Method for predicting mechanical properties of cold-rolled dual-phase steel automobile sheet and related device

Abstract

The application discloses a cold-rolled dual-phase steel automobile plate mechanical property prediction method and related equipment, and relates to the technical field of metal material processing. The method comprises the following steps: acquiring production data; inputting the production data and martensite volume fraction into a prediction model to predict the mechanical property of the cold-rolled dual-phase steel automobile plate, so as to obtain a performance prediction result, wherein the martensite volume fraction is calculated through a holding experiment; the prediction model is obtained through preset times of training based on historical production data and the martensite volume fraction; the historical production data comprises chemical composition, process specifications and mechanical property; the input variables of the prediction model are the chemical composition, the process specifications and the martensite volume fraction, and the output variable is the mechanical property. According to the application, the mechanical property of the cold-rolled dual-phase steel automobile plate can be accurately and efficiently predicted based on the microstructure characteristics and physical metallurgical rules of the cold-rolled dual-phase steel.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of metal material processing, and in particular to a cold-rolled dual-phase steel automobile sheet mechanical property prediction method and related equipment. BACKGROUND

[0002] Cold-rolled dual-phase steel is a material that combines high strength and excellent ductility, widely used in the automotive, shipbuilding and mechanical manufacturing industries. Its main organization is composed of ferrite and martensite, and the high strength of martensite and the high ductility of ferrite make dual-phase steel have excellent mechanical properties. In the manufacturing process, cold-rolled dual-phase steel is usually produced by cold rolling and continuous annealing process. However, this process involves many complex temperature and time parameters, and process adjustment and material optimization during production often involves high time and economic costs.

[0003] In order to effectively obtain dual-phase steel products with different mechanical properties, traditional production methods usually rely on a large number of experiments, especially hot rolling, pickling, cold rolling and continuous annealing simulation experiments to predict and adjust mechanical properties. These experiments are not only time-consuming and costly, especially when process parameters need to be adjusted, often requiring repeated experiments, resulting in significant economic and time burden. At present, there is still room for optimization for the rapid and efficient mechanical property prediction method for the organizational characteristics and physical metallurgical laws of cold-rolled dual-phase steel, and a more accurate and efficient prediction method is needed to meet the mechanical property evaluation needs under different process conditions. SUMMARY

[0004] A series of simplified concepts are introduced in the summary section, which will be further described in detail in the specific embodiment section. The summary section of the present application does not mean to attempt to limit the key features and necessary technical features of the claimed technical solution, nor does it attempt to determine the protection scope of the claimed technical solution.

[0005] In a first aspect, the present application provides a cold-rolled dual-phase steel automobile sheet mechanical property prediction method, comprising:

[0006] Obtaining production data;

[0007] The prediction model is obtained by training historical production data and the martensite volume fraction for a preset number of times, the historical production data including chemical composition, process specification, and mechanical property, the process specification including one or more of thickness, tapping temperature, finish rolling temperature, coiling temperature, annealing temperature, slow cooling temperature, fast cooling temperature, and strip speed, the mechanical property including one or more of yield strength, tensile strength, and elongation after fracture, input variables of the prediction model being the chemical composition, the process specification, and the martensite volume fraction, and output variables being the mechanical property.

[0008] In an implementable embodiment, the martensite volume fraction f m is expressed as:

[0009]

[0010] wherein f m is the martensite volume fraction; f a is the austenite volume fraction after annealing soaking; M s is the martensite transformation start temperature, in ℃; T f is the fast cooling temperature, in ℃.

[0011] In an implementable embodiment, the austenite volume fraction f a after annealing soaking is expressed as:

[0012]

[0013] f e = AT1+B

[0014]

[0015] wherein f e is the austenite equilibrium volume fraction; A, B, C, and D are fitting coefficients; E is a fitting index; T1 and T2 are soaking temperatures, the soaking temperatures being production line annealing soaking temperatures, wherein T1 is in ℃ and T2 is in K; t is a soaking time, the soaking time being a production line annealing soaking time, L is a length of an annealing soaking section, in meters, and S is a strip speed, in meters / second.

[0016] In an implementable embodiment, the fitting coefficients A, B, C, and D, and the specific obtaining steps of the fitting index E, include:

[0017] obtaining the martensite volume fraction, wherein the martensite volume fraction is obtained by optical microscope analysis and scanning electron microscope analysis on a water-quenched sample, the water-quenched sample is formed by water-quenching a holding sample, and the holding sample is determined by a holding experiment on the cold-rolled dual-phase steel cold hard plate under different holding temperatures and different holding times;

[0018] determining the austenite volume fraction and the austenite equilibrium volume fraction based on the martensite volume fraction, wherein the austenite equilibrium volume fraction is the martensite volume fraction under different holding temperatures after the holding time is greater than a preset holding time;

[0019] determining the fitting coefficients A and B based on the austenite volume fraction and the holding temperature T1;

[0020] determining the fitting index E and the fitting coefficients C and D based on the austenite equilibrium volume fraction, the holding time and the holding temperature T2.

[0021] In an implementable embodiment, the martensite transformation start temperature M s is expressed as:

[0022] M s = 520-320xC%-50xMn%-30xCr%-5xSi%

[0023] wherein C% is the carbon content in mass percentage, Mn% is the manganese content in mass percentage, Cr% is the chromium content in mass percentage, and Si% is the silicon content in mass percentage.

[0024] In an implementable embodiment, the holding temperature is greater than or equal to the start temperature of the transformation from pearlite to austenite and less than or equal to the end temperature of the transformation from ferrite to austenite, and the holding time is greater than or equal to a first preset time and less than or equal to a second preset time.

[0025] In an implementable embodiment, the method further comprises:

[0026] In the historical production data, the production data and the chemical composition of the cold-rolled dual-phase steel automobile plate used in the holding experiment, the maximum deviation of the content of each chemical element is as follows: the maximum deviation of the carbon content is 0.02%, the maximum deviation of the silicon content is 0.1%, the maximum deviation of the manganese content is 0.1%, the maximum deviation of the chromium content is 0.1%, and the maximum deviation of the aluminum content is 0.04%.

[0027] In a second aspect, the application provides a cold-rolled dual-phase steel automobile plate mechanical property prediction device, comprising:

[0028] a data acquisition unit configured to acquire production data;

[0029] The performance prediction unit is configured to input the production data and the martensite volume fraction into a prediction model to predict the mechanical properties of the cold-rolled dual-phase steel automobile sheet to obtain a performance prediction result, wherein the martensite volume fraction is calculated through a holding experiment; the prediction model is obtained by training historical production data and the martensite volume fraction for a preset number of times; the historical production data includes chemical composition, process specification and mechanical properties; the process specification includes one or more of thickness, tapping temperature, finish rolling temperature, coiling temperature, annealing temperature, slow cooling temperature, fast cooling temperature and strip speed; the mechanical properties include one or more of yield strength, tensile strength and elongation after fracture; the input variables of the prediction model are the chemical composition, the process specification and the martensite volume fraction, and the output variable is the mechanical property.

[0030] In a third aspect, an electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor is configured to implement the steps of the method for predicting the mechanical properties of the cold-rolled dual-phase steel automobile sheet according to any one of the first aspect when executing the computer program stored in the memory.

[0031] In a fourth aspect, the present application further provides a computer readable storage medium having a computer program stored thereon, wherein the computer program is executable by a processor to implement the method for predicting the mechanical properties of the cold-rolled dual-phase steel automobile sheet according to any one of the first aspect.

[0032] In summary, in the process of constructing the mechanical property prediction model of the cold-rolled dual-phase steel automobile sheet, the volume fraction of martensite is introduced as one of the key input features of the machine learning algorithm, considering its important influence on the mechanical properties. In order to more accurately calculate the volume fraction of martensite, the present application considers the influence of the volume fraction of austenite, because the dual-phase steel for automobiles usually undergoes intercritical annealing, and the volume fraction of austenite after annealing directly determines the maximum volume fraction of martensite transformation. Further, the present application establishes the relationship between the volume fraction of austenite and the annealing temperature and time, taking into account the equilibrium volume fraction of austenite (i.e. the maximum value of the volume fraction of austenite after long-time annealing at a given annealing temperature), which makes the calculation of the volume fraction of austenite at a specific annealing temperature and holding time and the volume fraction of martensite in the final cold-rolled dual-phase steel more accurate. In addition, the present application estimates the martensite transformation starting temperature through the chemical composition, thereby enhancing the correlation between the volume fraction of martensite and the chemical composition and improving the calculation accuracy. At the same time, the annealing time is determined by using the furnace zone length and the strip speed, ensuring the connection between the volume fraction of martensite and the actual production conditions, and further improving the calculation accuracy. In summary, by incorporating the relationship between the chemical composition, the annealing soaking temperature, the fast cooling temperature, the furnace zone speed and the volume fraction of martensite into the prediction model, the present application realizes the accurate prediction of the mechanical properties of the cold-rolled dual-phase steel automobile sheet. Through a series of heat treatment experiments at different temperatures and times, combined with the relationship between the equilibrium volume fraction of austenite and the holding temperature, the present application preliminarily fits some coefficients; and by analyzing the relationship between the volume fraction of austenite, the holding temperature and the holding time, all the coefficients and exponents are comprehensively fitted. This process is not only based on a small amount of experimental data, but also follows the physical metallurgical rules of the cold-rolled dual-phase steel product, so that the developed mechanical property prediction model can quickly and efficiently predict the mechanical properties of the cold-rolled dual-phase steel automobile sheet. BRIEF DESCRIPTION OF DRAWINGS

[0033] Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are for purposes of illustration only and are not to be construed as limiting the specification. Moreover, in the drawings, like reference numerals designate like parts throughout the several views, and in which:

[0034] Figure 1 A flow chart of a mechanical property prediction method of a cold-rolled dual-phase steel automobile sheet according to an embodiment of the present application is shown in FIG. 1.

[0035] Figure 2 A structure diagram of a mechanical property prediction device of a cold-rolled dual-phase steel automobile sheet according to an embodiment of the present application is shown in FIG. 2.

[0036] Figure 3A cold-rolled dual-phase steel automobile plate mechanical property prediction electronic device structure schematic diagram provided by an embodiment of the present application. DETAILED DESCRIPTION

[0037] The terms "first", "second", "third", "fourth" and the like in the description and claims of the present application and in the above-mentioned drawings (if any) are used to distinguish similar objects, and do not necessarily have to be used to describe a particular sequential or chronological order. It should be understood that the data thus used can be interchanged, where appropriate, so that the embodiments described herein can be carried out in sequences other than those illustrated or described herein. Furthermore, the terms "comprise" and "have" and any variations thereof, are intended to cover non-exclusive inclusion, for example, a process, method, system, product or apparatus that includes a list of steps or units as an element does not have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to such processes, methods, products or apparatuses. The technical solutions in the embodiments of the present application will be described in detail below with reference to the drawings of the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments.

[0038] Reference should be made to Figure 1 A cold-rolled dual-phase steel automobile plate mechanical property prediction method flowchart provided by an embodiment of the present application, specifically can include:

[0039] S110, obtaining production data;

[0040] Exemplarily, in the industrial production process, for the mechanical property prediction of the cold-rolled dual-phase steel automobile plate, the collection of the production data is an important basis for optimizing the production process, improving the product quality and predicting the mechanical property. The essence of the production data is the data prepared for production, which has not yet entered the actual production process, and these data are obtained by integrating historical production data, experimental measurement and theoretical modeling.

[0041] S120, inputting the above-mentioned production data and martensite volume fraction into a prediction model to predict the mechanical property of the cold-rolled dual-phase steel automobile plate to obtain a performance prediction result, wherein the martensite volume fraction is calculated through a holding experiment; and the prediction model is obtained by training the historical production data and the martensite volume fraction for a preset number of times;

[0042] The historical production data includes chemical composition, process specification and mechanical property;

[0043] The process specification includes one or more of thickness, tapping temperature, finishing temperature, coiling temperature, annealing temperature, slow cooling temperature, fast cooling temperature and strip speed;

[0044] The mechanical properties include one or more of yield strength, tensile strength, and elongation at break.

[0045] Exemplarily, the mechanical properties of the cold-rolled dual-phase steel are influenced by various factors, including chemical composition, process parameters, and theoretical experimental data. By inputting these production data (such as chemical composition, process specifications, and experimentally derived parameters) into the prediction model, the influence of different production conditions on the mechanical properties can be scientifically predicted. The principle of this process is to establish an efficient prediction model through machine learning techniques, which can comprehensively consider various input variables such as the proposed chemical composition, process parameters, and microstructure characteristics such as the volume fraction of martensite, to accurately predict the key mechanical properties of cold-rolled dual-phase steel, such as yield strength, tensile strength, and elongation at break. Through this method, the possible influence of the proposed production conditions on the performance of the steel can be simulated and evaluated before actual production, thereby providing data support and decision-making basis for process optimization, while significantly reducing the time cost and economic investment of actual experiments and adjustments.

[0046] The chemical composition data includes the main alloying elements in the steel plate, such as carbon, silicon, manganese, chromium, and aluminum, and the content of these elements directly affects the microstructure, martensite transformation starting temperature, stability of austenite, and ultimately the mechanical properties.

[0047] The process specification data includes the thickness of the cold-rolled steel plate, the tapping temperature, the finishing temperature, the coiling temperature, the annealing temperature, and other process parameters that determine the degree of deformation, grain structure, and cooling rate of the material, and ultimately affect its final mechanical properties.

[0048] The mechanical property data includes yield strength, tensile strength, and elongation at break, which are three important indicators of steel performance. Predicting these mechanical properties is crucial for optimizing the production process and improving product quality.

[0049] Exemplarily, the machine learning algorithm used in the present application can be any one of a random forest algorithm, an AdaBoost algorithm, or a gradient boosting decision tree algorithm. Random forest algorithm, AdaBoost algorithm, and gradient boosting decision tree algorithm all belong to ensemble learning algorithms, which is a very powerful paradigm in machine learning. By combining the predictions of multiple models, the overall prediction effect can be improved.

[0050] In some examples, the prediction model includes:

[0051] The input variables of the prediction model are the chemical composition, the process specifications, and the volume fraction of martensite, and the output variable is the mechanical property.

[0052] Exemplarily, in the process of predicting the mechanical properties of cold-rolled dual-phase steel automotive sheets, the main role of the prediction model is to predict the mechanical properties (such as yield strength, tensile strength, and elongation after fracture) of the final product by inputting different production parameters (such as chemical composition, process specifications, and martensite volume fraction). The input variables of the prediction model are chemical composition, process specifications, and martensite volume fraction, while the output variable is mechanical properties.

[0053] Chemical composition, process specifications, and martensite volume fraction are the key influencing factors of cold-rolled dual-phase steel, which play a core role in the formation of microstructure and the performance of mechanical properties. The role of each input variable in the model and its relationship with mechanical properties is as follows:

[0054] Chemical composition (C, Si, Mn, Cr, Al, etc.) directly determines the phase structure and crystal structure of cold-rolled dual-phase steel, and is the basis for affecting its mechanical properties. Different elements have a significant impact on the strength, plasticity, and hardness of steel. For example, carbon content has a direct impact on the hardness and strength of steel, while silicon and manganese affect the strength and ductility of steel, respectively. By taking chemical composition as input, the model can learn the influence of different alloying elements on steel performance and make predictions based on actual production conditions.

[0055] Process specifications are important parameters that affect the formation and final performance of cold-rolled dual-phase steel. Process parameters such as temperature, rolling speed, and cooling rate determine the microstructure and physical properties of cold-rolled steel sheets. For example, annealing temperature and cooling rate directly affect the degree of transformation from austenite to martensite, thereby affecting the final martensite volume fraction, which is a major determinant of the strength and ductility of cold-rolled dual-phase steel. By inputting these process parameters, the model can analyze how the process affects the microstructure of the finished product, and thus affect the mechanical properties.

[0056] Martensite is a high-strength phase in cold-rolled dual-phase steel, and the volume fraction of martensite determines the mechanical properties of steel. Generally, the higher the volume fraction of martensite, the greater the strength of the steel, but the ductility may decrease. The formation of martensite is influenced by factors such as annealing temperature and cooling rate. Therefore, the martensite volume fraction is a key input variable that provides microstructure information directly related to mechanical properties, which can help the model more accurately predict mechanical properties.

[0057] The output variable of the model is the mechanical properties, which usually includes yield strength, tensile strength, and elongation after fracture, which are the most common indicators of steel quality.

[0058] Yield strength (RP0.2) is the maximum stress a material can withstand before it permanently deforms during tensile testing, reflecting its resistance to deformation. Yield strength is closely related to the volume fraction of martensite, as martensite is a phase with higher hardness and lower deformability. Therefore, as the volume fraction of martensite increases, the yield strength typically increases. The model can predict the yield strength of cold-rolled dual-phase steel by inputting the volume fraction of martensite and relevant process parameters.

[0059] Tensile strength (TS) is the maximum stress a material can withstand during tensile testing, often closely related to the microstructure of the material, such as the proportion of martensite and ferrite. Tensile strength is not only affected by the volume fraction of martensite, but also closely related to the chemical composition of the steel sheet, process parameters such as temperature, cooling rate, etc. The model can accurately predict the tensile strength of cold-rolled dual-phase steel by analyzing the relationship between these input variables.

[0060] Elongation after fracture (A80) is the degree of extension of a material when it breaks during tensile testing, reflecting the ductility of the material. High elongation after fracture usually means that the material has good plasticity and toughness. The size of the elongation after fracture is affected by many factors, including chemical composition, microstructure and process conditions, etc. Lower volume fraction of martensite usually leads to higher elongation after fracture, because ferrite has higher plasticity. The prediction model needs to consider these factors comprehensively to give the prediction result of elongation after fracture.

[0061] Through the learning of historical data, the model can understand the relationship between input variables and mechanical properties. The training process usually involves a large amount of data set and optimization algorithm to ensure that the model can correctly fit these data. During the training process, the model will continuously adjust its internal parameters to reduce the prediction error, so that it can accurately predict the mechanical properties when facing new data.

[0062] In some examples, the above-mentioned volume fraction of martensite f m is expressed as:

[0063]

[0064] where f m is the volume fraction of martensite; f a is the volume fraction of austenite after annealing soaking; M s is the martensite transformation start temperature, unit: ℃; T f is the fast cooling temperature, unit: ℃.

[0065] By way of example, the annealing soaking process transforms the microstructure in the steel from ferrite or pearlite to austenite by heating. The austenite volume fraction determines the potential of the formation of the final martensite to some extent. Higher austenite volume fraction means more martensite can be formed in the subsequent cooling process, thus increasing the strength of the steel. a is a key control parameter in the annealing process of the steel.

[0066] The martensite transformation start temperature is an important material parameter, which directly determines the condition of austenite transforming into martensite. Higher carbon content or manganese content usually leads to lower martensite transformation start temperature. By understanding the M s temperature, the model estimates the change rule of the martensite volume fraction at different process temperatures.

[0067] The fast cooling temperature is the outlet temperature of the fast cooling section in the production line. Under the cooling condition of the fast cooling section, the austenite transforms into martensite. The fast cooling temperature directly affects the stability of the austenite and determines the final value of the martensite volume fraction in the cooling process. By adjusting the fast cooling temperature, the formation of the martensite phase can be optimized, thereby affecting the strength and other mechanical properties of the steel.

[0068] In some examples, the austenite volume fraction f a is expressed as:

[0069]

[0070] f e = AT1+B

[0071]

[0072] wherein f e is the equilibrium austenite volume fraction; A, B, C and D are fitting coefficients; E is a fitting index; T1 and T2 are the soaking temperatures, the soaking temperatures are the annealing soaking temperatures in the production line, wherein T1 is in unit of ℃ and T2 is in unit of K; t is the soaking time, the soaking time is the annealing soaking time in the production line, L is the length of the annealing soaking section in unit of meter, and S is the strip speed in unit of meter / second.

[0073] For example, this is the volume fraction of austenite that reaches equilibrium in the material after annealing for a long enough time at a specific temperature condition. By linearly relating the annealing temperature to the volume fraction of austenite, the maximum possible content of austenite at different temperatures can be predicted. The exponential term in the formula describes the tendency of the volume fraction of austenite to increase with holding time. This simulates the gradual increase of austenite at different times and temperatures, where the fitting exponent E, fitting coefficients A, B, C, and D are obtained based on experimental data to adjust the fitting effect of the formula to make it more consistent with the actual situation. Holding temperature and holding time play a key role in the evolution of the microstructure of the material, so the sensitivity of this model to temperature is expressed using an exponential relationship to ensure the accuracy of the prediction of the volume fraction of austenite. By calculating the actual holding time of the steel plate during annealing through the holding time, the physical parameters of the furnace area are closely combined with the process conditions to ensure that this model can be applied in actual production and provide accurate results.

[0074] In some examples, the above martensite transformation start temperature M s is expressed as:

[0075] M s = 520 - 302% - 50% Mn - 30% Cr - 5% Si

[0076] where C% is the carbon content in mass percent; Mn% is the manganese content in mass percent; Cr% is the chromium content in mass percent; and Si% is the silicon content in mass percent.

[0077] For example, carbon is the main element affecting the martensite transformation, and a higher carbon content will generally lower M s temperature, because carbon increases the lattice stress in austenite, making it more stable, so a lower temperature is needed to start the transformation into martensite. Manganese is a common alloying element, often used to increase the hardenability of steel and increase strength, and during the martensite transformation, manganese will lower M s temperature, because manganese can stabilize the austenite phase. Chromium also helps to stabilize austenite, thereby lowering M s temperature, and the presence of chromium will reduce the formation rate of martensite, increasing the hardness and corrosion resistance of the material. Silicon in steel usually plays a role in strengthening ferrite and has some effect on the martensite transformation, and the presence of silicon will slightly lower M s temperature, making it easier for the material to form martensite at lower temperatures.

[0078] In some examples, the above holding temperature is greater than or equal to the start temperature A c1 of the transformation of pearlite to austenite and less than or equal to the end temperature A c3The holding time is greater than or equal to a first preset time and less than or equal to a second preset time. The first preset time is 5 seconds, and the second preset time is 18000 seconds.

[0079] The temperature interval ensures that the material is annealed in the two-phase region, which can optimize the mechanical properties of the dual-phase steel. The start temperature of the pearlite to austenite transformation is the lowest temperature at which the pearlite begins to transform into austenite when the material is heated to a certain temperature. Above this temperature, the pearlite decomposes into austenite, thereby improving the ductility and strength of the material. The end temperature of the complete transformation of ferrite to austenite is the temperature at which the ferrite in the material completely transforms into austenite, thereby making it easier for the material to form martensite phase during subsequent cooling, thereby improving its strength.

[0080] The holding time must be greater than or equal to a first preset time (5 seconds) and less than or equal to a second preset time (18000 seconds). This time interval ensures that the material has enough time to undergo phase transformation during annealing, without causing grain growth and microstructure coarsening due to long holding time. The first preset time is the minimum holding time to ensure that the phase transformation process is initiated. In a holding time of more than 5 seconds, the pearlite and ferrite in the material have enough time to begin to transform into austenite. The second preset time is an upper limit time to prevent the material from growing in grain size and microstructure coarsening under long time high temperature holding. Prolonged holding time can lead to deterioration of material properties, so 18000 seconds is set as the upper limit of time.

[0081] In some examples, the maximum deviation of each chemical element in the above chemical composition includes:

[0082] The maximum deviation of each chemical element content in the chemical composition of the historical production data, the proposed production data and the cold rolled dual-phase steel automobile sheet used in the holding experiment is as follows: the maximum deviation of carbon content is 0.02%, the maximum deviation of silicon content is 0.1%, the maximum deviation of manganese content is 0.1%, the maximum deviation of chromium content is 0.1%, and the maximum deviation of aluminum content is 0.04%.

[0083] For example, the chemical composition plays a decisive role in the microstructure and phase transformation behavior of the steel, thereby affecting its mechanical properties. To ensure the prediction accuracy and applicability of the experimental fitting model (such as the relationship between austenite volume fraction, holding time and temperature), the chemical composition used in the historical production data, the proposed production data and the experiment must be consistent. If the composition fluctuation exceeds the allowed deviation range, it may cause the material performance rule to deviate, affecting the accuracy of the model. Therefore, the maximum deviation of each element (such as carbon 0.02%, silicon 0.1%, etc.) is an important basis for maintaining the consistency of the composition and ensuring the applicability of the model to actual production.

[0084] Exemplarily, by limiting the chemical composition history data of the cold-rolled dual-phase steel automobile sheet, the chemical composition of the cold-rolled dual-phase steel hard sheet and the chemical composition of the cold-rolled dual-phase steel automobile sheet to be produced, the maximum fluctuation range of each component is determined. The physical metallurgical law represented by the fitting relationship between the austenite volume fraction, the holding temperature and the holding time obtained in the holding experiment of the cold-rolled dual-phase steel hard sheet at different temperatures and for different time is applicable to the cold-rolled dual-phase steel automobile sheet in the component process history data and the actual production process.

[0085] Carbon affects the strength and hardness of the cold-rolled dual-phase steel. A moderate increase in carbon can increase the hardness, but an excessive amount can cause a decrease in ductility. Limiting the deviation of the carbon content within 0.02% can ensure the stability and consistency of the mechanical properties. Silicon strengthens the ferrite, which improves the hardness and strength of the material, but too much can affect the ductility. Controlling the silicon deviation within 0.1% can balance the hardness and ductility. Manganese improves the hardenability and strength. Controlling the deviation of manganese within 0.1% can stabilize the hardenability and ensure the mechanical properties. Chromium improves the corrosion resistance and hardness. Limiting the deviation of chromium within 0.1% can avoid the fluctuation of the strength and ensure the consistency of the performance. Aluminum, as a deoxidizer, affects the purity and grain refinement. Controlling the deviation of aluminum within 0.04% can maintain the structural uniformity and the stability of the mechanical properties.

[0086] The technical solutions of the present application are further described in detail below through specific embodiments.

[0087] In this embodiment, the mechanical property prediction model is established by using the hard sheet holding experiment of the cold-rolled dual-phase steel automobile sheet with the grade HC700 / 980DP and the chemical composition, the component process specification parameter and the mechanical property parameter history data of the cold-rolled dual-phase steel automobile sheet.

[0088] The chemical composition of the cold-rolled dual-phase steel automobile sheet hard sheet of HC700 / 980DP is as follows: C is 0.1%, Si is 0.3%, Mn is 2.4%, Cr is 0.4%, Al is 0.04%, and the balance is Fe and unavoidable impurities. The A c1 and A c3 are about 730℃ and 850℃, respectively. The cold-rolled dual-phase steel hard sheet is held at 730-850℃ for 5 seconds to 18000 seconds, respectively, and then water quenched. The water quenched sample is analyzed by optical microscope and scanning electron microscope to detect the volume fraction of martensite, and the experimental results are shown in Table 1.

[0089] Table 1 Holding experiment conditions and detected volume fraction of martensite

[0090] Serial number Incubation temperature / °C Incubation time / s Volume fraction of martensite Serial number Incubation temperature / °C Incubation time / s Volume fraction of martensite 1 730 300 0.06 20 790 4800 0.632 2 730 600 0.097 21 790 15000 0.633 3 730 900 0.129 22 820 18 0.165 4 730 1200 0.166 23 820 20 0.281 5 730 1500 0.225 24 820 40 0.419 6 730 9600 0.267 25 820 70 0.525 7 730 18000 0.262 26 820 170 0.626 8 760 60 0.075 27 820 240 0.79 9 760 110 0.128 28 820 480 0.812 10 760 230 0.166 29 820 12000 0.807 11 760 480 0.219 30 850 5 0.159 12 760 600 0.293 31 850 12 0.477 13 760 5400 0.421 32 850 20 0.821 14 760 16000 0.432 33 850 45 1.012 15 790 50 0.181 34 850 120 1.012 16 790 100 0.255 35 850 220 1.002 17 790 220 0.335 36 850 340 1.013 18 790 400 0.462 37 850 12000 1.004 19 790 520 0.526

[0091] The martensite volume fraction tends to stabilize after a holding time greater than 12000 s. The martensite volume fraction of water-quenched samples after a holding time greater than 12000 s at different holding temperatures is selected as the austenite equilibrium volume fraction f. e ; through the equilibrium volume fraction of austenite f e The relationship between the temperature and the insulation temperature T1 was fitted, and the fitted relationship is as follows:

[0092] f e =AT1+B

[0093] The experimental results in Table 1 were fitted, and the fitting results were: fitting coefficient A = 0.006; fitting coefficient B = -4.08.

[0094] The martensite volume fraction of water-quenched samples after holding at different temperatures and times was taken as the austenite volume fraction f at the corresponding holding temperature and time. a ; for austenite volume fraction f a The relationship between the insulation temperature T1, the insulation temperature T2, and the insulation time t is fitted, and the fitted relationship is:

[0095]

[0096] Wherein, the insulation temperature T1 and the insulation temperature T2 are the same temperature, T1 is in °C and T2 is in K; the insulation time t is in s.

[0097] The fitting results were obtained based on the experimental results in Table 1. The fitting coefficients were: C = 715.8; D = -9993.5; and E = 0.8.

[0098] Historical data on the chemical composition, process specifications, and mechanical properties of cold-rolled duplex steel automotive sheets were obtained, totaling 3100 samples. Data from 10 of these samples are shown in Tables 2 and 3.

[0099] Table 2 Historical Data on Chemical Components (Mass Percentage)

[0100] Serial number C Si Mn Cr Al 1 0.09 0.3 2.4 0.4 0.035 2 0.095 0.32 2.38 0.41 0.034 3 0.092 0.33 2.41 0.35 0.36 4 0.094 0.29 2.39 0.42 0.035 5 0.093 0.28 2.38 0.41 0.038 6 0.085 0.35 2.45 0.45 0.055 7 0.087 0.34 2.43 0.45 0.055 8 0.105 0.25 2.35 0.35 0.015 9 0.1 0.28 2.36 0.38 0.02 10 0.098 0.28 2.42 0.41 0.037

[0101] Table 3 Historical data on process specifications and mechanical properties

[0102]

[0103] The martensitic phase transformation initiation temperature M of the 10 sample data were calculated based on the historical chemical composition data in Table 2. s As shown in Table 4.

[0104] Table 4 shows the martensitic phase transformation initiation temperature M calculated from historical data. s

[0105] Serial number M s / ℃]] Serial number M s / ℃]] 1 357.7 6 355.05 2 356.7 7 355.46 3 357.91 8 357.15 4 356.37 9 357.2 5 357.54 10 353.94

[0106] According to the process specification history data in Table 3 and the holding experiment results of the cold-rolled dual-phase steel cold hard plate at different holding temperatures and different holding times, the fitting coefficients A, B, C, D and the fitting index E are obtained, and based on the length of the annealing soaking furnace area of 180 m, the history data austenite volume fraction f after annealing soaking is calculated a and the martensite volume fraction f of the cold-rolled dual-phase steel automobile plate m , as shown in Table 5.

[0107] Table 5 Austenite volume fraction after annealing soaking and martensite volume fraction of cold-rolled dual-phase steel automobile plate

[0108] Serial number f a ]]> f m ]]> Serial number f a ]]> f m ]]> 1 0.422 0.372 6 0.456 0.396 2 0.429 0.375 7 0.486 0.423 3 0.469 0.409 8 0.594 0.522 4 0.465 0.404 9 0.589 0.518 5 0.472 0.411 10 0.585 0.512

[0109] The mechanical property history data of the cold-rolled dual-phase steel automobile plate, including yield strength, tensile strength and elongation after fracture, are taken as output variables, the process specification parameter history data, including thickness, discharge temperature, finish rolling temperature, coiling temperature, annealing temperature, slow cooling temperature, fast cooling temperature, strip speed and the calculated martensite volume fraction of the cold-rolled dual-phase steel automobile plate, are taken as input variables, and the mechanical property prediction model of the cold-rolled dual-phase steel automobile plate is established by using the random forest algorithm, the AdaBoost algorithm and the gradient boosting decision tree algorithm respectively.

[0110] The chemical composition and the adjusted process specification data of the cold-rolled dual-phase steel automobile plate to be produced are obtained, at this time the holding temperature is changed to the annealing soaking temperature in the annealing process, the input parameters are substituted into the above formula, and the martensite transformation start temperature, the austenite volume fraction after annealing soaking and the martensite volume fraction of the cold-rolled dual-phase steel automobile plate to be produced are calculated, wherein the martensite transformation start temperature M s of the cold-rolled dual-phase steel automobile plate to be produced is 355.92℃, the austenite volume fraction f a after annealing soaking is 0.78 and the martensite volume fraction f m is 0.61.

[0111] In the chemical composition of the cold-rolled dual-phase steel automobile plate to be produced, the mass percentages are as follows: C is 0.09%, Si is 0.3%, Mn is 2.4%, Cr is 0.4%, Al is 0.035%, and the balance is Fe and unavoidable impurities; in the adjusted process specification of the cold-rolled dual-phase steel automobile plate to be produced, the thickness is 1.0 mm, the discharge temperature is 1254℃, the finish rolling temperature is 890℃, the coiling temperature is 560℃, the annealing temperature is 820℃, the slow cooling temperature is 710℃, the fast cooling temperature is 280℃, and the strip speed is 130 meters per minute.

[0112] The chemical composition of the cold-rolled dual-phase steel automobile sheet to be produced, the adjusted process specification parameters and the calculated volume fraction of martensite of the cold-rolled dual-phase steel automobile sheet are input into the established mechanical property prediction model of the cold-rolled dual-phase steel automobile sheet, and the predicted yield strength, tensile strength and elongation at break of the cold-rolled dual-phase steel automobile sheet are shown in Table 6.

[0113] Table 6 Mechanical properties of the cold-rolled dual-phase steel automobile sheet predicted

[0114] Model algorithm Yield strength RP0.2 (MPa) Tensile strength (MPa) Elongation after fracture A80 (%) Random forest 843 1063 12 AdaBoost 825 1088 13 Gradient boosting decision tree 828 1079 12

[0115] The chemical composition of the cold-rolled dual-phase steel automobile sheet to be produced, the adjusted process specification parameters and the calculated volume fraction of martensite of the cold-rolled dual-phase steel automobile sheet are input into the established mechanical property prediction model of the cold-rolled dual-phase steel automobile sheet, and the predicted yield strength, tensile strength and elongation at break of the cold-rolled dual-phase steel automobile sheet are shown in Table 6.

[0116] Table 7 Mechanical properties of the cold-rolled dual-phase steel automobile sheet produced

[0117] Yield strength RP0.2 (MPa) Tensile strength (MPa) Elongation after fracture A80 (%) 876 1030 11.5

[0118] According to the results in Table 6 and Table 7, it can be seen that, by using the three algorithms of random forest, AdaBoost and gradient boosting decision tree, the mechanical properties under different process conditions can be quickly predicted under the condition of fully considering the organizational characteristics and physical metallurgical rules of the cold-rolled dual-phase steel for automobiles. The error of each mechanical property index (such as yield strength, tensile strength and elongation at break) in the prediction result compared with the actual measured value is small, indicating that the mechanical property prediction method proposed in the present application has high precision and efficiency. This result verifies the practicability and reliability of the prediction model in the production process optimization and performance evaluation of the cold-rolled dual-phase steel.

[0119] Please refer to Figure 2 A cold-rolled dual-phase steel automobile sheet mechanical property prediction device structure schematic diagram is provided for the embodiment of the present application, which comprises:

[0120] The data acquisition unit 21 is configured to acquire the to-be-produced data.

[0121] The performance prediction unit 22 is configured to input the production data and the martensite volume fraction into a prediction model to predict the mechanical properties of the cold-rolled dual-phase steel automobile sheet, and obtain a performance prediction result, wherein the martensite volume fraction is calculated through a holding experiment; the prediction model is obtained by training historical production data and the martensite volume fraction for a preset number of times; the historical production data includes chemical composition, process specification and mechanical properties; the process specification includes one or more of thickness, tapping temperature, finish rolling temperature, coiling temperature, annealing temperature, slow cooling temperature, fast cooling temperature and strip speed; the mechanical properties include one or more of yield strength, tensile strength and elongation at break; the input variables of the prediction model are the chemical composition, the process specification and the martensite volume fraction, and the output variable is the mechanical properties.

[0122] Referring to Figure 3 The embodiment further provides an electronic device 300, which comprises a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and capable of running on the processor, and the processor 320 implements the steps of any method for predicting the mechanical properties of a cold-rolled dual-phase steel automobile sheet.

[0123] Since the electronic device described in the embodiment is a device used to implement the device for predicting the mechanical properties of a cold-rolled dual-phase steel automobile sheet, based on the method described in the embodiment, those skilled in the art can understand the specific implementation of the electronic device and its various forms, so the implementation of the electronic device in the method of the embodiment will not be described in detail, as long as the device used to implement the method of the embodiment belongs to the scope of the present application.

[0124] In the implementation process, the computer program 311 can implement any embodiment of the first aspect when executed by the processor.

[0125] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0126] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system or a computer program product. Therefore, the present application can be in the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, the present application can be in the form of a computer program product implemented on one or more computer readable storage media containing computer readable program code (including but not limited to disk memory, CD-ROM, optical memory, etc.).

[0127] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 means for functionally implementing the steps listed in the flowchart block or blocks.

[0128] These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 means for functionally implementing the steps listed in the flowchart block or blocks.

[0129] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 means for functionally implementing the steps listed in the flowchart block or blocks.

[0130] The embodiments of the present application also provide a computer program product, which includes computer software instructions, when the computer software instructions are run on a processing device, causes the processing device to execute the steps of Figure 1 The flow of a mechanical property prediction method of a cold-rolled dual-phase steel automobile plate in a corresponding embodiment.

[0131] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the processes or functions according to the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center through wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that the computer can store or be integrated into a data storage device such as a server, data center, etc. containing one or more available media. The available media can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid state disk (SSD)), etc.

[0132] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

[0133] In several embodiments provided in the present application, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the apparatus embodiments described above are only schematic. The division of the units is only a logical function division. In actual implementation, additional division can be made, for example, a plurality of units or components can be combined or integrated into another system, or some features can be omitted or not executed. In addition, the coupling or direct coupling or communication connection between the units or components shown or discussed can be indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0134] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or they can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiments.

[0135] In addition, each of the function units in each of the embodiments of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software function unit.

[0136] When the integrated unit is realized in the form of a software function unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application, essentially or in other words, the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes several instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods in each of the embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0137] The above embodiments are only used to illustrate the technical solutions of the present application, but not limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

[0138] Although the preferred embodiments of the present application have been described, those skilled in the art can make additional changes and modifications to the embodiments once they know the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0139] Obviously, those skilled in the art can make various modifications and changes to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and changes of the present application fall within the scope of the claims of the present application and their equivalents, the present application also intends to include these modifications and changes.

Claims

1. A method for predicting mechanical properties of a cold rolled dual phase steel automotive sheet, characterized in that, The method comprises the following steps: obtaining production data, the production data comprising chemical composition and process specification of the cold rolled dual-phase steel automobile plate; inputting the production data and the martensite volume fraction into a prediction model to predict the mechanical properties of the cold rolled dual-phase steel automobile plate, to obtain a performance prediction result, wherein the martensite volume fraction is calculated through a holding experiment; the martensite volume fraction is expressed as: wherein, is the martensite volume fraction; is the austenite volume fraction after annealing soaking; is the martensite transformation start temperature, in ; is the fast cooling temperature, in ; the volume fraction of austenite after the annealing soaking is represented by: wherein, is the austenite equilibrium volume fraction; , , and are fitting coefficients; is the fitting exponent; and is the soaking temperature, which is the production line annealing soaking temperature, wherein, is in , is in ; is the soaking time, which is the production line annealing soaking time, is the annealing soaking zone length in meters, is the strip speed in meters per second; The martensitic transformation start temperature is represented as: wherein, is the carbon content in mass percent; is the manganese content in mass percent; is the chromium content in mass percent; is the silicon content in mass percent; the fitting coefficients , , and , the specific acquisition steps of the fitting index , include: obtaining the martensite volume fraction, wherein the martensite volume fraction is obtained by optical microscope analysis and scanning electron microscope analysis on a water-quenched sample, the water-quenched sample being formed by water-quenching a holding sample, and the holding sample being determined by a holding experiment on the cold rolled dual-phase steel cold hard plate under different holding temperatures and different holding times; determining the austenite volume fraction and the austenite equilibrium volume fraction based on the martensite volume fraction, wherein the austenite equilibrium volume fraction is the martensite volume fraction under different holding temperatures when the holding time is greater than a preset holding time; based on the austenite volume fraction and the soaking temperature , determining fitting coefficients and ; based on the austenite equilibrium volume fraction, soaking time and soaking temperature , determining a fitting index , a fitting coefficient and ; the prediction model is obtained by training the historical production data and the martensite volume fraction for a preset number of times; the historical production data comprises chemical composition, process specification and mechanical properties; the process specification comprises one or more of thickness, tapping temperature, finishing temperature, coiling temperature, annealing temperature, slow cooling temperature, fast cooling temperature and strip speed; the mechanical properties comprise one or more of yield strength, tensile strength and elongation after fracture; the input variables of the prediction model are the chemical composition, the process specification and the martensite volume fraction, and the output variable is the mechanical properties.

2. The method of predicting mechanical properties of cold rolled dual phase steel automotive sheet as claimed in claim 1 wherein, The holding temperature is greater than or equal to the start temperature of the transformation of pearlite to austenite and less than or equal to the end temperature of the transformation of all ferrite to austenite; the holding time is greater than or equal to a first preset time and less than or equal to a second preset time.

3. The method of predicting mechanical properties of cold rolled dual phase steel automotive sheet as claimed in claim 1 wherein, Further comprising: the maximum deviation of the content of each chemical element in the chemical composition of the cold rolled dual-phase steel automobile plate used in the historical production data, the production data and the holding experiment is 0.02% for carbon content, 0.1% for silicon content, 0.1% for manganese content, 0.1% for chromium content and 0.04% for aluminum content.

4. A device for predicting mechanical properties of a cold rolled dual phase steel automotive sheet, characterized in that, The method comprises the following steps: a data acquisition unit is configured to obtain production data, the production data comprising chemical composition and process specification of the cold rolled dual-phase steel automobile plate; a performance prediction unit is configured to input the production data and the martensite volume fraction into a prediction model to predict the mechanical properties of the cold rolled dual-phase steel automobile plate, to obtain a performance prediction result, wherein the martensite volume fraction is calculated through a holding experiment; the martensite volume fraction is represented as: in, This represents the volume fraction of martensite. The volume fraction of austenite after homogenization during annealing; The martensitic phase transformation initiation temperature, in units of ; This is the rapid cooling temperature, in units of... ; the volume fraction of austenite after the annealing soaking is represented by: wherein, is the austenite equilibrium volume fraction; , , and are fitting coefficients; is the fitting exponent; and is the soaking temperature, which is the production line annealing soaking temperature, wherein, is in meters per second; , is in meters per second; ; is the soaking time, which is the production line annealing soaking time, is the annealing soaking zone furnace length in meters, is the strip speed in meters per second; The martensitic transformation start temperature is represented as: wherein, is the carbon content in mass percent; is the manganese content in mass percent; is the chromium content in mass percent; is the silicon content in mass percent; the fitting coefficients , , and , the specific acquisition steps of the fitting index , include: obtaining the martensite volume fraction, wherein the martensite volume fraction is obtained by optical microscope analysis and scanning electron microscope analysis on a water-quenched sample, the water-quenched sample being formed by water-quenching a holding sample, and the holding sample being determined by a holding experiment on the cold rolled dual-phase steel cold hard plate under different holding temperatures and different holding times; Determine an austenite volume fraction and an austenite equilibrium volume fraction based on the martensite volume fraction, wherein the austenite equilibrium volume fraction is the martensite volume fraction at different holding temperatures after the holding time is greater than a preset holding time; based on the austenite volume fraction and the soaking temperature , determining a fitting coefficient and ; based on the austenite equilibrium volume fraction, soaking time and soaking temperature , determining a fitting index , fitting coefficients and ; The prediction model is obtained by training a preset number of times based on historical production data and the martensite volume fraction; the historical production data includes chemical composition, process specification and mechanical property; the process specification includes one or more of thickness, tapping temperature, finish rolling temperature, coiling temperature, annealing temperature, slow cooling temperature, fast cooling temperature and strip speed; the mechanical property includes one or more of yield strength, tensile strength and elongation after fracture; the input variables of the prediction model are the chemical composition, the process specification and the martensite volume fraction, and the output variable is the mechanical property.

5. An electronic device comprising: A memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor is configured to implement the steps of the method for predicting the mechanical property of the cold-rolled dual-phase steel automobile sheet according to any one of claims 1-3 when executing the computer program stored in the memory.

6. A computer readable storage medium having stored thereon a computer program, characterized in that: The computer program is executed by the processor to implement the method for predicting the mechanical property of the cold-rolled dual-phase steel automobile sheet according to any one of claims 1-3.

Images