Homogeneous isomeric low-alloy high-strength steel structural arc additive manufacturing process

Abstract

The application discloses a kind of isomeric low-alloy high-strength steel structure arc additive process, it is related to the technical field of arc additive manufacturing, including low-alloy high-strength steel wire material is treated and tensile test is carried out to obtain test data, process parameter-performance prediction model is established according to the test data;The performance requirement of target structure is obtained, and the process parameter is formulated using process parameter-performance prediction model according to the performance requirement;Low-alloy high-strength steel wire material is carried out arc additive using arc additive manufacturing system, and low-alloy high-strength steel structure is obtained;The temperature information of the low-alloy high-strength steel structure is obtained using infrared thermal imager, and the process parameter is adjusted in real time according to temperature information, and target structure is obtained;Realize the gradient distribution of precipitation strengthening phase, and realize the isomorphism of alloy element in-situ strengthening low-alloy high-strength steel material, satisfy the diversification demand of different strength and plasticity of target structure.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electric arc additive manufacturing, and in particular to an isomeric low-alloy high-strength steel structure electric arc additive manufacturing process. BACKGROUND

[0002] In recent years, high-strength steel has been widely used in weapons, ships, energy and many other fields due to its high strength characteristics, and has become one of the new types of engineering materials that are currently developing rapidly. However, traditional ultra-high strength steel usually adds a large amount of expensive alloy elements such as Co and Ni. For example, 18Ni maraging steel and Ni-Co system secondary hardening ultra-high strength steel, the widespread use of such expensive materials is severely restricted by cost, and cannot meet the needs of commercial and mass production. Therefore, developing low-cost and high-performance high-strength steel has become a research hotspot in this field. Electric arc additive manufacturing technology, as a new manufacturing process, can well solve the problems of traditional manufacturing methods in manufacturing complex structural parts. Compared with other additive manufacturing technologies, electric arc additive manufacturing technology has the characteristics of high deposition efficiency, low cost and simple process, and has been widely used in related fields.

[0003] At present, the Chinese invention with the publication number CN112287489B discloses an electric arc wire additive manufacturing process parameter determination method based on multi-physical field simulation, which can determine the target process parameters corresponding to the target shaped part and improve the manufacturing precision, but cannot realize the gradient distribution of precipitated strengthening phases, and cannot meet the diversified needs of structural parts for different strengths and plastic shapes. SUMMARY

[0004] The technical problem solved by the present application is that the existing technology cannot realize the gradient distribution of precipitated strengthening phases, and cannot meet the diversified needs of structural parts for different strengths and plastic shapes.

[0005] To solve the above technical problems, in a first aspect, the present application provides an isomeric low-alloy high-strength steel structure electric arc additive manufacturing process, comprising the following steps:

[0006] Step S1, heat treating and tensile testing the low-alloy high-strength steel wire to obtain test data of the low-alloy high-strength steel wire, and establishing a process parameter-performance prediction model according to the test data;

[0007] Step S2, obtaining the performance requirements of the target structure, and formulating process parameters using the process parameter-performance prediction model according to the performance requirements;

[0008] Step S3, using an electric arc additive manufacturing system to perform electric arc additive manufacturing on the low-alloy high-strength steel wire to obtain a low-alloy high-strength steel structure;

[0009] Step S4, acquiring temperature information of the low-alloy high-strength steel structure by using an infrared thermal imager, and adjusting the process parameters in real time according to the temperature information to obtain a target structure;

[0010] As a preferred scheme of the isomeric low-alloy high-strength steel structure arc additive manufacturing process, wherein:

[0011] The step S1 specifically comprises the following steps:

[0012] Step S101, performing three normalizing and m times of air cooling on the low-alloy high-strength steel wire reinforced in-situ by alloying elements, wherein m is a natural number greater than 1, to obtain a first low-alloy high-strength steel, setting gradient tempering parameters for the first low-alloy high-strength steel, and performing a tempering operation on the first low-alloy high-strength steel according to the gradient tempering parameters to obtain a second low-alloy high-strength steel, the gradient tempering parameters including gradient tempering temperature and gradient tempering time;

[0013] Step S102, performing TEM analysis on the second low-alloy high-strength steel by using a transmission electron microscope to obtain precipitation phase information, performing a tensile test on the second low-alloy high-strength steel to obtain tensile property information of the second low-alloy high-strength steel, and obtaining a one-to-one mapping relationship between the precipitation phase information, the tensile property information and the gradient tempering parameters, the precipitation phase information including precipitation phase density, precipitation phase size and precipitation phase misfit, and the tensile property information including elastic limit, elongation, elastic modulus, proportional limit, area reduction, tensile strength, yield point and yield strength;

[0014] Step S103, adjusting the gradient tempering parameters and repeating steps S101-S102 to obtain n sets of test data, wherein n is a natural number, storing the test data into a database, setting corresponding process parameters according to the gradient tempering parameters to establish a process library of low-alloy high-strength steel, extracting the tensile property information in the database as input and extracting the gradient tempering parameters in the database as output, training a machine learning model by using a support vector machine algorithm and a genetic algorithm until the model fitting degree is greater than or equal to a first expected threshold, and then obtaining a process parameter-performance prediction model;

[0015] As a preferred scheme of the isomeric low-alloy high-strength steel structure arc additive manufacturing process, wherein:

[0016] The step S2 specifically comprises the following steps:

[0017] Obtaining performance requirements of a target structural member, inputting the performance requirements into a process parameter-performance prediction model, obtaining a target gradient tempering parameter of the structural member, inputting the target gradient tempering parameter into a process library to obtain a first process parameter, the process parameter including an interlayer cooling speed, a printing strategy and an externally applied preheating substrate temperature;

[0018] As a preferred scheme of the isomeric low-alloy high-strength steel structure electric arc additive manufacturing process, in the process, the process parameter-performance prediction model is obtained by using the support vector machine algorithm and the genetic algorithm.

[0019] The step S4 specifically includes the following steps:

[0020] According to the first process parameter, the low-alloy high-strength steel wire is subjected to electric arc additive manufacturing to obtain a target low-alloy high-strength steel structural member, and an infrared thermal imager is used to obtain an infrared radiation energy distribution map of the target low-alloy high-strength steel structural member in real time, and the temperature information of the target low-alloy high-strength steel structural member is obtained through the infrared radiation energy distribution map, the temperature information is input into the process library to obtain a second process parameter, and the electric arc additive manufacturing is performed through the second process parameter.

[0021] As a preferred scheme of the isomeric low-alloy high-strength steel structure electric arc additive manufacturing process, in the process, the process parameter-performance prediction model is obtained by using the support vector machine algorithm and the genetic algorithm.

[0022] The process parameter-performance prediction model is obtained by using the support vector machine algorithm and the genetic algorithm, and includes the following steps:

[0023] The gradient tempering parameters and corresponding tensile property information in the test data are extracted and merged as a sample training set, the sample training set is divided into a training set and a test set according to a certain proportion, the kernel function type, the kernel parameter and the penalty factor of the support vector machine are encoded by using a binary encoding method, an initial population is randomly generated according to the sample training set, the support vector machine algorithm is used to perform regression prediction according to the sample training set, the tensile property information is used as the prediction input, and the gradient tempering parameter is used as the prediction output, the mean square error formula is used to obtain the fitness value of each initial population, the genetic operator operations of selection, crossover and mutation are performed on the initial population to generate a next generation population, and the process is repeated until the fitness value of the next generation population is greater than or equal to a second expected threshold value, and then the optimal kernel parameter is output, and the primary process parameter-performance prediction model is established by using the optimal kernel parameter, the test set is input into the primary process parameter-performance prediction model for testing, the model fitting degree is obtained, if the model fitting degree is greater than or equal to a first expected threshold value, the process parameter-performance prediction model is obtained, and if the model fitting degree is less than the first expected threshold value, the model parameters are adjusted.

[0024] As a preferred scheme of the isomeric low-alloy high-strength steel structure electric arc additive manufacturing process, in the process, the process parameter-performance prediction model is obtained by using the support vector machine algorithm and the genetic algorithm.

[0025] The mathematical expression of the mean square error formula is as follows:

[0026] ,

[0027] Wherein, E is the fitness value, n is the population number, is the actual value, is the predicted value;

[0028] As a preferred scheme of the isomorphic low alloy high strength steel structure arc additive manufacturing process of the application, wherein:

[0029] The test data includes gradient tempering parameters, precipitated phase information and tensile property information;

[0030] The temperature information includes the temperature of each position of the target low alloy high strength steel structure;

[0031] As a preferred scheme of the isomorphic low alloy high strength steel structure arc additive manufacturing process of the application, wherein:

[0032] The arc additive manufacturing system includes a digital control system, a wire feeder, a welding robot, an arc welding power supply, a welding torch, a workbench, a clamp, an infrared thermal imager and a computer.

[0033] In a second aspect, the application provides an electronic device, comprising: a processor and a memory, wherein:

[0034] The memory stores a computer program that can be called by the processor;

[0035] The processor executes the isomorphic low alloy high strength steel structure arc additive manufacturing process of any one of the above by calling the computer program stored in the memory.

[0036] In a third aspect, the application provides a computer readable storage medium, which stores a computer program, wherein the program is executed by a processor to realize the isomorphic low alloy high strength steel structure arc additive manufacturing process of any one of the above.

[0037] The beneficial effects of the present application are as follows: the present application obtains gradient tempering parameters, tensile property information and precipitated phase information of low-alloy high-strength steel wire by heat treatment and tensile test on low-alloy high-strength steel additive, establishes a first mapping relationship according to the gradient tempering parameters, tensile property information and precipitated phase information, establishes a process parameter-performance prediction model according to the tensile property information and gradient tempering parameters by using a vector machine algorithm and a genetic algorithm, and obtains target gradient tempering parameters for arc additive manufacturing according to the performance requirements of the target structure, thereby improving the arc additive manufacturing precision, adjusting the process parameters in real time during the arc additive manufacturing process, regulating the thermal history of different positions of the structure by using the forming characteristics of the arc additive manufacturing, realizing the gradient distribution of the precipitated strengthening phase, and realizing the homeomorphism of the alloy element in-situ strengthening low-alloy high-strength steel material, and meeting the diversified requirements of the target structure on different strengths and plasticities. BRIEF DESCRIPTION OF DRAWINGS

[0038] Figure 1 A basic flowchart of a homomorphism low-alloy high-strength steel structure arc additive manufacturing process is provided for an embodiment of the present application.

[0039] Figure 2 A tensile strength change trend of a homomorphism low-alloy high-strength steel structure is provided for an embodiment of the present application.

[0040] Figure 3 An elongation change trend of a homomorphism low-alloy high-strength steel structure is provided for an embodiment of the present application.

[0041] Figure 4 Performance test results of a target structure of a homomorphism low-alloy high-strength steel are provided for an embodiment of the present application. DETAILED DESCRIPTION

[0042] In order to make the above-mentioned objects, features and advantages of the present application more apparent and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments.

[0043] Embodiment 1, refer to Figures 1-4 For an embodiment of the present application, a homomorphism low-alloy high-strength steel structure arc additive manufacturing process is provided, which includes the following steps:

[0044] Step S1, heat treatment and tensile test are performed on low-alloy high-strength steel wire to obtain test data of the low-alloy high-strength steel wire, and a process parameter-performance prediction model is established according to the test data;

[0045] Step S2, obtaining the performance requirement of the target structure, and determining the process parameters according to the performance requirement and the process parameter-performance prediction model;

[0046] Step S3, using the electric arc additive manufacturing system to perform electric arc additive manufacturing on the low-alloy high-strength steel wire, and obtaining the low-alloy high-strength steel structure;

[0047] Step S4, obtaining the temperature information of the low-alloy high-strength steel structure by using an infrared thermal imager, and adjusting the process parameters in real time according to the temperature information to obtain the target structure.

[0048] In this embodiment, the gradient tempering parameters, tensile performance information and precipitated phase information of the low-alloy high-strength steel wire are obtained by heat treatment and tensile test on the low-alloy high-strength steel wire, the first mapping relationship is established according to the gradient tempering parameters, tensile performance information and precipitated phase information, the process parameter-performance prediction model is established by using vector machine algorithm and genetic algorithm according to the tensile performance information and gradient tempering parameters, and the target gradient tempering parameters are obtained by using the process parameter-performance prediction model according to the performance requirement of the target structure to perform electric arc additive manufacturing, which improves the electric arc additive manufacturing precision, adjusts the process parameters in real time during the electric arc additive manufacturing process, utilizes the forming characteristics of the electric arc additive manufacturing, controls the thermal history of different positions of the structure, realizes the gradient distribution of the precipitated strengthening phase, realizes the homeomorphism of the alloy element in-situ strengthened low-alloy high-strength steel material, and meets the diversified requirements of the target structure on different strengths and plasticities.

[0049] In one embodiment, the temperature is divided by gradient, and the process parameters at different temperatures are recorded, the temperature information is one-to-one mapped with the process parameters, and the following table is the mapping relationship table of the electric arc additive manufacturing process parameters;

[0050] Region Heat input (kJ / mm) Temperature information (°C) Target tissue Bottom 1.2-1.5 300-400 High density nano-VC precipitation Middle 0.8-1.2 200-300 Mixed precipitation + dislocation strengthening Top 0.5-0.8 <200 Fine-grained matrix dominated

[0051] Step S1 specifically includes the following steps:

[0052] Step S101, performing three normalizing and m times air cooling on the low-alloy high-strength steel wire strengthened in-situ by alloy elements, wherein m is a natural number greater than 1, obtaining a first low-alloy high-strength steel, setting gradient tempering parameters for the first low-alloy high-strength steel, and performing tempering operation on the first low-alloy high-strength steel according to the gradient tempering parameters to obtain a second low-alloy high-strength steel, the gradient tempering parameters including gradient tempering temperature and gradient tempering time;

[0053] In step S102, TEM analysis is performed on the second low-alloy high-strength steel using a transmission electron microscope to obtain information about precipitated phases, a tensile test is performed on the second low-alloy high-strength steel to obtain tensile property information of the second low-alloy high-strength steel, and a first mapping relationship is obtained by one-to-one correspondence between the information about precipitated phases, the tensile property information, and the gradient tempering parameters. The information about precipitated phases includes precipitated phase density, precipitated phase size, and precipitated phase misfit, and the tensile property information includes elastic limit, elongation, elastic modulus, proportional limit, area reduction, tensile strength, yield point, and yield strength.

[0054] In step S103, the gradient tempering parameters are adjusted, and steps S101-S102 are repeated to obtain n sets of test data, where n is a natural number. The test data is stored in a database, and a process library of low-alloy high-strength steel is established according to the gradient tempering parameters to set corresponding process parameters. The tensile property information in the database is extracted as input, and the gradient tempering parameters in the database are extracted as output. A machine learning model is trained using a support vector machine algorithm and a genetic algorithm until the model fitting degree is greater than or equal to a first expected threshold, and then a process parameter-performance prediction model is obtained.

[0055] In this embodiment, strong carbide forming elements such as V, Ti, and Nb are selected as in-situ strengthening phases, and the precipitated phase misfit is controlled to be 0.03%-0.5%. The composition range of C is 0.1%-0.3%, the composition range of V is 0.2%-1.5%, the composition range of Ti is 0.05%-0.3%, and the remaining content is Fe, trace amounts of Al, and trace amounts of Mo.

[0056] In this embodiment, the gradient tempering temperature is 100°C, and every 5 degrees Celsius is used as a gradient tempering temperature until the gradient tempering temperature reaches 300°C. The gradient tempering time is 0.5 hours, and every 0.5 hours is used as a gradient tempering time until 6 hours is reached.

[0057] In this embodiment, the precipitated phase density is , the precipitated phase size is 2-20 nm, and the precipitated phase misfit is 0.03%-0.5%.

[0058] In this embodiment, TEM analysis is a high-resolution electron microscope technique mainly used for observing the microstructure and composition of materials.

[0059] In this embodiment, the support vector machine algorithm is a machine learning algorithm that performs binary classification of data in a supervised learning manner.

[0060] In this embodiment, the genetic algorithm is a computational model that simulates the natural selection and genetic mechanisms of Darwin's biological evolution process, and is a method of searching for the optimal solution by simulating the natural evolution process.

[0061] In this embodiment, setting the process parameters according to the gradient tempering parameters includes:

[0062] The heat input is calculated by the heat formula, and the welding current (150-300 A) and the walking speed (5-15 mm / s) are adjusted in real time. The mathematical expression of the heat formula is as follows:

[0063] ,

[0064] Where Q is the heat input, U is the welding voltage, I is the welding current, v is the walking speed, and η ranges from 0.8 to 0.85.

[0065] A double pulse waveform is used, with a base current of 80-120 A to maintain the stability of the molten pool and a peak current of 200-350 A to control the penetration depth.

[0066] After each layer is deposited, a delay of 5-10 seconds is applied, and the temperature field is scanned by a FLIR A65 infrared camera (accuracy ±2℃) to extract the lowest point temperature as the control reference.

[0067] Adaptive cooling strategy:

[0068] When the actual temperature is greater than the set temperature, start compressed air cooling (flow rate 10-20 m³ / h)

[0069] When the actual temperature is less than the set temperature, enable local induction heating (frequency 50 kHz, power 3-5 kW).

[0070] In this embodiment, the first expected threshold is 95%.

[0071] In this embodiment, the low-alloy high-strength steel wire material is subjected to heat treatment and tensile test to obtain gradient tempering parameters, tensile performance information and precipitated phase information, and a process parameter-performance prediction model is established according to the tensile performance information and the gradient tempering parameters using a vector machine algorithm and a genetic algorithm, which provides accurate and reliable model support and process library support for obtaining target gradient tempering parameters and process parameters according to the performance requirements of target structural parts and realizing the gradient distribution of precipitated strengthening phases.

[0072] Step S2 specifically includes the following steps:

[0073] Obtain the performance requirements of the target structural part, input the performance requirements into the process parameter-performance prediction model, obtain the target gradient tempering parameters of the structural part, input the target gradient tempering parameters into the process library to obtain the first process parameters, and the process parameters include interlayer cooling speed, printing strategy and external preheating substrate temperature.

[0074] In the embodiment, the first process parameter is obtained according to the performance requirement of the target structure by using the process parameter-performance prediction model and the process library, which provides detailed and accurate process parameters for realizing the allotropy of the low-alloy high-strength steel material and meeting the diversified requirements of the target structure on different strengths and plasticities.

[0075] The step S4 specifically comprises the following steps:

[0076] The low-alloy high-strength steel wire is subjected to arc additive manufacturing according to the first process parameter to obtain the target low-alloy high-strength steel structure, and the infrared thermal imager is used to obtain the infrared radiation energy distribution map of the target low-alloy high-strength steel structure in real time, and the temperature information of the target low-alloy high-strength steel structure is obtained through the infrared radiation energy distribution map, the temperature information is input into the process library to obtain the second process parameter, and the arc additive manufacturing is performed through the second process parameter.

[0077] In the embodiment, the temperature information of the target low-alloy high-strength steel structure is detected in real time by using the infrared thermal imager, and the second process parameter is adjusted in real time according to the temperature information by using the process library, which guarantees the accuracy of the process of manufacturing the target structure and ensures the quality of the target structure on the basis of meeting the requirements of the target structure on multiple strengths and plasticities.

[0078] The process parameter-performance prediction model is obtained by using the support vector machine algorithm and the genetic algorithm, which comprises:

[0079] The gradient tempering parameters and the corresponding tensile property information in the test data are extracted and merged as a sample training set, the sample training set is divided into a training set and a test set according to a certain proportion, the kernel function type, the kernel parameter and the penalty factor of the support vector machine are encoded by using a binary coding mode, an initial population is randomly generated according to the sample training set, the support vector machine algorithm is used to perform regression prediction according to the sample training set, the tensile property information is used as the prediction input, and the gradient tempering parameter is used as the prediction output, the mean square error formula is used to obtain the fitness value of each initial population, the genetic operator operations of selection, crossover and mutation are performed on the initial population to generate a next generation population, and the process is repeated until the fitness value of the next generation population is greater than or equal to a second expected threshold value, then the optimal kernel parameter is output, and the primary process parameter-performance prediction model is established by using the optimal kernel parameter, the test set is input into the primary process parameter-performance prediction model for testing, the model fitting degree is obtained, if the model fitting degree is greater than or equal to a first expected threshold value, the process parameter-performance prediction model is obtained, and if the model fitting degree is less than the first expected threshold value, the model parameter is adjusted.

[0080] In this embodiment, the process parameter-performance prediction model is obtained by using the support vector machine algorithm and the genetic algorithm, the target gradient tempering parameter and the process parameter are obtained according to the performance requirement of the target structure, and the gradient distribution of the precipitated strengthening phase is realized to provide accurate and reliable model support.

[0081] The mathematical expression of the mean square error formula is as follows:

[0082] ,

[0083] Wherein, E is the fitness value, n is the population number, is the actual value, is the predicted value.

[0084] In this embodiment, the fitness value of each initial population is obtained by using the mean square error formula, which provides the optimal kernel parameter for establishing the process parameter-performance prediction model and guarantees the accuracy of the model parameters.

[0085] The test data includes gradient tempering parameters, precipitated phase information and tensile property information;

[0086] The temperature information includes the temperature of each position of the target low-alloy high-strength steel structure.

[0087] In embodiment 2, an electric arc additive manufacturing system includes a digital control system, a wire feeder, a welding robot, an arc welding power source, a welding torch, a workbench, a clamp, an infrared thermal imager and a computer.

[0088] In this embodiment, the performance test is performed on the target structure obtained after the electric arc additive manufacturing, and the test results show that the bottom of the target structure and the top of the target structure both meet the performance requirements.

[0089] In this embodiment, the electric arc additive manufacturing system is used to perform additive manufacturing according to the process parameters, the wire feeding speed of the wire feeder, the motion path and speed of the welding robot and the output parameters of the arc welding power source are accurately controlled to ensure the stable combustion of the electric arc and the uniform melting and deposition of the wire material. At the same time, the welding robot performs layer-by-layer accumulation according to the preset path to ensure the accurate generation of the target structure.

[0090] In the embodiment, the gradient tempering parameters, tensile property information and precipitated phase information of the low-alloy high-strength steel wire are obtained by heat treatment and tensile test on the low-alloy high-strength steel wire, the first mapping relationship is established according to the tensile property information and the precipitated phase information, the process parameter-performance prediction model is established by using the vector machine algorithm and the genetic algorithm according to the tensile property information and the gradient tempering parameters, and the target gradient tempering parameters are obtained according to the performance requirements of the target structure and the first mapping relationship and the process parameter-performance prediction model to perform the electric arc additive manufacturing, thereby improving the electric arc additive manufacturing precision, adjusting the process parameters in real time during the electric arc additive manufacturing, regulating the thermal history of different positions of the structure by using the forming characteristics of the electric arc additive manufacturing, realizing the gradient distribution of the precipitated strengthening phase, and realizing the homeomorphism of the in-situ strengthening of the low-alloy high-strength steel material by the alloying elements, thereby meeting the diversified requirements of the target structure on different strengths and plasticities.

[0091] Those skilled in the art will 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 take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media having computer-usable program code embodied in the medium. The storage media can be realized by any type of volatile or non-volatile storage devices or a combination thereof, such as static random access memory, electrically erasable programmable read-only memory, erasable programmable read-only memory, programmable read-only memory, read-only memory, magnetic storage, flash memory, magnetic disk or optical disk. These computer program instructions can also be stored in a computer readable storage medium that can guide the computer or other programmable data processing device to work in a specific way, so that the instructions stored in the computer readable storage medium produce the products including the instruction device, which realize the processes specified in the flow Figure 1 one or more flows and / or blocks Figure 1 one or more flows and / or blocks

[0092] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and not to limit the present application. Although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present application, which should be covered in the scope of the claims of the present application.

Claims

1. An arc additive process for isomeric low-alloy high-strength steel structures, characterized in that: The following steps are involved: Step S1, performing heat treatment and tensile testing on a low-alloy high-strength steel wire to obtain test data of the low-alloy high-strength steel wire, and establishing a process parameter-performance prediction model based on the test data; Step S2, obtaining the performance requirements of the target structural part, and formulating process parameters based on the performance requirements using a process parameter-performance prediction model; Step S3, performing arc additive manufacturing on the low-alloy high-strength steel wire using an arc additive manufacturing system to obtain a low-alloy high-strength steel structural component; Step S4, using an infrared thermal imager to obtain temperature information of the low-alloy high-strength steel structural component, and adjusting the process parameters in real time according to the temperature information to obtain a target structural component; The step S1 specifically includes the following steps: Step S101, normalizing three times and air cooling m times on a low-alloy high-strength steel wire material in-situ strengthened by alloying elements, where m is a natural number greater than 1, obtaining a first low-alloy high-strength steel, setting gradient tempering parameters for the first low-alloy high-strength steel, and tempering the first low-alloy high-strength steel according to the gradient tempering parameters, to obtain a second low-alloy high-strength steel; the gradient tempering parameters including gradient tempering temperature and gradient tempering time; Step S102: performing TEM analysis on the second low-alloy high-strength steel using a transmission electron microscope to obtain precipitate phase information, performing a tensile test on the second low-alloy high-strength steel to obtain tensile property information of the second low-alloy high-strength steel, and performing a one-to-one correspondence between the precipitate phase information, the tensile property information, and the gradient tempering parameter to obtain a first mapping relationship, wherein the precipitate phase information includes precipitate phase density, precipitate phase size, and precipitate phase mismatch, and the tensile property information includes elastic limit, elongation, elastic modulus, proportional limit, area reduction, tensile strength, yield point, and yield strength. The TEM analysis is a high-resolution electron microscope technique primarily used to observe the microstructure and composition of a material; Step S103: Adjust the gradient tempering parameters and repeat steps S101 to S102 to obtain n sets of test data, where n is a natural number. The test data is stored in a database, and corresponding process parameters are set according to the gradient tempering parameters to establish a process library for low-alloy high-strength steel. Tensile property information in the database is extracted as input, and gradient tempering parameters in the database are extracted as output. A machine learning model is trained using a support vector machine algorithm and a genetic algorithm until the model fit is greater than or equal to a first expected threshold, thereby obtaining a process parameter-performance prediction model. The step S4 specifically includes the following steps: Performing arc additive manufacturing on a low-alloy high-strength steel wire according to first process parameters to obtain a target low-alloy high-strength steel structural component, and using an infrared thermal imager to obtain an infrared radiation energy distribution map of the target low-alloy high-strength steel structural component in real time, obtaining temperature information of the target low-alloy high-strength steel structural component based on the infrared radiation energy distribution map, inputting the temperature information into a process library to obtain second process parameters, and performing arc additive manufacturing based on the second process parameters; The process parameter-performance prediction model obtained by using support vector machine algorithm and genetic algorithm includes: The gradient tempering parameters and corresponding tensile property information in the test data are extracted and merged into a sample training set. The sample training set is divided into a training set and a test set according to a certain ratio. The kernel function type, kernel parameters and penalty factor of the support vector machine are encoded using a binary coding method. An initial population is randomly generated based on the sample training set. Regression prediction is performed based on the sample training set using a support vector machine algorithm, with the tensile property information as the prediction input and the gradient tempering parameters as the prediction output. The fitness value of each initial population is obtained using a mean square error formula. The initial population is subjected to genetic operator operations of selection, crossover and mutation to generate a next generation population. When the fitness value of the next generation population is greater than or equal to a second expected threshold, the optimal kernel parameters are output. A primary process parameter-performance prediction model is established using the optimal kernel parameters. The test set is input into the primary process parameter-performance prediction model for testing to obtain model fit. If the model fit is greater than or equal to the first expected threshold, a process parameter-performance prediction model is obtained. If the model fit is less than the first expected threshold, the model parameters are adjusted.

2. The arc additive process for isomeric low-alloy high-strength steel structures according to claim 1, characterized in that: The step S2 specifically includes the following steps: The performance requirements of the target structural part are obtained, the performance requirements are input into a process parameter-performance prediction model, the target gradient tempering parameters of the structural part are obtained, and the target gradient tempering parameters are input into a process library to obtain first process parameters, wherein the process parameters include an interlayer cooling rate, a printing strategy, and an external preheating substrate temperature.

3. The arc additive process for isomeric low-alloy high-strength steel structures according to claim 1, characterized in that: The mathematical expression of the mean square error formula is as follows: ， Among them, E is the fitness value, n is the population size, is the actual value, is the predicted value.

4. The arc additive process for isomeric low-alloy high-strength steel structures according to claim 1, characterized in that: The test data includes gradient tempering parameters, precipitation phase information and tensile property information; The temperature information includes the temperature of each position of the target low-alloy high-strength steel structural part.

5. The arc additive process for isomeric low-alloy high-strength steel structure according to claim 1, characterized in that: The arc additive manufacturing system includes a digital control system, a wire feeder, a welding robot, an arc welding power source, a welding gun, a workbench, a fixture, an infrared thermal imager and a computer.

6. An electronic device, characterized in that: include: A processor and a memory, wherein: The memory stores a computer program that can be called by the processor; The processor executes the arc additive process for isomorphous low-alloy high-strength steel structures according to any one of claims 1 to 4 in the background by calling the computer program stored in the memory.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, an arc additive process for isomorphous low-alloy high-strength steel structures as described in any one of claims 1 to 4 is implemented.

Images