Commercial vehicle piston steel closed-loop design method and piston steel preparation method

Abstract

The invention provides a commercial vehicle piston steel closed-loop design method and a piston steel preparation method, and relates to the technical field of metal material calculation design and ferrous metallurgy manufacturing. The design method comprises the following steps: constructing a high-dimensional material database containing chemical components, process parameters and high-temperature thermophysical properties; a multi-head self-attention mechanism neural network model based on a Transform architecture is established, and nonlinear interaction between microelements V and Mo and matrix elements is accurately captured; an optimization model with the maximum yield strength at the high temperature of 500 DEG C and the maximum heat conductivity as double targets is constructed in a low-silicon constraint space through an NSGA-II algorithm, and global optimization is carried out. Through AI aided design and strict Si content control, on the premise that the Ni element is zero, the problems that traditional high-strength steel is poor in heat dissipation and high in cost due to high alloy content are solved, and the manufacturing method is suitable for manufacturing the high-explosion-pressure commercial vehicle engine piston.

Description

Technical Field

[0001] This invention relates to the technical field of computational design of metallic materials and iron and steel metallurgical manufacturing, and in particular to a closed-loop design method and preparation method for commercial vehicle piston steel. It requires the use of artificial intelligence deep learning models and multi-objective evolutionary algorithms for development. It is a low-cost, high thermal conductivity, and high heat strength alloy steel and its manufacturing process specifically designed for manufacturing pistons of commercial vehicle engines with high burst pressure and high heat load. Background Technology

[0002] With increasingly stringent global requirements for energy conservation and emission reduction in commercial vehicles (such as Euro VI and China VI emission standards), heavy-duty diesel engines are moving towards ultra-high burst pressure (P). max The engine is developing towards higher power density (>220 bar, even reaching 250 bar). Under these conditions, the piston, as the heart of the engine, operates in an extremely harsh environment: it must withstand enormous periodic gas burst pressure and reciprocating inertial forces; the temperature at the piston top (especially at the combustion chamber throat) is consistently between 450-520°C, and it is subjected to intense thermal cycling.

[0003] Currently, traditional piston steels (such as 42CrMo4 and 38MnVS6) are no longer sufficient to meet the above requirements. Traditional 42CrMo4 exhibits severe matrix softening at temperatures exceeding 500℃, with its yield strength dropping below 600MPa, making it highly susceptible to high-temperature creep and throat cracking. To address the high-temperature strength issue, existing technologies primarily employ high-alloying methods (such as adding large amounts of Ni and W) or high-silicon solid solution strengthening methods (adding 0.8-1.2% Si).

[0004] However, the aforementioned existing technical solutions have a serious physical flaw: a significant decrease in thermal conductivity. Scientific research shows that Si and Ni are the elements most detrimental to the thermal conductivity of steel. High Si content causes severe lattice distortion and intense scattering of electrons and phonons, leading to a sharp drop in the thermal conductivity of steel at high temperatures (typically below 30 W / m·K, or even as low as 26-28 W / m·K). Under high explosion pressure conditions above 220 bar, if the piston material has poor thermal conductivity, the enormous heat generated in the combustion chamber cannot be transferred to the cooling oil chamber at the bottom of the piston body in time, resulting in "heat accumulation" at the piston top. This not only accelerates high-temperature oxidation and corrosion of the material but also causes coking of the engine oil, creating a vicious cycle and ultimately leading to piston ablation failure.

[0005] For example, Chinese patent CN119980069A discloses a high-strength, high-toughness, low-thermal-conductivity commercial vehicle engine piston steel and its preparation method. Obviously, the selection of the composition content of the piston steel cannot accurately match the current optimal solution. In the preparation method, the selection of smelting method, billet heat treatment, controlled rolling air cooling and tempering heat treatment, as well as their effects on the microstructure of the prepared steel, have not achieved the ideal effect. In particular, the thermal conductivity of the prepared steel is less than 30W / m·K at 500℃, and the yield strength will not reach the level of ultra-high yield strength (≥800MPa).

[0006] Chinese patent CN114807745A discloses a steel for automobile piston pins and its manufacturing method. The steel has a wide range of alloying elements and needs to meet the matching relationship between the alloying elements. Moreover, its preparation method is complicated and difficult to operate. After rolling, it undergoes spheroidizing annealing in an annealing furnace. The high-temperature yield strength is less than 800MPa. The piston pin itself can reach a maximum temperature of about 350℃ when the automobile engine is running. Obviously, it cannot obtain the excellent high-temperature strength and thermal conductivity of 500℃.

[0007] Chinese patent CN117778901A discloses a steel for automotive shock absorber piston rods and its production method. The steel has a wide selection of alloying elements, especially high-cost alloying elements, which are expensive. Furthermore, the addition of nano-reinforcing phases is difficult, and it is obviously impossible to obtain high-performance steel with a dispersed distribution of nano-reinforcing phases through simple smelting, forging, and heat treatment processes alone. In addition, the uniform distribution of the mixture formed by mixing the four rare earth elements in the steel is also difficult to predict.

[0008] Therefore, the industry urgently needs a new material that is both strong and thermally conductive: one that can maintain ultra-high yield strength (≥800MPa) at 500℃ and excellent thermal conductivity (≥32W / m·K), while keeping costs under control. However, strength and thermal conductivity are often inversely related in terms of physical mechanisms (the more alloying elements, the higher the strength, but the worse the thermal conductivity), and traditional trial-and-error R&D methods are unlikely to find this narrow balance window. Summary of the Invention

[0009] The main objective of this invention is to address the technical problems in the design and preparation of piston steel for commercial vehicles, such as poor heat dissipation of high-strength steel, long R&D cycle, high alloy cost, and difficulty in achieving the desired performance indicators. Therefore, a closed-loop design method and a piston steel preparation method for commercial vehicles are proposed to solve the aforementioned problems.

[0010] A closed-loop design method for commercial vehicle piston steel, comprising the following steps:

[0011] S1. Construction of a high-dimensional thermophysical property database: Collect historical production data and thermodynamic calculation data of steel used in internal combustion engine pistons to construct a multidimensional dataset;

[0012] S2. Attention mechanism feature encoding: Construct a deep neural network prediction model; calculate the covariance matrix between the features of each alloy element to capture the nonlinear interaction of trace elements in a low-silicon matrix and their influence on lattice distortion.

[0013] S3. Dual-objective evolutionary optimization: Defining the objective function vector ,in The raw material cost function It is a comprehensive performance function that includes high-temperature strength and thermal conductivity; iterative search is performed within the low silicon content constraint space to output the optimal solution set;

[0014] S4. Closed-loop iteration and decision-making: The inflection point identification method is used to select the optimal formula from the optimal solution set of S3, and small furnace smelting and performance testing are carried out. The measured data is fed back to the multidimensional dataset of S1 to trigger the online fine-tuning of the model.

[0015] Optionally, the input features of the multidimensional dataset in S1 include the mass fractions of C, Si, Mn, Cr, Mo, V, Ni, Al, S, and P, as well as the austenitizing temperature, tempering temperature, and cooling rate; the output features mainly include room temperature mechanical properties, 500℃ high-temperature yield strength, and 500℃ thermal conductivity.

[0016] Optionally, the thermodynamic calculation data in S1 is thermodynamic Calphad data.

[0017] Optionally, the deep neural network prediction model in S2 is based on the Transformer architecture, and the calculation of the covariance matrix between the features of each alloy element requires the use of the Multi-Head Self-Attention mechanism.

[0018] Optionally, the Multi-Head Self-Attention mechanism in S2 includes h = 4-8 attention heads, and the formula for calculating the attention weight matrix of the i-th head is:

[0019]

[0020] in, These are query, key, and value matrices, respectively. The scaling factor is used; the model analyzes the weighted relationships between V and Mo, and Si and thermal conductivity through heat maps to guide the optimization direction.

[0021] Optionally, the iterative search in the low silicon content constraint space of S3 is performed using NSGA-II in the low silicon content constraint space of Si≤0.35%, and the output optimal solution set is the Pareto Front optimal solution set.

[0022] Optionally, the comprehensive performance function in S3 Set as:

[0023]

[0024] in Yield strength at 500℃ Thermal conductivity at 500℃ , The weighting factor is used; a penalty term is applied when the predicted thermal conductivity is below 32 W / (m·K). This forces the population to converge toward regions with high thermal conductivity.

[0025] Optionally, in S4, the inflection point identification method is used to select the optimal chemical composition weight percentage of the formulation from the Pareto Front optimal solution set of S3 as follows: C 0.38-0.45%, Si 0.15-0.35%, Mn 0.70-1.10%, Cr 1.00-1.30%, Mo 0.20-0.40%, V 0.08-0.15%, P≤0.015%, S≤0.015%, Al 0.015-0.035%, with the balance being Fe and unavoidable impurities;

[0026] The microstructure of the commercial vehicle piston steel is tempered sorbite, with the original austenite grain size ≥ 8; the matrix contains dispersed MC-type and M-type VC with a size ≤ 20 nm. 23 C6 type nano carbides; the commercial vehicle piston steel has a high-temperature yield strength of ≥800MPa at 500℃ in the quenched and tempered state, and a thermal conductivity of ≥32W / (m·K) at 500℃.

[0027] A method for preparing piston steel based on the aforementioned closed-loop design method for commercial vehicle piston steel, the method comprising the following steps:

[0028] Step 1, Smelting: Electric furnace / converter + LF refining + VD vacuum treatment, after VD breaks the vacuum, feed V-Fe, Mo-Fe and Ca-Si wires to smelt and obtain piston steel ingots;

[0029] Step 2, Forging: Heat the piston steel ingot from Step 1 to the homogenization temperature and hold it thereafter, then begin forging. After forging, perform stacking cooling to obtain piston steel forgings.

[0030] Step 3, Preliminary heat treatment: The piston steel forging billet from Step 2 is normalized to obtain normalized piston steel forgings;

[0031] Step 4, tempering: The piston steel normalized forgings from Step 3 are oil quenched and then tempered at high temperature to finally obtain the finished commercial vehicle piston steel.

[0032] Optionally, the dimensions of the piston steel ingot in step 1 are 400×400×2000-600×600×3000mm.

[0033] Optionally, the homogenization temperature in step 2 is 1150-1200℃, the holding time is 120-240min, the initial forging temperature is >1120℃, the final forging temperature is >850℃, the forging ratio is ≥4, and the size of the piston steel forging is 100×100×3000-200×200×6000mm.

[0034] Optionally, the normalizing temperature in step 3 is 870±10℃, and the treatment time is 60-120min.

[0035] Optionally, the oil quenching temperature in step 4 is 860-880℃, and the oil quenching time is 45-90 min; the high-temperature tempering temperature is 590-630℃, and the holding time is ≥2 h.

[0036] Optionally, the high-temperature tempering in step 4 is controlled using Larssen-Miller parameters (LMP).

[0037]

[0038] in, Kelvin temperature, The number of hours is used to ensure that the carbides are fully spheroidized and to reduce lattice distortion, thereby maximizing thermal conductivity.

[0039] Optionally, the room temperature mechanical properties of the commercial vehicle piston steel product obtained in step 4 are as follows: tensile strength of 1000-1250 MPa, yield strength of 900-1100 MPa, yield ratio of 0.85-0.92, elongation of 12-18%, product of strength and ductility of 15-22 GPa%, impact energy of 40-80 J, hardness of 35-42 HRC, and elastic modulus of 206-215 GPa; high temperature yield strength of 800-900 MPa at 500℃, elastic modulus of 170-190 GPa at 500℃, and thermal conductivity of 32-36 W / (m·K) at 500℃.

[0040] Technical principle of the invention:

[0041] A closed-loop design method for commercial vehicle piston steel based on deep learning and multi-objective optimization. This method no longer relies on traditional trial and error, but instead constructs a physical metallurgy-oriented AI model. (1) Data layer: A high-dimensional database is established that includes chemical composition, heat treatment process and high-temperature thermal properties (thermal conductivity at 500℃, high-temperature strength). The physical parameters of the influence of each element on the mean free path of electrons / phonons are introduced as prior knowledge of the model. (2) Algorithm layer: A neural network based on the Transformer architecture is adopted. Using the multi-head self-attention mechanism, the model can quantify the interaction weights between carbide-forming elements such as V, Mo, and Cr at different Si content levels. The model found that in a low silicon environment (Si<0.35%), the combined addition of V and Mo can produce an excess precipitation strengthening effect and has the least damage to thermal conductivity. (3) Optimization layer: A dual-objective optimization function is constructed, with the objective set as "Max(high-temperature strength) & Max(thermal conductivity)". The NSGA-II genetic algorithm was used to search within the confined composition space, automatically avoiding the "high silicon trap" and "high nickel trap" that cause a sharp drop in thermal conductivity.

[0042] A high thermal conductivity and high heat strength piston steel designed and prepared using the above method has the following chemical composition by weight percentage: C 0.38-0.45%: ensuring the hardness and strength of the matrix after quenching and tempering. Si 0.15-0.35%: the core controlled element of this invention. Unlike existing high-strength steels (typically Si>0.6%), this invention strictly controls Si to below 0.35% to reduce the scattering of solid solution atoms on lattice thermal vibrations and ensure thermal conductivity ≥32W / m·K. Mn 0.70-1.10%: providing hardenability and replacing expensive Ni. Cr 1.00-1.30%: improving oxidation resistance and tempering stability, forming a Cr2O3 protective film. Mo 0.20-0.40%: improving high-temperature creep resistance and inhibiting the aggregation and growth of V carbides. V 0.08-0.15%: providing strong precipitation strengthening by forming fine and dispersed VC nanoprecipitates, compensating for the loss of solid solution strengthening caused by low Si. P and S are both ≤0.015%, Al 0.015-0.035%.

[0043] The above technical solution has at least the following advantages compared with the existing technology:

[0044] The above-mentioned solution proposes a closed-loop design method and a piston steel preparation method for commercial vehicles, which can solve the technical problems existing in the composition design and preparation of piston steel for commercial vehicles, such as poor heat dissipation of high-strength steel, long research and development cycle, high alloy cost, and difficulty in balancing performance indicators.

[0045] The design method of this invention solves the contradiction between strength and heat dissipation in the preparation method: by precisely matching the "low Si + V-Mo" scheme through AI, the prepared steel has a yield strength of over 800 MPa at 500℃ while maintaining a thermal conductivity of around 33.5 W / (m·K), which is 15-20% higher than that of high Si steel or high Ni steel of the same strength level, significantly reducing the piston heat load.

[0046] The advantages of this invention are low cost and high efficiency: it does not contain expensive strategic elements such as Ni and W, and uses inexpensive Si (reduced amount), Mn and Cr with trace amounts of V to achieve high performance. The cost of raw materials is only slightly higher than that of ordinary 42CrMo and far lower than that of 4340 steel.

[0047] The present invention has high efficiency and high accuracy in the research and development of the optimal solution for the composition and preparation process of commercial vehicle piston steel: the closed-loop design method shortens the new material development cycle from 24 months to 3-6 months.

[0048] The room temperature mechanical properties of the commercial vehicle piston steel product obtained by the combined design and preparation methods of this invention are as follows: tensile strength of 1000-1250 MPa, yield strength of 900-1100 MPa, yield ratio of 0.85-0.92, elongation of 12-18%, product of strength and ductility of 15-22 GPa%, impact energy of 40-80 J, hardness of 35-42 HRC, and elastic modulus of 206-215 GPa; high temperature yield strength of 800-900 MPa at 500℃, elastic modulus of 170-190 GPa at 500℃, and thermal conductivity of 32-36 W / (m·K) at 500℃.

[0049] In summary, compared with traditional commercial vehicle piston steel preparation, the method of this invention obtains the optimal solution for its composition and the optimal solution for its preparation process through the design method of commercial vehicle piston steel, and then prepares it through the preparation method. This method is simple, accurate, efficient, and has a short cycle. The raw material cost is low. The commercial vehicle piston steel prepared has outstanding performance in terms of high temperature strength and thermal conductivity, which is conducive to large-scale industrial production and application. Attached Figure Description

[0050] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0051] Figure 1 This is a schematic diagram of the algorithm flow of a closed-loop design method for piston steel in commercial vehicles according to the present invention;

[0052] Figure 2This is a microstructure diagram of piston steel prepared under EBSD in the quenched and tempered state according to the closed-loop design method for commercial vehicle piston steel in Embodiment 1 of the present invention.

[0053] Figure 3 This is a comparison curve of the thermal conductivity of piston steel prepared under the closed-loop design method for commercial vehicle piston steel in Examples 1-2 of the present invention and piston steel prepared in Comparative Examples 1-3 at different temperatures.

[0054] Figure 4 This is a Pareto front distribution map generated by the NSGA-II algorithm of the closed-loop design method for commercial vehicle piston steel according to the present invention. Detailed Implementation

[0055] The technical solution of the present invention will now be described with reference to the accompanying drawings.

[0056] In embodiments of the present invention, words such as "exemplarily," "for example," etc., are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" in the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the word "exemplary" is intended to present the concept in a concrete manner. Furthermore, in embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one.

[0057] In the embodiments of the present invention, the terms "image" and "picture" may sometimes be used interchangeably. It should be noted that when the distinction is not emphasized, their intended meanings are consistent.

[0058] In this embodiment of the invention, sometimes a subscript such as W1 may be written in a non-subscript form such as W1. When the difference is not emphasized, the meaning they express is the same.

[0059] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0060] A closed-loop design method for commercial vehicle piston steel, wherein the commercial vehicle piston steel closed-loop design method combines Figure 1 Includes the following steps:

[0061] S1. Construction of a high-dimensional thermophysical property database: Collect historical production data and thermodynamic calculation data of steel used in internal combustion engine pistons to construct a multidimensional dataset;

[0062] S2. Attention mechanism feature encoding: Construct a deep neural network prediction model; calculate the covariance matrix between the features of each alloy element to capture the nonlinear interaction of trace elements in a low-silicon matrix and their influence on lattice distortion.

[0063] S3. Dual-objective evolutionary optimization: Defining the objective function vector ,in The raw material cost function It is a comprehensive performance function that includes high-temperature strength and thermal conductivity; iterative search is performed within the low silicon content constraint space to output the optimal solution set;

[0064] S4. Closed-loop iteration and decision-making: The inflection point identification method is used to select the optimal formula from the optimal solution set of S3, and small furnace smelting and performance testing are carried out. The measured data is fed back to the multidimensional dataset of S1 to trigger the online fine-tuning of the model.

[0065] Specifically, the input features of the multidimensional dataset in S1 include the mass fractions of C, Si, Mn, Cr, Mo, V, Ni, Al, S, and P, as well as the austenitizing temperature, tempering temperature, and cooling rate; the output features mainly include room temperature mechanical properties, 500℃ high-temperature yield strength, and 500℃ thermal conductivity.

[0066] Specifically, the thermodynamic calculation data in S1 are thermodynamic Calphad data.

[0067] In particular, the deep neural network prediction model in S2 is based on the Transformer architecture, and the calculation of the covariance matrix between the features of each alloy element requires the use of the Multi-Head Self-Attention mechanism.

[0068] Specifically, the Multi-Head Self-Attention mechanism in S2 includes h = 4-8 attention heads, and the formula for calculating the attention weight matrix of the i-th head is:

[0069]

[0070] in, These are query, key, and value matrices, respectively. The scaling factor is used; the model analyzes the weighted relationships between V and Mo, and Si and thermal conductivity through heat maps to guide the optimization direction.

[0071] Specifically, the iterative search within the low-silicon content constraint space in S3 is performed using NSGA-II within the low-silicon content constraint space (Si ≤ 0.35%), and the output optimal solution set is the Pareto Front optimal solution set. The multi-objective optimization Pareto front distribution generated by the NSGA-II algorithm for the closed-loop design method of commercial vehicle piston steel is shown below. Figure 4 As shown. Figure 4As shown, the horizontal and vertical axes correspond to the optimization objective functions of yield strength and thermal conductivity at 500℃, respectively. The distributed gray scatter points and the converging solid Pareto front clearly reveal the competitive inverse relationship between these two performance indicators in the low-silicon confinement system. The circled KNEE POINT (inflection point) in the figure is located at the point of maximum curvature of the front curve. It is the optimal equilibrium solution locked by the decision algorithm of this invention, representing the marginal maximization of comprehensive performance gains. At this position, the material can obtain the maximum strength gain with the minimum thermal conductivity sacrifice, effectively avoiding the trap of convergence to a single performance extreme. This confirms the feasibility of achieving a physical balance between high strength and high thermal conductivity in this invention, and provides a direct mathematical model basis for the selection of the optimal formulation in the examples.

[0072] Specifically, the comprehensive performance function in S3 Set as:

[0073]

[0074] in Yield strength at 500℃ Thermal conductivity at 500℃ , The weighting factor is used; a penalty term is applied when the predicted thermal conductivity is below 32 W / (m·K). This forces the population to converge toward regions with high thermal conductivity.

[0075] Specifically, in S4, the inflection point identification method was used to select the optimal chemical composition weight percentage from the Pareto Front optimal solution set of S3 as follows: C 0.38-0.45%, Si 0.15-0.35%, Mn 0.70-1.10%, Cr 1.00-1.30%, Mo 0.20-0.40%, V 0.08-0.15%, P≤0.015%, S≤0.015%, Al 0.015-0.035%, with the balance being Fe and unavoidable impurities;

[0076] The microstructure of the commercial vehicle piston steel is tempered sorbite, with the original austenite grain size ≥ 8; the matrix contains dispersed MC-type and M-type VC with a size ≤ 20 nm. 23 C6 type nano carbides; the commercial vehicle piston steel has a high-temperature yield strength of ≥800MPa at 500℃ in the quenched and tempered state, and a thermal conductivity of ≥32W / (m·K) at 500℃.

[0077] A method for preparing piston steel based on the aforementioned closed-loop design method for commercial vehicle piston steel, the method comprising the following steps:

[0078] Step 1, Smelting: Electric furnace / converter + LF refining + VD vacuum treatment, after VD breaks the vacuum, feed V-Fe, Mo-Fe and Ca-Si wires to smelt and obtain piston steel ingots;

[0079] Step 2, Forging: Heat the piston steel ingot from Step 1 to the homogenization temperature and hold it thereafter, then begin forging. After forging, perform stacking cooling to obtain piston steel forgings.

[0080] Step 3, Preliminary heat treatment: The piston steel forging billet from Step 2 is normalized to obtain normalized piston steel forgings;

[0081] Step 4, tempering: The piston steel normalized forgings from Step 3 are oil quenched and then tempered at high temperature to finally obtain the finished commercial vehicle piston steel.

[0082] Specifically, the dimensions of the piston steel ingot in step 1 are 400×400×2000-600×600×3000mm.

[0083] Specifically, the homogenization temperature in step 2 is 1150-1200℃, the holding time is 120-240min, the initial forging temperature is >1120℃, the final forging temperature is >850℃, the forging ratio is ≥4, and the dimensions of the piston steel forging are 100×100×3000-200×200×6000mm.

[0084] Specifically, the normalizing temperature in step 3 is 870±10℃, and the treatment time is 60-120min.

[0085] Specifically, the oil quenching temperature in step 4 is 860-880℃, and the oil quenching time is 45-90 min; the high-temperature tempering temperature is 590-630℃, and the holding time is ≥2 h.

[0086] Specifically, the high-temperature tempering in step 4 is controlled using Larssen-Miller parameters (LMP).

[0087]

[0088] in, Kelvin temperature, The number of hours is used to ensure that the carbides are fully spheroidized and to reduce lattice distortion, thereby maximizing thermal conductivity.

[0089] Specifically, the room temperature mechanical properties of the commercial vehicle piston steel product from step 4 are as follows: tensile strength 1000-1250MPa, yield strength 900-1100MPa, yield ratio 0.85-0.92, elongation 12-18%, strength-ductility product 15-22GPa%, impact energy 40-80J, hardness 35-42HRC, and elastic modulus 206-215GPa; high temperature yield strength at 500℃ is 800-900MPa, elastic modulus at 500℃ is 170-190GPa, and thermal conductivity at 500℃ is 32-36W / (m·K).

[0090] The performance tests in the following examples were conducted in accordance with GB / T 228.2 (high temperature tensile test) and ASTM E1461 (thermal conductivity by laser flash test).

[0091] Example 1

[0092] This embodiment provides a closed-loop design method for commercial vehicle piston steel, which includes the following steps:

[0093] S1. Construction of a High-Dimensional Thermophysical Property Database: Historical production data and thermodynamic Calphad data for internal combustion engine piston steel were collected to construct a multidimensional dataset. The input features of the multidimensional dataset include the mass fractions of C, Si, Mn, Cr, Mo, V, Ni, Al, S, and P, as well as austenitizing temperature, tempering temperature, and cooling rate. The output features primarily include room temperature mechanical properties, yield strength at 500℃, and thermal conductivity at 500℃. Specifically, this embodiment trains a Transformer model based on 1500 sets of historical data (including experimental values ​​and Thermo-Calc calculated values). The model input layer accepts a 12-dimensional vector, which is processed through a 3-layer encoder. Key findings: Visual analysis of the attention weight matrix shows a strong negative correlation between Si content and thermal conductivity (Weight = -0.85); however, when Si < 0.35%, the positive interaction weight between V and Mo significantly increases (Weight = +0.78).

[0094] S2. Attention Mechanism Feature Encoding: A deep neural network prediction model is constructed based on the Transformer architecture; the multi-head self-attention mechanism is used to calculate the covariance matrix between the features of each alloy element, capturing the nonlinear interaction of trace elements in a low-silicon matrix and their influence on lattice distortion.

[0095] S3. Dual-objective evolutionary optimization: Define the objective function vector F(x)=[fcost(x),-fperf(x)], where fcost(x) is the raw material cost function and fperf(x) is the comprehensive performance function including high temperature strength and thermal conductivity; NSGA-II is used for iterative search in the low silicon content constraint space of Si≤0.35% to output the Pareto Front optimal solution set;

[0096] S4. Closed-loop iteration and decision-making: The optimal formula is selected from the Pareto Front optimal solution set of S3 using the inflection point identification method. The chemical composition by weight percentage is: C 0.42, Si 0.25, Mn 0.95, Cr 1.15, Mo 0.25, V 0.12, P 0.009, S 0.005, Al 0.025, with the balance being Fe and unavoidable impurities. Afterwards, small-scale furnace smelting and performance testing are carried out, and the measured data is fed back to the multidimensional dataset of S1 to trigger the online fine-tuning of the model.

[0097] like Figure 2 As shown, the microstructure of the commercial vehicle piston steel in this embodiment is tempered sorbite with a primary austenite grain size of 8.5. The matrix is ​​dispersed with VC and M23C6 type nanocarbides with a size of 10-15nm. The commercial vehicle piston steel has a high-temperature yield strength of 825MPa at 500℃ in the quenched and tempered state, and a thermal conductivity of 33.5W / (m·K) at 500℃. The cost index (baseline = 1.0) is 1.08.

[0098] A method for preparing piston steel based on the aforementioned closed-loop design method for commercial vehicle piston steel, the method comprising the following steps:

[0099] Step 1, Smelting: Electric furnace / converter + LF refining + VD vacuum treatment, after VD breaking the vacuum, feed V-Fe, Mo-Fe and Ca-Si wires to smelt to obtain 50kg piston steel ingots; the size of the piston steel ingots is 350×350×1500mm.

[0100] Step 2, Forging: The piston steel ingot from Step 1 is heated to a homogenization temperature of 1180℃ and held for 2 hours. Forging then begins at an initial forging temperature of 1150℃, using a two-upsetting and two-drawing process with a forging ratio >4. The final forging temperature is 880℃. After forging, the piston steel ingot is buried in sand and cooled to below 200℃, followed by air cooling to obtain the piston steel forging. The piston steel forging has a size of Φ150mm.

[0101] Step 3, Preliminary heat treatment: The piston steel forging billet from Step 2 is normalized at 870℃, held at that temperature for 1 hour, and then air-cooled to obtain normalized piston steel forging.

[0102] Step 4, tempering: The piston steel normalized forgings from Step 3 are subjected to oil quenching. The quenching temperature is raised to 880℃ and held for 45 minutes. Then, the oil is quenched (oil temperature 60℃) and immediately tempered at 610℃ for 2 hours to obtain the finished commercial vehicle piston steel product.

[0103] The room temperature mechanical properties of the commercial vehicle piston steel product in this embodiment are as follows: tensile strength of 1100 MPa, yield strength of 950 MPa, yield ratio of 0.86, elongation of 15.5%, strength-ductility product of 17.0 GPa%, impact energy of 60 J, hardness of 35 HRC, and elastic modulus of 2.10 × 10^11 Pa; high temperature yield strength of 825 MPa at 500℃, elastic modulus of 1.75 × 10^11 Pa at 500℃, and thermal conductivity of 33.5 W / (m·K) at 500℃.

[0104] Example 2

[0105] This embodiment provides a closed-loop design method for commercial vehicle piston steel, which includes the following steps:

[0106] S1. Construction of high-dimensional thermophysical property database: Same as in Example 1.

[0107] S2, Attention mechanism feature encoding: Same as in Example 1.

[0108] S3. Dual-objective evolutionary optimization: Same as Example 1, only the parameters of the output optimal solution set are different.

[0109] S4. Closed-loop iteration and decision-making: The optimal formula is selected from the Pareto Front optimal solution set of S3 using the inflection point identification method. The chemical composition by weight percentage is: C 0.44, Si 0.30, Mn 1.05, Cr 1.25, Mo 0.38, V 0.14, P 0.009, S 0.005, Al 0.025, with the balance being Fe and unavoidable impurities. Afterwards, small-scale furnace smelting and performance testing are carried out, and the measured data is fed back to the multidimensional dataset of S1 to trigger the online fine-tuning of the model.

[0110] The microstructure of the commercial vehicle piston steel in this embodiment is tempered sorbite with a primary austenite grain size of 8.5. The matrix contains dispersed nano-carbides of 10-15 nm size, mainly VC and M23C6 type. The commercial vehicle piston steel has a high-temperature yield strength of 855 MPa at 500 °C in the quenched and tempered state, a thermal conductivity of 32.8 W / (m·K) at 500 °C, and a cost index (baseline = 1.0) of 1.12.

[0111] A method for preparing piston steel based on the aforementioned closed-loop design method for commercial vehicle piston steel, the method comprising the following steps:

[0112] Step 1, Smelting: Electric furnace / converter + LF refining + VD vacuum treatment, after VD breaking the vacuum, feed V-Fe, Mo-Fe and Ca-Si wires to smelt to obtain 50kg piston steel ingots; the size of the piston steel ingots is 350×350×1500mm.

[0113] Step 2, Forging: The piston steel ingot from Step 1 is heated to a homogenization temperature of 1180℃ and held for 2 hours. Forging then begins at an initial forging temperature of 1150℃, using a two-upsetting and two-drawing process with a forging ratio >4. The final forging temperature is 880℃. After forging, the piston steel ingot is buried in sand and cooled to below 200℃, followed by air cooling to obtain the piston steel forging. The piston steel forging has a size of Φ150mm.

[0114] Step 3, Preliminary heat treatment: The piston steel forging billet from Step 2 is normalized at 870℃, held at that temperature for 1 hour, and then air-cooled to obtain normalized piston steel forging.

[0115] Step 4, tempering: The piston steel normalized forgings from Step 3 are subjected to oil quenching, heated to 880℃ and held for 60 minutes, followed by oil quenching (oil temperature 60℃), and then tempered at 620℃ for 2 hours to finally obtain the finished commercial vehicle piston steel.

[0116] The room temperature mechanical properties of the commercial vehicle piston steel product in this embodiment are as follows: tensile strength of 1180 MPa, yield strength of 1020 MPa, yield ratio of 0.86, elongation of 14.0%, strength-ductility product of 16.5 GPa%, impact energy of 50 J, hardness of 37 HRC, and elastic modulus of 2.12 × 10^11 Pa; high temperature yield strength of 855 MPa at 500℃, elastic modulus of 1.78 × 10^11 Pa at 500℃, and thermal conductivity of 32.8 W / (m·K) at 500℃.

[0117] Example 3

[0118] The closed-loop design method for commercial vehicle piston steel in this embodiment is basically the same as that in Embodiment 1 in steps S1-S3, except that in S3, the focus is on optimizing the thermal conductivity under extremely low silicon content.

[0119] S4. Closed-loop iteration and decision-making: The optimal formula is selected from the Pareto Front optimal solution set of S3 using the inflection point identification method. The chemical composition by weight percentage is: C 0.40, Si 0.18, Mn 0.85, Cr 1.10, Mo 0.35, V 0.15, P 0.008, S 0.004, Al 0.020, with the balance being Fe and unavoidable impurities. After that, small-scale furnace smelting and performance testing are carried out.

[0120] The microstructure of the commercial vehicle piston steel in this embodiment is tempered sorbite with a primary austenite grain size of 8.0. The matrix contains dispersed nano-carbides of 10-15 nm size, mainly VC and M23C6 type. The commercial vehicle piston steel has a high-temperature yield strength of 815 MPa at 500 °C in the quenched and tempered state, a thermal conductivity of 34.8 W / (m·K) at 500 °C, and a cost index (baseline = 1.0) of 1.10.

[0121] A method for preparing piston steel based on the aforementioned closed-loop design method for commercial vehicle piston steel, the method comprising the following steps:

[0122] Step 1, Smelting: Electric furnace / converter + LF refining + VD vacuum treatment, after VD breaking the vacuum, feed V-Fe, Mo-Fe and Ca-Si wires to smelt and obtain 50kg piston steel ingots; the size of the piston steel ingots is 400×400×1500mm.

[0123] Step 2, Forging: The piston steel ingot from Step 1 is heated to a homogenization temperature of 1160℃ and held for 3 hours. Forging then begins at an initial forging temperature of 1130℃, using a two-upsetting and two-drawing process with a forging ratio >5. The final forging temperature is 860℃. After forging, the ingot is buried in sand and cooled to below 200℃, followed by air cooling to obtain the piston steel forging. The piston steel forging has a size of Φ160mm.

[0124] Step 3, Preliminary heat treatment: The piston steel forging billet from Step 2 is normalized at 870℃, held at that temperature for 2 hours, and then air-cooled to obtain normalized piston steel forging.

[0125] Step 4, tempering: The piston steel normalized forgings from Step 3 are subjected to oil quenching, heated to 870℃ and held for 60 minutes, followed by oil quenching (oil temperature 60℃), and then tempered at 600℃ for 2.5 hours to finally obtain the finished commercial vehicle piston steel.

[0126] The room temperature mechanical properties of the commercial vehicle piston steel product in this embodiment are as follows: tensile strength of 1080 MPa, yield strength of 930 MPa, yield ratio of 0.86, elongation of 16.5%, strength-ductility product of 17.8 GPa%, impact energy of 65 J, hardness of 34 HRC, and elastic modulus of 2.08 × 10^11 Pa; high temperature yield strength of 815 MPa at 500℃, elastic modulus of 1.72 × 10^11 Pa at 500℃, and thermal conductivity of 34.8 W / (m·K) at 500℃.

[0127] Example 4

[0128] The closed-loop design method for commercial vehicle piston steel in this embodiment is basically the same as that in embodiment 1 in steps S1-S3, except that in S3, the focus is on exploring the upper limit of strength.

[0129] S4. Closed-loop iteration and decision-making: The optimal formula is selected from the Pareto Front optimal solution set of S3 using the inflection point identification method. The chemical composition by weight percentage is: C 0.45, Si 0.32, Mn 1.00, Cr 1.30, Mo 0.30, V 0.10, P 0.010, S 0.005, Al 0.030, with the balance being Fe and unavoidable impurities. Then, small-scale furnace smelting and performance testing are carried out.

[0130] The microstructure of the commercial vehicle piston steel in this embodiment is tempered sorbite with a primary austenite grain size of 9.0. The matrix contains dispersed nano-carbides of 10-15 nm size, mainly VC and M23C6 type. The commercial vehicle piston steel has a high-temperature yield strength of 875 MPa at 500 °C in the quenched and tempered state, a thermal conductivity of 32.2 W / (m·K) at 500 °C, and a cost index (baseline = 1.0) of 1.09.

[0131] A method for preparing piston steel based on the aforementioned closed-loop design method for commercial vehicle piston steel, the method comprising the following steps:

[0132] Step 1, Smelting: Electric furnace / converter + LF refining + VD vacuum treatment, after VD breaking the vacuum, feed V-Fe, Mo-Fe and Ca-Si wires to smelt to obtain 50kg piston steel ingots; the size of the piston steel ingots is 350×350×1200mm.

[0133] Step 2, Forging: The piston steel ingot from Step 1 is heated to a homogenization temperature of 1190℃ and held for 2.5 hours. Forging then begins at an initial forging temperature of 1160℃, using a two-upsetting and two-drawing process with a forging ratio >4.5 and a final forging temperature of 890℃. After forging, the ingot is buried in sand and cooled to below 200℃, followed by air cooling to obtain the piston steel forging. The piston steel forging has a size of Φ180mm.

[0134] Step 3, Preliminary heat treatment: The piston steel forging billet from Step 2 is normalized at 875℃, held at that temperature for 1.5 hours, and then air-cooled to obtain normalized piston steel forging.

[0135] Step 4, tempering: The piston steel normalized forgings from Step 3 are subjected to oil quenching, heated to 880℃ and held for 50 minutes, then oil quenched (oil temperature 60℃), and then tempered at 590℃ for 2 hours to finally obtain the finished commercial vehicle piston steel.

[0136] The room temperature mechanical properties of the commercial vehicle piston steel product in this embodiment are as follows: tensile strength of 1220 MPa, yield strength of 1080 MPa, yield ratio of 0.88, elongation of 13.5%, strength-ductility product of 16.5 GPa%, impact energy of 45 J, hardness of 38 HRC, and elastic modulus of 2.13 × 10^11 Pa; high temperature yield strength of 875 MPa at 500℃, elastic modulus of 1.79 × 10^11 Pa at 500℃, and thermal conductivity of 32.2 W / (m·K) at 500℃.

[0137] Example 5

[0138] The closed-loop design method for commercial vehicle piston steel in this embodiment is basically the same as that in Embodiment 1 in steps S1-S3.

[0139] S4. Closed-loop iteration and decision-making: The optimal formulation is selected from the Pareto Front optimal solution set of S3 using the inflection point identification method. The chemical composition by weight percentage is: C 0.41, Si 0.28, Mn 0.90, Cr 1.20, Mo 0.28, V 0.11, P 0.012, S 0.008, Al 0.022, with the balance being Fe and unavoidable impurities.

[0140] The microstructure of the commercial vehicle piston steel in this embodiment is tempered sorbite with a primary austenite grain size of 8.5. The matrix contains dispersed VC and M23C6 type nanocarbides with a size of 10-15nm. The commercial vehicle piston steel has a high-temperature yield strength of 805MPa at 500℃ in the quenched and tempered state, a thermal conductivity of 33.8W / (m·K) at 500℃, and a cost index (baseline = 1.0) of 1.07.

[0141] A method for preparing piston steel based on the aforementioned closed-loop design method for commercial vehicle piston steel, the method comprising the following steps:

[0142] Step 1, Smelting: Electric furnace / converter + LF refining + VD vacuum treatment, after VD breaking the vacuum, feed V-Fe, Mo-Fe and Ca-Si wires to smelt and obtain 50kg piston steel ingots; the size of the piston steel ingots is 500×500×2000mm.

[0143] Step 2, Forging: The piston steel ingot from Step 1 is heated to a homogenization temperature of 1200℃ and held for 4 hours. Forging then begins at an initial forging temperature of 1180℃, using a two-upsetting and two-drawing process with a forging ratio >6 and a final forging temperature of 900℃. After forging, the piston steel is buried in sand and cooled to below 200℃, then air-cooled to obtain the piston steel forging. The dimensions of the piston steel forging are 200×200mm.

[0144] Step 3, Preliminary heat treatment: The piston steel forging billet from Step 2 is normalized at 870℃, held at that temperature for 3 hours, and then air-cooled to obtain normalized piston steel forging.

[0145] Step 4, Tempering: The piston steel normalized forgings from Step 3 are subjected to oil quenching. The quenching temperature is raised to 875℃ and held for 80 minutes. Then, the oil is quenched again (oil temperature 60℃). The tempering is then carried out at high temperature. The tempering is controlled by Larssen-Miller parameters (LMP). The LMP value is set to 18800, which corresponds to a tempering temperature of 625℃ and a holding time of 3 hours. Finally, the finished commercial vehicle piston steel is obtained.

[0146] The room temperature mechanical properties of the commercial vehicle piston steel product in this embodiment are as follows: tensile strength of 1050 MPa, yield strength of 900 MPa, yield ratio of 0.86, elongation of 17.0%, strength-ductility product of 17.8 GPa%, impact energy of 72 J, hardness of 33 HRC, and elastic modulus of 2.08 × 10^11 Pa; high temperature yield strength of 805 MPa at 500℃, elastic modulus of 1.70 × 10^11 Pa at 500℃, and thermal conductivity of 33.8 W / (m·K) at 500℃.

[0147] Example 6

[0148] The closed-loop design method for commercial vehicle piston steel in this embodiment is basically the same as that in embodiment 1 in steps S1-S3, except that S3 focuses on low cost control.

[0149] S4. Closed-loop iteration and decision-making: The optimal formulation is selected from the Pareto Front optimal solution set of S3 using the inflection point identification method. The chemical composition by weight percentage is: C 0.43, Si 0.30, Mn 1.10, Cr 1.05, Mo 0.22, V 0.09, P 0.015, S 0.010, Al 0.035, with the balance being Fe and unavoidable impurities.

[0150] The microstructure of the commercial vehicle piston steel in this embodiment is tempered sorbite with a primary austenite grain size of 8.0. The matrix contains dispersed nano-carbides of 10-15 nm size, mainly VC and M23C6 type. The commercial vehicle piston steel has a high-temperature yield strength of 802 MPa at 500 °C in the quenched and tempered state, and a thermal conductivity of 33.0 W / (m·K) at 500 °C. The cost index (baseline = 1.0) is 1.03.

[0151] A method for preparing piston steel based on the aforementioned closed-loop design method for commercial vehicle piston steel, the method comprising the following steps:

[0152] Step 1, Smelting: Electric furnace / converter + LF refining + VD vacuum treatment, after VD breaking the vacuum, feed V-Fe, Mo-Fe and Ca-Si wires to smelt and obtain 50kg piston steel ingots; the size of the piston steel ingots is 300×300×1000mm.

[0153] Step 2, Forging: The piston steel ingot from Step 1 is heated to a homogenization temperature of 1150℃ and held for 2 hours. Forging then begins at an initial forging temperature of 1120℃, using a two-upsetting and two-drawing process with a forging ratio >4. The final forging temperature is 850℃. After forging, the ingot is buried in sand and cooled to below 200℃, followed by air cooling to obtain the piston steel forging. The piston steel forging has a size of Φ120mm.

[0154] Step 3, Preliminary heat treatment: The piston steel forging billet from Step 2 is normalized at 865℃, held at that temperature for 1.5 hours, and then air-cooled to obtain normalized piston steel forging.

[0155] Step 4, tempering: The piston steel normalized forgings from Step 3 are subjected to oil quenching, heated to 860℃ and held for 45 minutes, followed by oil quenching (oil temperature 60℃), and then tempered at 605℃ for 2 hours to finally obtain the finished commercial vehicle piston steel.

[0156] The room temperature mechanical properties of the commercial vehicle piston steel product in this embodiment are as follows: tensile strength of 1030 MPa, yield strength of 880 MPa, yield ratio of 0.85, elongation of 15.0%, strength-ductility product of 15.5 GPa%, impact energy of 55 J, hardness of 32 HRC, and elastic modulus of 2.07 × 10^11 Pa; high temperature yield strength of 802 MPa at 500℃, elastic modulus of 1.70 × 10^11 Pa at 500℃, and thermal conductivity of 33.0 W / (m·K) at 500℃.

[0157] Comparative Example 1

[0158] This comparative example uses a traditional commercial vehicle piston steel (similar to 42CrMo4) with the following chemical composition by weight percentage: C 0.41, Si 0.25, Mn 0.75, Cr 0.95, Mo 0.20, V <0.01, P 0.015, S 0.010, Al 0.025, with the balance being Fe and unavoidable impurities.

[0159] The microstructure of the commercial vehicle piston steel in this comparative example is tempered sorbite with a primary austenite grain size of 7.5. The matrix lacks nanoscale MC-type carbide precipitation. The commercial vehicle piston steel has a high-temperature yield strength of 580 MPa at 500℃ in the quenched and tempered state, and a thermal conductivity of 35.0 W / (m·K) at 500℃. The cost index (benchmark = 1.0) is 1.00.

[0160] A method for preparing piston steel based on the comparative formulation, the method comprising the following steps:

[0161] Step 1, Smelting: Electric furnace / converter + LF refining + VD vacuum treatment, after VD breaking the vacuum, Mo-Fe and Ca-Si wires are fed in (V-Fe is not fed in) to smelt and obtain 50kg piston steel ingots; the size of the piston steel ingots is 350×350×1500mm.

[0162] Step 2, Forging: The piston steel ingot from Step 1 is heated to a homogenization temperature of 1180℃ and held for 2 hours. Forging then begins at an initial forging temperature of 1150℃, using a two-upsetting and two-drawing process with a forging ratio >4. The final forging temperature is 880℃. After forging, the piston steel ingot is buried in sand and cooled to below 200℃, followed by air cooling to obtain the piston steel forging. The piston steel forging has a size of Φ150mm.

[0163] Step 3, Preliminary heat treatment: The piston steel forging billet from Step 2 is normalized at 870℃, held at that temperature for 1 hour, and then air-cooled to obtain normalized piston steel forging.

[0164] Step 4, tempering: The piston steel normalized forgings from Step 3 are subjected to oil quenching, heated to 850℃ and held for 60 minutes, followed by oil quenching (oil temperature 60℃), and then tempered at 600℃ for 2 hours to finally obtain the finished commercial vehicle piston steel product.

[0165] The room temperature mechanical properties of the commercial vehicle piston steel product in this comparative example are as follows: tensile strength 980 MPa, yield strength 850 MPa, yield ratio 0.87, elongation 14.0%, strength-ductility product 13.7 GPa%, impact energy 45 J, hardness 30 HRC, and elastic modulus 2.06 × 10^11 Pa; high temperature yield strength at 500℃ is 580 MPa, elastic modulus at 500℃ is 1.60 × 10^11 Pa, and thermal conductivity at 500℃ is 35.0 W / (m·K).

[0166] Comparative Example 2

[0167] This comparative example uses a high-nickel piston steel (similar to a modified 4340) with the following chemical composition by weight percentage: C 0.40, Si 0.25, Mn 0.70, Cr 0.80, Mo 0.25, Ni 1.80, P 0.012, S 0.008, Al 0.025, with the balance being Fe and unavoidable impurities.

[0168] The microstructure of the commercial vehicle piston steel in this comparative example is tempered sorbite with a pre-austenite grain size of 8.5. The matrix exhibits solid solution strengthening due to the high Ni content, but lacks precipitation strengthening by V. The commercial vehicle piston steel has a high-temperature yield strength of 750 MPa at 500℃ in the quenched and tempered state, a thermal conductivity of 28.5 W / (m·K) at 500℃, and a cost index (baseline = 1.0) of 1.65.

[0169] A method for preparing piston steel based on the comparative formulation, the method comprising the following steps:

[0170] Step 1, Smelting: Electric furnace / converter + LF refining + VD vacuum treatment, after VD breaking the vacuum, Ni plate, Mo-Fe and Ca-Si wire are fed in for smelting to obtain 50kg piston steel ingots; the size of the piston steel ingots is 350×350×1500mm.

[0171] Step 2, Forging: The piston steel ingot from Step 1 is heated to a homogenization temperature of 1180℃ and held for 2 hours. Forging then begins at an initial forging temperature of 1150℃, using a two-upsetting and two-drawing process with a forging ratio >4. The final forging temperature is 880℃. After forging, the piston steel ingot is buried in sand and cooled to below 200℃, followed by air cooling to obtain the piston steel forging. The piston steel forging has a size of Φ150mm.

[0172] Step 3, Preliminary heat treatment: The piston steel forging billet from Step 2 is normalized at 870℃, held at that temperature for 1 hour, and then air-cooled to obtain normalized piston steel forging.

[0173] Step 4, tempering: The piston steel normalized forgings from Step 3 are subjected to oil quenching, heated to 850℃ and held for 60 minutes, followed by oil quenching (oil temperature 60℃), and then tempered at 600℃ for 2 hours to finally obtain the finished commercial vehicle piston steel product.

[0174] The room temperature mechanical properties of the commercial vehicle piston steel product in this comparative example are as follows: tensile strength 1200 MPa, yield strength 1080 MPa, yield ratio 0.90, elongation 15.0%, strength-ductility product 18.0 GPa%, impact energy 80 J, hardness 38 HRC, and elastic modulus 2.05 × 10^11 Pa; high temperature yield strength at 500℃ is 750 MPa, elastic modulus at 500℃ is 1.70 × 10^11 Pa, and thermal conductivity at 500℃ is 28.5 W / (m·K).

[0175] Comparative Example 3

[0176] This comparative example uses a high-silicon, high-vanadium piston steel (simulating an existing technical route), with the following chemical composition by weight percentage: C 0.35, Si 1.05, Mn 0.90, Cr 1.20, Mo 0.20, V 0.22, P 0.015, S 0.010, Al 0.025, with the balance being Fe and unavoidable impurities.

[0177] The microstructure of the commercial vehicle piston steel in this comparative example is tempered sorbite with a primary austenite grain size of 8.0. The matrix contains a large number of carbides and has a high Si solid solution content. The commercial vehicle piston steel has a high-temperature yield strength of 760 MPa at 500℃ in the quenched and tempered state, a thermal conductivity of 28.0 W / (m·K) at 500℃, and a cost index (baseline = 1.0) of 1.05.

[0178] A method for preparing piston steel based on the comparative formulation, the method comprising the following steps:

[0179] Step 1, Smelting: Electric furnace / converter + LF refining + VD vacuum treatment, after VD breaking the vacuum, a large amount of V-Fe, Mo-Fe, Si-Fe and Ca-Si wires are fed in for smelting to obtain 50kg piston steel ingots; the size of the piston steel ingots is 350×350×1500mm.

[0180] Step 2, Forging: The piston steel ingot from Step 1 is heated to a homogenization temperature of 1180℃ and held for 2 hours. Forging then begins at an initial forging temperature of 1150℃, using a two-upsetting and two-drawing process with a forging ratio >4. The final forging temperature is 880℃. After forging, the piston steel ingot is buried in sand and cooled to below 200℃, followed by air cooling to obtain the piston steel forging. The piston steel forging has a size of Φ150mm.

[0181] Step 3, Preliminary heat treatment: The piston steel forging billet from Step 2 is normalized at 870℃, held at that temperature for 1 hour, and then air-cooled to obtain normalized piston steel forging.

[0182] Step 4, tempering: The piston steel normalized forgings from Step 3 are subjected to oil quenching, heated to 880℃ and held for 60 minutes, then oil quenched (oil temperature 60℃), and then tempered at 600℃ for 2 hours to finally obtain the finished commercial vehicle piston steel.

[0183] The room temperature mechanical properties of the commercial vehicle piston steel product in this comparative example are as follows: tensile strength 1150 MPa, yield strength 1000 MPa, yield ratio 0.87, elongation 12.0%, strength-ductility product 13.8 GPa%, impact energy 30 J, hardness 36 HRC, and elastic modulus 2.00 × 10^11 Pa; high temperature yield strength at 500℃ is 760 MPa, elastic modulus at 500℃ is 1.65 × 10^11 Pa, and thermal conductivity at 500℃ is 28.0 W / (m·K).

[0184] Combination Figure 3 A comparison of Examples 1-2 and Comparative Examples 1-3 shows that: [The following text appears to be a separate, unrelated sentence fragment: "combined with..."] Figure 3 A comparison of Examples 1-2 and Comparative Examples 1-3 shows that the thermal conductivity of Examples 1-2 at 500℃ remained consistently high, ranging from 32.8 to 33.5 W / (m·K), significantly better than Comparative Examples 2 and 3, which employed high-nickel or high-silicon strengthening methods (both dropping below 29 W / (m·K)). This strongly demonstrates that the "low-silicon + V-Mo synergistic precipitation" strategy based on AI closed-loop design effectively avoids the severe phonon scattering effect caused by drastic lattice distortion induced by solid solution atoms (such as high Si and high Ni) in traditional high-strength steel. Compared to Comparative Example 1, which only possesses high thermal conductivity but severely insufficient high-temperature strength (<600 MPa), this invention achieves ultra-high yield strength (≥800 MPa) while maintaining excellent thermal conductivity close to the matrix limit. It successfully breaks through the physical inversion bottleneck of the traditional piston steel's inability to simultaneously achieve strength and thermal conductivity, solving the problem of heat accumulation and ablation failure under high-pressure conditions, demonstrating outstanding substantive features and significant beneficial effects.

[0185] The above-mentioned solution proposes a closed-loop design method and a piston steel preparation method for commercial vehicles, which can solve the technical problems existing in the composition design and preparation of piston steel for commercial vehicles, such as poor heat dissipation of high-strength steel, long research and development cycle, high alloy cost, and difficulty in balancing performance indicators.

[0186] The design method of this invention solves the contradiction between strength and heat dissipation in the preparation method: by precisely matching the "low Si + V-Mo" scheme through AI, the prepared steel has a yield strength of over 800 MPa at 500℃ while maintaining a thermal conductivity of around 33.5 W / (m·K), which is 15-20% higher than that of high Si steel or high Ni steel of the same strength level, significantly reducing the piston heat load.

[0187] The advantages of this invention are low cost and high efficiency: it does not contain expensive strategic elements such as Ni and W, and uses inexpensive Si (reduced amount), Mn and Cr with trace amounts of V to achieve high performance. The cost of raw materials is only slightly higher than that of ordinary 42CrMo and far lower than that of 4340 steel.

[0188] The present invention has high efficiency and high accuracy in the research and development of the optimal solution for the composition and preparation process of commercial vehicle piston steel: the closed-loop design method shortens the new material development cycle from 24 months to 3-6 months.

[0189] The room temperature mechanical properties of the commercial vehicle piston steel product obtained by the combined design and preparation methods of this invention are as follows: tensile strength of 1000-1250 MPa, yield strength of 900-1100 MPa, yield ratio of 0.85-0.92, elongation of 12-18%, product of strength and ductility of 15-22 GPa%, impact energy of 40-80 J, hardness of 35-42 HRC, and elastic modulus of 206-215 GPa; high temperature yield strength of 800-900 MPa at 500℃, elastic modulus of 170-190 GPa at 500℃, and thermal conductivity of 32-36 W / (m·K) at 500℃.

[0190] In summary, compared with traditional commercial vehicle piston steel preparation, the method of this invention obtains the optimal solution for its composition and the optimal solution for its preparation process through the design method of commercial vehicle piston steel, and then prepares it through the preparation method. This method is simple, accurate, efficient, and has a short cycle. The raw material cost is low. The commercial vehicle piston steel prepared has outstanding performance in terms of high temperature strength and thermal conductivity, which is conducive to large-scale industrial production and application.

[0191] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0192] In this invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be a single item or multiple items.

[0193] It should be understood that, in various embodiments of the present invention, the order of the above-mentioned process numbers does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0194] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A closed-loop design method for commercial vehicle piston steel, characterized in that, The closed-loop design method for commercial vehicle piston steel includes the following steps: S1. Construction of a high-dimensional thermophysical property database: Collect historical production data and thermodynamic calculation data of steel used in internal combustion engine pistons to construct a multidimensional dataset; S2. Attention mechanism feature encoding: Construct a deep neural network prediction model; calculate the covariance matrix between the features of each alloy element to capture the nonlinear interaction of trace elements in a low-silicon matrix and their influence on lattice distortion. S3. Dual-objective evolutionary optimization: Defining the objective function vector ,in The raw material cost function It is a comprehensive performance function that includes high-temperature strength and thermal conductivity; iterative search is performed within the low silicon content constraint space to output the optimal solution set; S4. Closed-loop iteration and decision-making: The inflection point identification method is used to select the optimal formula from the optimal solution set of S3, and small furnace smelting and performance testing are carried out. The measured data is fed back to the multidimensional dataset of S1 to trigger the online fine-tuning of the model.

2. The closed-loop design method for commercial vehicle piston steel according to claim 1, characterized in that, The input features of the multidimensional dataset in S1 include the mass fractions of C, Si, Mn, Cr, Mo, V, Ni, Al, S, and P, as well as the austenitizing temperature, tempering temperature, and cooling rate. Key output characteristics include room temperature mechanical properties, 500℃ high-temperature yield strength, and 500℃ thermal conductivity.

3. The closed-loop design method for commercial vehicle piston steel according to claim 1, characterized in that, The thermodynamic calculation data in S1 are thermodynamic Calphad data.

4. The closed-loop design method for commercial vehicle piston steel according to claim 1, characterized in that, The deep neural network prediction model in S2 is based on the Transformer architecture. Calculating the covariance matrix between the features of each alloy element requires the use of a Multi-Head Self-Attention mechanism.

5. The closed-loop design method for commercial vehicle piston steel according to claim 4, characterized in that, The Multi-HeadSelf-Attention mechanism in S2 contains h = 4-8 attention heads. The formula for calculating the attention weight matrix of the i-th head is: in, These are query, key, and value matrices, respectively. The scaling factor is used; the model analyzes the weighted relationships between V and Mo, and Si and thermal conductivity through heat maps to guide the optimization direction.

6. The closed-loop design method for commercial vehicle piston steel according to claim 1, characterized in that, The iterative search in the low silicon content constraint space of S3 is performed using NSGA-II in the low silicon content constraint space of Si≤0.35%, and the output optimal solution set is the Pareto Front optimal solution set.

7. The closed-loop design method for commercial vehicle piston steel according to claim 1, characterized in that, S3 Comprehensive performance function Set as: in Yield strength at 500℃ Thermal conductivity at 500℃ , The weighting factor is used; a penalty term is applied when the predicted thermal conductivity is below 32 W / (m·K). This forces the population to converge toward regions with high thermal conductivity.

8. The closed-loop design method for commercial vehicle piston steel according to claim 1, characterized in that, In S4, the inflection point identification method was used to select the optimal chemical composition weight percentage from the Pareto Front optimal solution set of S3 as follows: C 0.38-0.45%, Si 0.15-0.35%, Mn 0.70-1.10%, Cr 1.00-1.30%, Mo 0.20-0.40%, V 0.08-0.15%, P≤0.015%, S≤0.015%, Al 0.015-0.035%, with the balance being Fe and unavoidable impurities; The microstructure of the commercial vehicle piston steel is tempered sorbite, with the original austenite grain size ≥ 8; the matrix contains dispersed MC-type and M-type VC with a size ≤ 20 nm. 23 C6 type nano carbides; the commercial vehicle piston steel has a high-temperature yield strength of ≥800MPa at 500℃ in the quenched and tempered state, and a thermal conductivity of ≥32W / (m·K) at 500℃.

9. A method for preparing piston steel based on the closed-loop design method for commercial vehicle piston steel according to claim 1, characterized in that, The piston steel preparation method is the same as the method in S4 that uses the inflection point identification method to select the optimal formula from the Pareto Front optimal solution set in S3, and it includes the following steps: Step 1, Smelting: Electric furnace / converter + LF refining + VD vacuum treatment, after VD breaks the vacuum, feed V-Fe, Mo-Fe and Ca-Si wires to smelt and obtain piston steel ingots; Step 2, Forging: Heat the piston steel ingot from Step 1 to the homogenization temperature and hold it thereafter, then begin forging. After forging, perform stacking cooling to obtain piston steel forgings. Step 3, Preliminary heat treatment: The piston steel forging billet from Step 2 is normalized to obtain normalized piston steel forgings; Step 4, tempering: The piston steel normalized forgings from Step 3 are oil quenched and then tempered at high temperature to finally obtain the finished commercial vehicle piston steel.

10. The piston steel preparation method of the closed-loop design method for commercial vehicle piston steel according to claim 9, characterized in that, The room temperature mechanical properties of the commercial vehicle piston steel finished product in step 4 are as follows: tensile strength 1000-1250MPa, yield strength 900-1100MPa, yield ratio 0.85-0.92, elongation 12-18%, strength-ductility product 15-22GPa%, impact energy 40-80J, hardness 35-42HRC, and elastic modulus 206-215GPa; high temperature yield strength at 500℃ is 800-900MPa, elastic modulus at 500℃ is 170-190GPa, and thermal conductivity at 500℃ is 32-36W / (m·K).

Images