces are extracted to obtain multiple qualified microstructure change sequences, and the qualified microstructure states at each moment are fitted to generate the standard microstructure states at each moment to obtain the standard microstructure change sequence.

8. Dual-phase steel forming system based on intercritical heat treatment, characterized in that: For implementing the dual-phase steel forming method based on intercritical zone heat treatment according to any one of claims 1 to 7, the system comprises: A temperature control curve determination module, wherein the temperature control curve determination module obtains material properties and geometric dimensions of a workpiece to be processed, and determines a heat treatment temperature control curve based on the material properties and the geometric dimensions; A curve segmentation module, wherein the curve segmentation module segments the heat treatment temperature control curve to obtain a heating control curve, a heat preservation control curve and a cooling control curve, and configures the heating control area, the heat preservation control area and the cooling control area accordingly; A processing data acquisition module, wherein the processing data acquisition module performs small batch processing on the workpiece to be processed according to the configured heating control zone, the insulation control zone and the cooling control zone, and simultaneously performs temperature monitoring and microstructure change acquisition to obtain multiple actual heat treatment curves, multiple microstructure change sequences and multiple dual-phase steel workpieces; A prediction model generation module, wherein the prediction model generation module generates a target microstructure change prediction model of the workpiece to be processed based on multiple actual heat treatment curves, multiple microstructure change sequences and multiple dual-phase steel workpieces in combination with a general microstructure change prediction model; A forming control module is provided, wherein the forming control module performs mass production of the workpiece to be processed, performs real-time prediction control and overall prediction optimization of the mass production process through the target microstructure change prediction model, and performs dual-phase steel forming control.

Images