Method, device, equipment and product for determining the tendency of weld porosity

Abstract

The present invention provides a method, device, equipment and product for distinguishing the tendency of weld porosity generation, the method comprising: obtaining preset welding parameters in the welding process; inputting the preset welding parameters into a molten pool mimicry model, and outputting the porosity generation tendency value corresponding to the preset welding parameters, wherein the molten pool mimicry model is obtained based on molten pool mimicry sample training; determining that the porosity generation tendency value meets the preset porosity generation threshold, then determining that the preset welding parameters meet the welding requirements; determining that the porosity generation tendency value does not meet the preset porosity generation threshold, then discarding the preset welding parameters. The present invention numerically simulates the porosity generation tendency of the fusion welding process, reproduces the welding process by means of computational fluid dynamics numerical simulation, fully considers the physical mechanism of porosity generation, establishes a cavitation potential model to determine the tendency of porosity generation, and then achieves guidance on the welding process.

Description

Technical Field

[0001] The present invention relates to the field of welding technology, and in particular to a method, device, equipment and product for determining the tendency of weld porosity generation. Background Art

[0002] Porosity is one of the common defects in fusion welding. There are two types of pores in the weld: "metallurgical type" and "process type". In the current numerical simulation research on pores, most of the research focuses on process pores in high-energy beam welding such as laser and electron beam. It is believed that process pores are related to the instability of the keyhole in high-energy beam welding. The instability of the keyhole leads to the collapse of the keyhole, and closed bubbles are formed in the molten pool. Some bubbles fail to escape from the molten pool when the molten pool solidifies, thus forming process pores. However, there is still a lack of research and evaluation on metallurgical pores. Summary of the invention

[0003] The present invention provides a method for determining the tendency of weld pores to be generated, so as to solve the defects in the prior art that metallurgical pores have a great influence on the service performance of fusion welding joints, are difficult to measure and detect, and currently lack a reliable and effective evaluation method. By numerically simulating the tendency of pores to be generated in the fusion welding process, the welding process is reproduced by means of computational fluid dynamics numerical simulation, the physical mechanism of pore generation is fully considered, and a cavitation potential model is established to determine the tendency of pores to be generated, thereby achieving guidance on the welding process.

[0004] The invention also provides a device for determining the tendency of weld porosity generation.

[0005] The present invention further provides an electronic device.

[0006] The present invention further provides a computer program product.

[0007] According to a first aspect of the present invention, a method for determining a tendency of weld porosity generation is provided, comprising:

[0008] Obtaining preset welding parameters during welding;

[0009] Inputting the preset welding parameters into a molten pool mimicry model, and outputting a porosity generation tendency value corresponding to the preset welding parameters, wherein the molten pool mimicry model is obtained based on molten pool mimicry sample training;

[0010] Determining that the pore generation tendency value meets a preset pore generation threshold value, then determining that the preset welding parameters meet the welding requirements;

[0011] If it is determined that the pore generation tendency value does not meet the preset pore generation threshold, the preset welding parameters are discarded.

[0012] It should be noted that by obtaining the preset welding parameters in the welding process and inputting them into the molten pool simulation model, the pore generation tendency value corresponding to the preset welding parameters can be obtained. By judging through the obtained pore generation tendency value, it can be known whether the preset welding parameters will cause pores to be generated in the molten pool, and whether the preset welding parameters need to be optimized.

[0013] According to an embodiment of the present invention, the step of inputting the preset welding parameters into the molten pool simulation model and outputting the porosity generation tendency value corresponding to the preset welding parameters specifically includes:

[0014] Obtaining characteristic values ​​of the preset welding parameters;

[0015] Extracting a first eigenvector of the eigenvalue, wherein the first eigenvector points to a starting point of a sampling period;

[0016] Inputting the first characteristic vector into the molten pool mimicry model, and outputting the corresponding instant pore tendency parameter;

[0017] The pore generation tendency value is generated according to the instant pore tendency parameter.

[0018] Specifically, this embodiment provides an implementation method for outputting the pore generation tendency value corresponding to the preset welding parameters. By extracting the first eigenvector in the eigenvalue, the pore generation tendency at any time is obtained, that is, the instantaneous pore generation tendency at the time corresponding to the first eigenvector is obtained.

[0019] It should be noted that the problem of difficulty in real-time monitoring of pore formation during melting welding is overcome through numerical simulation based on heat-fluid coupling. The cavitation potential model is established considering the physical mechanism of pore generation, so as to achieve effective evaluation of the immediate pore generation tendency.

[0020] According to an embodiment of the present invention, the step of inputting the preset welding parameters into the molten pool simulation model and outputting the porosity generation tendency value corresponding to the preset welding parameters specifically includes:

[0021] Obtaining characteristic values ​​of the preset welding parameters;

[0022] Extracting a first eigenvector and a second eigenvector of the eigenvalue, wherein the first eigenvector points to a starting point of a sampling period, and the second eigenvector points to an ending point of the sampling period;

[0023] Inputting the first eigenvector and the second eigenvector into the molten pool mimicry model, and outputting corresponding cumulative pore tendency parameters;

[0024] The pore generation tendency value is generated according to the accumulated pore tendency parameter.

[0025] Specifically, this embodiment provides another implementation method for outputting the pore generation tendency value corresponding to the preset welding parameters. By extracting the first eigenvector and the second eigenvector in the eigenvalue, the accumulation of the pore generation tendency between the starting point and the end point of the sampling period is obtained, that is, the cumulative parameters of the pore generation tendency between the first eigenvector and the second eigenvector are obtained.

[0026] It should be noted that the problem of difficulty in real-time monitoring of pore formation during melting welding is overcome through numerical simulation based on heat-fluid coupling. The cavitation potential model is established considering the physical mechanism of pore generation, so as to effectively evaluate the tendency of cumulative pore generation.

[0027] According to an embodiment of the present invention, the step of obtaining preset welding parameters in the welding process specifically includes:

[0028] Acquiring temperature field characteristics, flow field characteristics, material characteristics and welding process characteristics of the molten pool during the welding process;

[0029] The preset welding parameters are generated according to the temperature field characteristics, the flow field characteristics, the material characteristics and the welding process characteristics.

[0030] Specifically, this embodiment provides an implementation method for obtaining preset welding parameters during the welding process. By obtaining physical quantities such as temperature, pressure, speed, and parameters that change with the flow field during the welding process, and combining the thermal physical parameters of the material, the preset welding parameters are generated.

[0031] According to one embodiment of the present invention, the pore generation tendency value output by the molten pool simulation model is the cavitation tendency of the metallurgical pores during the welding process.

[0032] Specifically, this embodiment provides an implementation method for the pore generation tendency value output by the molten pool simulation model. Metallurgical pores are caused by the production of insoluble gases due to metallurgical reactions. Their formation and stable existence are related to the molten pool cavitation, and are related to the material properties, welding methods, and welding processes. They are a type of pores that are difficult to control and eliminate in fusion welding.

[0033] It should be noted that the presence of metallurgical pores will often lead to stress concentration, become a potential crack source, reduce the load-bearing area of ​​the weld, reduce the fatigue strength of the weld, and ultimately lead to fracture and failure of the welded structure.

[0034] It should also be noted that this embodiment is based on a numerical simulation method, which can effectively save test costs, shorten the research and development cycle of the fusion welding process, and improve research and development production efficiency.

[0035] Furthermore, this embodiment establishes the correlation between the heat transfer, flow and phase change behaviors of the welding pool and the formation of welding defects by reproducing the process of the welding pool forming, developing and solidifying, so as to guide the welding process.

[0036] According to one embodiment of the present invention, the molten pool mimicry model is obtained based on the steps of training the molten pool mimicry sample, specifically including:

[0037] obtaining multiple welding parameter samples;

[0038] Generate a plurality of the molten pool simulation samples according to a plurality of the welding parameter samples;

[0039] The molten pool mimicry model is obtained by training based on a plurality of the molten pool mimicry samples.

[0040] Specifically, this embodiment provides an implementation method for training a molten pool mimicry model, which realizes the establishment of a molten pool mimicry sample through multiple welding parameter samples, and trains the molten pool mimicry model based on multiple molten pool mimicry samples.

[0041] According to one embodiment of the present invention, the step of obtaining the molten pool mimicry model by training a plurality of the molten pool mimicry samples specifically includes:

[0042] Obtaining a sample characteristic value of the molten pool mimicry sample;

[0043] Obtaining a first sample vector, a second sample vector, a third sample vector and a fourth sample vector in the sample characteristic value, wherein the first sample vector points to the starting point of a sampling period, the second sample vector points to the cavitation pressure in the molten pool, the third sample vector points to the instantaneous pressure in the molten pool, and the fourth sample vector points to the additional pressure in the cavitation process of the molten pool;

[0044] Constructing an instant cavitation tendency function of the molten pool according to the first sample vector, the second sample vector, the third sample vector and the fourth sample vector;

[0045] The molten pool mimicry model is trained according to the instant cavitation tendency function.

[0046] Specifically, this embodiment provides an implementation method for obtaining the molten pool mimicry model based on multiple molten pool mimicry sample training, and by acquiring the cavitation pressure, instantaneous pressure and additional pressure in the molten pool, sample training of the instantaneous cavitation tendency at the starting point of the sampling period is achieved.

[0047] Furthermore, by constructing an instant cavitation tendency function according to the first sample vector, the second sample vector, the third sample vector and the fourth sample vector, the output of the instant cavitation tendency is achieved, and the training of the molten pool mimicry model is achieved according to the output training of the instant cavitation tendency.

[0048] According to an embodiment of the present invention, the step of obtaining the first sample vector, the second sample vector, the third sample vector and the fourth sample vector in the sample eigenvalue specifically includes:

[0049] Obtain atmospheric pressure, welding material molar mass, gas constant, welding material vaporization heat, welding material boiling point temperature and molten pool instant temperature;

[0050] Constructing a saturated vapor pressure function of the welding material according to the atmospheric pressure, the molar mass of the welding material, the gas constant, the heat of vaporization of the welding material, the boiling point temperature of the welding material and the instantaneous temperature of the molten pool;

[0051] The cavitation pressure is generated by the saturated vapor pressure function.

[0052] Specifically, this embodiment provides an implementation method for calculating the cavitation pressure pointed to by the second sample vector.

[0053] According to an embodiment of the present invention, the step of obtaining the first sample vector, the second sample vector, the third sample vector and the fourth sample vector in the sample eigenvalue specifically includes:

[0054] Obtain the surface tension of welding materials and the critical nucleation radius of pores;

[0055] Constructing a surface additional pressure function of the welding material according to the surface tension of the welding material and the critical nucleation radius of the pores;

[0056] The additional pressure is generated by the surface additional pressure function.

[0057] Specifically, this embodiment provides an implementation method for calculating the additional pressure pointed to by the fourth sample vector.

[0058] According to an embodiment of the present invention, after the step of obtaining the first sample vector, the second sample vector, the third sample vector and the fourth sample vector in the sample feature value, the method further includes:

[0059] Obtaining a fifth sample vector in the sample characteristic value, wherein the fifth sample vector points to the end point of the sampling period;

[0060] constructing a cumulative cavitation tendency function of the molten pool according to the first sample vector, the second sample vector, the third sample vector, the fourth sample vector and the fifth sample vector;

[0061] The molten pool mimicry model is trained according to the cumulative cavitation tendency function.

[0062] Specifically, this embodiment provides another implementation method for obtaining the molten pool mimicry model based on multiple molten pool mimicry sample training. By acquiring the cavitation pressure, instantaneous pressure and additional pressure in the molten pool, the starting point and end point of the sampling period are acquired, and the sample training of the cumulative cavitation tendency is realized.

[0063] Furthermore, by constructing a cumulative cavitation tendency function based on the first sample vector, the second sample vector, the third sample vector, the fourth sample vector and the fifth sample vector, the output of the instantaneous cavitation tendency is achieved, and the training of the molten pool mimicry model is achieved based on the output training of the cumulative cavitation tendency.

[0064] According to a second aspect of the present invention, a device for determining a tendency of weld porosity generation includes: an acquisition module, a generation module, a first determination module, and a second determination module;

[0065] The acquisition module is used to acquire welding parameters during the welding process;

[0066] The generation module is used to input the welding parameters into a molten pool mimicry model, and output a porosity generation tendency value corresponding to the welding parameters, wherein the molten pool mimicry model is obtained based on molten pool mimicry sample training;

[0067] The first judgment module is used to determine that the pore generation tendency value meets the preset pore generation threshold, and then determine that the welding parameters meet the welding requirements;

[0068] The second judgment module is used to determine that if the pore generation tendency value does not meet a preset pore generation threshold, then discard the welding parameters.

[0069] According to a third aspect of the present invention, an electronic device is provided, comprising: a memory and a processor;

[0070] The memory and the processor communicate with each other via a bus;

[0071] The memory stores computer instructions that can be executed on the processor;

[0072] When the processor calls the computer instructions, it can execute the above-mentioned method for determining the tendency of weld porosity generation.

[0073] According to a fourth aspect of the present invention, a computer program product is provided, which includes a non-transitory machine-readable medium storing a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned method for determining the tendency of weld porosity generation are implemented.

[0074] The above one or more technical solutions in the present invention have at least one of the following technical effects: the present invention provides a method, device, equipment and product for judging the tendency of pore generation in welds, which numerically simulates the tendency of pore generation in the fusion welding process, reproduces the welding process by means of computational fluid dynamics numerical simulation, fully considers the physical mechanism of pore generation, establishes a cavitation potential model to determine the tendency of pore generation, and thus realizes the guidance of the welding process.

[0075] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0077] Figure 1 It is a schematic flow chart of a method for determining the tendency of weld porosity generation provided by the present invention;

[0078] Figure 2 It is a schematic diagram of the structure of a device for determining the tendency of weld porosity generation provided by the present invention;

[0079] Figure 3 It is a structural schematic diagram of the electronic device provided by the present invention.

[0080] Reference numerals:

[0081] 100, acquisition module; 200, generation module; 300, first judgment module; 400, second judgment module; 810, processor; 820, communication interface; 830, memory; 840, communication bus. DETAILED DESCRIPTION

[0082] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0083] The present invention is described in detail below in conjunction with the accompanying drawings of the specification. The specific operating method in the method embodiment can also be applied to the device embodiment or the system embodiment. In the description of the present invention, unless otherwise specified, "at least one" includes one or more. "Multiple" refers to two or more. For example, at least one of A, B and C includes: A exists alone, B exists alone, A and B exist at the same time, A and C exist at the same time, B and C exist at the same time, and A, B and C exist at the same time. In the present invention, " / " means or, for example, A / B can mean A or B; "and / or" in this article is only a kind of association relationship that describes the associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone.

[0084] The present invention will be described in detail below in conjunction with specific implementation modes.

[0085] In some specific embodiments of the present invention, Figure 1 As shown, this scheme provides a method for determining the tendency of weld porosity generation, including:

[0086] Obtaining preset welding parameters during welding;

[0087] Inputting preset welding parameters into the molten pool mimicry model, and outputting the porosity generation tendency value corresponding to the preset welding parameters, wherein the molten pool mimicry model is obtained based on the molten pool mimicry sample training;

[0088] If it is determined that the pore generation tendency value meets the preset pore generation threshold value, it is determined that the preset welding parameters meet the welding requirements;

[0089] If it is determined that the pore generation tendency value does not meet the preset pore generation threshold, the preset welding parameters are discarded.

[0090] In detail, the present invention provides a method for determining the tendency of weld porosity to occur, so as to solve the defects in the prior art that metallurgical pores have a great influence on the service performance of fusion welding joints, are difficult to measure and detect, and currently lack a reliable and effective evaluation method. By numerically simulating the tendency of pores to occur in the fusion welding process, the welding process is reproduced by means of computational fluid dynamics numerical simulation, the physical mechanism of pore generation is fully considered, and a cavitation potential model is established to determine the tendency of pores to occur, thereby achieving guidance on the welding process.

[0091] It should be noted that by obtaining the preset welding parameters in the welding process and inputting them into the molten pool simulation model, the pore generation tendency value corresponding to the preset welding parameters can be obtained. By judging through the obtained pore generation tendency value, it can be known whether the preset welding parameters will cause pores to be generated in the molten pool, and whether the preset welding parameters need to be optimized.

[0092] In a possible implementation method, by establishing the correlation among engineering conditions, molten pool behavior and weld porosity tendency, the process development cycle can be shortened and development investment can be reduced; the tendency of fusion welding porosity defects can be analyzed, and control strategies and process improvement measures can be proposed to improve weld quality, reduce repair welding and rework processes, improve production efficiency and reduce manufacturing costs.

[0093] In a possible implementation, the discarded preset welding parameters are optimized, and the optimized and adjusted preset welding parameters are re-input into the molten pool mimicry model, and the corresponding pore generation tendency values ​​are obtained, and the judgment is re-performed based on the updated pore generation tendency values.

[0094] In some possible embodiments of the present invention, the step of inputting preset welding parameters into the molten pool simulation model and outputting the porosity generation tendency value corresponding to the preset welding parameters specifically includes:

[0095] Obtaining characteristic values ​​of preset welding parameters;

[0096] Extracting a first eigenvector of the eigenvalue, the first eigenvector points to the starting point of the sampling period;

[0097] Input the first eigenvector into the molten pool mimicry model, and output the corresponding instant pore tendency parameter;

[0098] A stomatal generation tendency value is generated according to the instant stomatal tendency parameter.

[0099] Specifically, this embodiment provides an implementation method for outputting the pore generation tendency value corresponding to the preset welding parameters. By extracting the first eigenvector in the eigenvalue, the pore generation tendency at any time is obtained, that is, the instantaneous pore generation tendency at the time corresponding to the first eigenvector is obtained.

[0100] It should be noted that the problem of difficulty in real-time monitoring of pore formation during melting welding is overcome through numerical simulation based on heat-fluid coupling. The cavitation potential model is established considering the physical mechanism of pore generation, so as to achieve effective evaluation of the immediate pore generation tendency.

[0101] In a possible embodiment, the pores are metallurgical pores.

[0102] In a possible implementation, the preset welding parameters at least include the process parameters applied during the entire welding cycle, and the starting point of the sampling cycle pointed to by the first eigenvector is acquired at any welding moment, so as to judge the tendency of porosity generation at the starting point.

[0103] In a possible implementation manner, the number of first eigenvectors is N, where N is a positive integer greater than or equal to two.

[0104] In a possible implementation, when extracting the first eigenvector of the eigenvalue, corresponding feature indexing may be performed, and the feature indexing includes the relative time value of the starting point of the acquisition cycle pointed to by the first eigenvector in the entire welding process.

[0105] In some possible embodiments of the present invention, the step of inputting preset welding parameters into the molten pool simulation model and outputting the porosity generation tendency value corresponding to the preset welding parameters specifically includes:

[0106] Obtaining characteristic values ​​of preset welding parameters;

[0107] Extracting a first eigenvector and a second eigenvector of the eigenvalue, wherein the first eigenvector points to the starting point of the sampling period, and the second eigenvector points to the ending point of the sampling period;

[0108] Inputting the first eigenvector and the second eigenvector into the molten pool mimicry model, and outputting the corresponding cumulative pore tendency parameter;

[0109] A stomatal generation tendency value is generated according to the cumulative stomatal tendency parameter.

[0110] Specifically, this embodiment provides another implementation method for outputting the porosity generation tendency value corresponding to the preset welding parameters. By extracting the first eigenvector and the second eigenvector in the eigenvalue, the accumulation of the porosity generation tendency between the starting point and the end point of the sampling period is obtained, that is, the cumulative parameters of the porosity generation tendency between the first eigenvector and the second eigenvector are obtained.

[0111] It should be noted that the problem of difficulty in real-time monitoring of pore formation during melting welding is overcome through numerical simulation based on heat-fluid coupling. The cavitation potential model is established considering the physical mechanism of pore generation, so as to effectively evaluate the tendency of cumulative pore generation.

[0112] In a possible embodiment, the pores are metallurgical pores.

[0113] In a possible implementation, the preset welding parameters at least include the process parameters applied during the entire welding cycle, and the acquisition is performed at any welding moment, that is, the starting point of the sampling cycle pointed to by the first eigenvector, so as to realize the judgment of the tendency of porosity generation at the starting point. Similarly, the second eigenvector points to the end point of the sampling cycle. By acquiring the time length between the first eigenvector and the second eigenvector, the evaluation of the tendency of porosity generation within the time length is obtained.

[0114] In a possible implementation, the number of first feature vectors is M, where M is a positive integer greater than or equal to 2, and the number of second feature vectors corresponds to the number of first feature vectors, that is, within the acquisition cycle, they correspond to the starting point and the ending point, respectively.

[0115] In a possible implementation, when extracting the first eigenvector of the eigenvalue, corresponding feature indexing may be performed, and the feature indexing includes the relative time value of the starting point of the acquisition cycle pointed to by the first eigenvector in the entire welding process.

[0116] In a possible implementation, when extracting the second eigenvector of the eigenvalue, corresponding feature indexing may be performed, and the feature indexing includes the relative time value of the end point of the acquisition period pointed to by the second eigenvector in the entire welding process.

[0117] In some possible embodiments of the present invention, the step of obtaining preset welding parameters in the welding process specifically includes:

[0118] Obtain the temperature field characteristics, flow field characteristics, material characteristics and welding process characteristics of the molten pool during welding;

[0119] Generate preset welding parameters based on temperature field characteristics, flow field characteristics, material characteristics and welding process characteristics.

[0120] Specifically, this embodiment provides an implementation method for obtaining preset welding parameters during the welding process. By obtaining physical quantities such as temperature, pressure, speed, and parameters that change with the flow field during the welding process, and combining the thermal physical parameters of the material, the preset welding parameters are generated.

[0121] In a possible implementation, the temperature field characteristics, flow field characteristics, material characteristics and welding process characteristics in the molten pool are obtained, and the temperature field and flow field of the molten pool in the welding process can be numerically simulated by thermal-flux coupling. Evaluation criteria are established through the temperature and pressure distribution in the molten pool to evaluate the tendency of porosity in the weld.

[0122] In a possible implementation manner, the material feature is at least one or a combination of metals such as aluminum alloy, titanium alloy, steel, etc.

[0123] In a possible implementation manner, the welding process features at least include various melting welding methods such as arc welding, laser welding, laser-arc hybrid welding, and electron beam welding.

[0124] In some possible embodiments of the present invention, the pore generation tendency value output by the molten pool simulation model is the cavitation tendency of metallurgical pores during the welding process.

[0125] Specifically, this embodiment provides an implementation method for the pore generation tendency value output by the molten pool simulation model. Metallurgical pores are caused by the production of insoluble gases due to metallurgical reactions. Their formation and stable existence are related to the molten pool cavitation, and are related to the material properties, welding methods, and welding processes. They are a type of pores that are difficult to control and eliminate in fusion welding.

[0126] It should be noted that the presence of metallurgical pores will often lead to stress concentration, become a potential crack source, reduce the load-bearing area of ​​the weld, reduce the fatigue strength of the weld, and ultimately lead to fracture and failure of the welded structure.

[0127] It should also be noted that this embodiment is based on a numerical simulation method, which can effectively save test costs, shorten the research and development cycle of the fusion welding process, and improve research and development production efficiency.

[0128] Furthermore, this embodiment establishes the correlation between the heat transfer, flow and phase change behaviors of the welding pool and the formation of welding defects by reproducing the process of the welding pool forming, developing and solidifying, so as to guide the welding process.

[0129] In a possible implementation, the tendency of metallurgical pores in the joint to be generated is reduced by changing the numerical simulation input, thereby obtaining optimized fusion welding process parameters or joint design.

[0130] In a possible implementation, the tendency of metallurgical pore generation is evaluated by numerical simulation. The tendency of metallurgical pore generation under different welding conditions and process parameters can be evaluated by changing the numerical simulation input conditions to obtain optimized process parameters and joint shape.

[0131] In some possible embodiments of the present invention, the steps of obtaining the molten pool mimicry model based on molten pool mimicry sample training specifically include:

[0132] obtaining multiple welding parameter samples;

[0133] Generate multiple molten pool simulation samples according to multiple welding parameter samples;

[0134] The melt pool mimicry model is obtained by training multiple melt pool mimicry samples.

[0135] Specifically, this embodiment provides an implementation method for training a molten pool mimicry model, which realizes the establishment of a molten pool mimicry sample through multiple welding parameter samples, and trains the molten pool mimicry model based on multiple molten pool mimicry samples.

[0136] In a possible implementation manner, the establishment of the molten pool simulation sample in this embodiment is carried out by establishing a physical model of the melting welding process based on the method of computational fluid.

[0137] In a possible implementation manner, the training of the molten pool simulation model in this embodiment is carried out by establishing a physical model of the melting welding process based on a computational fluid method.

[0138] In some possible embodiments of the present invention, the step of obtaining a molten pool mimicry model by training a plurality of molten pool mimicry samples specifically includes:

[0139] Obtaining sample characteristic values ​​of the melt pool mimicry sample;

[0140] Obtaining a first sample vector, a second sample vector, a third sample vector and a fourth sample vector in the sample characteristic value, wherein the first sample vector points to the starting point of the sampling period, the second sample vector points to the cavitation pressure in the molten pool, the third sample vector points to the instantaneous pressure in the molten pool, and the fourth sample vector points to the additional pressure in the cavitation process of the molten pool;

[0141] Constructing an instant cavitation tendency function of the molten pool according to the first sample vector, the second sample vector, the third sample vector and the fourth sample vector;

[0142] The melt pool mimicry model is trained based on the instant cavitation tendency function.

[0143] Specifically, this embodiment provides an implementation method for obtaining a molten pool mimicry model based on multiple molten pool mimicry sample training, and realizes sample training of the instantaneous cavitation tendency at the starting point of the sampling period by acquiring the cavitation pressure, instantaneous pressure and additional pressure in the molten pool.

[0144] Furthermore, by constructing an instant cavitation tendency function according to the first sample vector, the second sample vector, the third sample vector and the fourth sample vector, the output of the instant cavitation tendency is achieved, and the training of the molten pool mimicry model is achieved according to the output training of the instant cavitation tendency.

[0145] In a possible implementation, the instant cavitation tendency function of the molten pool is constructed according to the first sample vector, the second sample vector, the third sample vector and the fourth sample vector, using the following formula:

[0146] S0=max[0,P cav -(P(ijk)+P add )]

[0147] Where S0 represents the instant cavitation tendency function, that is, the tendency of cavitation at any point in the molten pool at any time during the welding process. Its value represents the tendency of metallurgical pores to be generated at a specified position in the molten pool at the current moment. The larger the value, the greater the tendency of pores to be generated. 0 means that no metallurgical pores are generated.

[0148] P cav is the cavitation pressure, in Pa.

[0149] P(ijk) is the current pressure at any point in the molten pool, in Pa.

[0150] P add It is the additional cavitation pressure at any point in the molten pool, in Pa.

[0151] In a possible implementation, the pressure P(ijk) at any point in the molten pool obtained by thermal-fluid coupling calculation is combined with P cav and P add , for P(ijk) and P add The sum of cav To compare the size, when P cav When it is greater than the sum of the two, S0=P cav -(P(ijk)+P add ); when P cav When it is less than the sum of the two, S0 is taken as 0, thereby obtaining the metallurgical pore evaluation index value S0 at the current moment.

[0152] In some possible embodiments of the present invention, the step of obtaining the first sample vector, the second sample vector, the third sample vector and the fourth sample vector in the sample eigenvalue specifically includes:

[0153] Obtain atmospheric pressure, welding material molar mass, gas constant, welding material vaporization heat, welding material boiling point temperature and molten pool instant temperature;

[0154] The saturated vapor pressure function of welding material is constructed according to the atmospheric pressure, the molar mass of welding material, the gas constant, the vaporization heat of welding material, the boiling point temperature of welding material and the instantaneous temperature of molten pool;

[0155] The cavitation pressure is generated as a function of the saturated vapor pressure.

[0156] Specifically, this embodiment provides an implementation method for calculating the cavitation pressure pointed to by the second sample vector.

[0157] In a possible implementation manner, the second sample vector is calculated using the following formula:

[0158]

[0159] Where Pcav is the saturated vapor pressure of the metal, that is, the cavitation pressure.

[0160] P0 is atmospheric pressure, that is 1.01325×105Pa.

[0161] M is the molar mass of the metal material being welded, expressed in kg / mol, and is a property of the material.

[0162] R is the gas constant, 8.314 J / (mol〃K).

[0163] ΔH vap It is the heat of vaporization of the metal material being welded, and its unit is J / kg, which is a material property.

[0164] T0 is the boiling point temperature of the material, in K, that is, the temperature corresponding to the saturated vapor pressure P0.

[0165] T1 is the temperature of any point in the molten pool, in K.

[0166] In some possible embodiments of the present invention, the step of obtaining the first sample vector, the second sample vector, the third sample vector and the fourth sample vector in the sample eigenvalue specifically includes:

[0167] Obtain the surface tension of welding materials and the critical nucleation radius of pores;

[0168] The surface additional pressure function of welding material is constructed according to the surface tension of welding material and the critical nucleation radius of pores;

[0169] The additional pressure is generated by the surface additional pressure function.

[0170] Specifically, this embodiment provides an implementation method for calculating the additional pressure pointed to by the fourth sample vector.

[0171] In a possible implementation manner, the fourth sample vector is calculated using the following formula:

[0172] P add =2σ / γ

[0173] Where P add It is the additional pressure of surface tension, that is, the additional cavitation pressure at any point in the molten pool.

[0174] σ is the surface tension of the welded metal material, which is a material property and its unit is N / m.

[0175] γ is the critical nucleation radius of metallurgical pores, which is a material property and its unit is m.

[0176] In some possible embodiments of the present invention, after the step of obtaining the first sample vector, the second sample vector, the third sample vector and the fourth sample vector in the sample eigenvalue, the method further includes:

[0177] Obtaining a fifth sample vector in the sample characteristic value, wherein the fifth sample vector points to the end point of the sampling period;

[0178] constructing a cumulative cavitation tendency function of the molten pool according to the first sample vector, the second sample vector, the third sample vector, the fourth sample vector and the fifth sample vector;

[0179] The melt pool mimicry model is trained based on the cumulative cavitation tendency function.

[0180] Specifically, this embodiment provides another implementation method for obtaining a molten pool mimicry model based on training of multiple molten pool mimicry samples. By acquiring the cavitation pressure, instantaneous pressure and additional pressure in the molten pool, the starting point and end point of the sampling period are acquired, and sample training of cumulative cavitation tendency is realized.

[0181] Furthermore, by constructing a cumulative cavitation tendency function based on the first sample vector, the second sample vector, the third sample vector, the fourth sample vector and the fifth sample vector, the output of the instantaneous cavitation tendency is achieved, and the training of the molten pool mimicry model is achieved based on the output training of the cumulative cavitation tendency.

[0182] In a possible implementation, the cumulative cavitation tendency function of the molten pool is constructed according to the first sample vector, the second sample vector, the third sample vector, the fourth sample vector and the fifth sample vector, using the following formula:

[0183]

[0184] Where S1 represents the cumulative cavitation tendency function, that is, the cumulative cavitation tendency of any point in the molten pool from the start of welding to a certain moment during welding. Its numerical value represents the tendency of metallurgical pores to be generated. The larger the value, the greater the tendency of pores to be generated. 0 means that no metallurgical pores are generated.

[0185] P cav is the cavitation pressure, in Pa.

[0186] P(ijk) is the current pressure at any point in the molten pool, in Pa.

[0187] P add It is the additional cavitation pressure at any point in the molten pool, in Pa.

[0188] In a possible implementation, the pressure P(ijk) at any point in the molten pool obtained by thermal-fluid coupling calculation is combined with P cav and P add, for P(ijk) and P add The sum of cav To compare the size, when P cav When it is greater than the sum of the two, S0=P cav -(P(ijk)+P add ); when P cav When it is less than the sum of the two, S0 is taken as 0, so as to obtain the metallurgical porosity evaluation index value S0 at the current moment. At the same time, the S0 value at any position of the weld from the start of welding to a certain moment is integrated to obtain the evaluation index S1 of the cumulative generation tendency of metallurgical porosity in the molten pool, which is used to evaluate the generation trend of metallurgical porosity in the weld.

[0189] In some specific embodiments of the present invention, Figure 2 As shown, the present solution provides a device for determining the tendency of weld porosity generation, including: an acquisition module 100, a generation module 200, a first judgment module 300 and a second judgment module 400.

[0190] The acquisition module 100 is used to acquire welding parameters during the welding process.

[0191] The generation module 200 is used to input welding parameters into the molten pool mimicry model and output the porosity generation tendency value corresponding to the welding parameters, wherein the molten pool mimicry model is obtained based on the molten pool mimicry sample training.

[0192] The first judgment module 300 is used to determine that the pore generation tendency value meets the preset pore generation threshold, and then determine that the welding parameters meet the welding requirements.

[0193] The second judgment module 400 is used to determine that if the porosity generation tendency value does not meet a preset porosity generation threshold, then discard the welding parameters.

[0194] Figure 3 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 3 As shown, the electronic device may include: a processor 810, a communication interface 820, a memory 830 and a communication bus 840, wherein the processor 810, the communication interface 820 and the memory 830 communicate with each other through the communication bus 840. The processor 810 may call the logic instructions in the memory 830 to execute the method for determining the tendency of weld porosity generation.

[0195] It should be noted that the electronic device in this embodiment can be a server, a PC, or other devices in specific implementation, as long as its structure includes the following: Figure 3The processor 810, communication interface 820, memory 830 and communication bus 840 shown in the figure, wherein the processor 810, communication interface 820, memory 830 communicate with each other through the communication bus 840, and the processor 810 can call the logic instructions in the memory 830 to execute the above method. This embodiment does not limit the specific implementation form of the electronic device.

[0196] Among them, the server can be a single server or a server group. The server group can be centralized or distributed (for example, the server can be a distributed system). In some embodiments, the server can be local or remote relative to the terminal. For example, the server can access information stored in a user terminal, a database, or any combination thereof via a network. As another example, the server can be directly connected to at least one of the user terminal and the database to access the information and / or data stored therein. In some embodiments, the server can be implemented on a cloud platform; as an example only, the cloud platform can include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an inter-cloud, a multi-cloud, etc., or any combination thereof. In some embodiments, the server and the user terminal can be implemented on an electronic device having one or more components in an embodiment of the present invention.

[0197] Further, the network can be used for the exchange of information and / or data. In some embodiments, one or more components (e.g., servers, user terminals, and databases) in the interactive scene can send information and / or data to other components. In some embodiments, the network can be any type of wired or wireless network, or a combination thereof. As an example only, the network can include a wired network, a wireless network, an optical fiber network, a telecommunication network, an intranet, the Internet, a local area network (LAN), a wide area network (WAN), a wireless local area network (WLAN), a metropolitan area network (MAN), a wide area network (WAN), a public switched telephone network (PSTN), a Bluetooth network, a ZigBee network, or a near field communication (NFC) network, etc., or any combination thereof. In some embodiments, the network can include one or more network access points. For example, the network can include a wired or wireless network access point, such as a base station and / or a network switching node, and one or more components of the interactive scene can be connected to the network through the access point to exchange data and / or information.

[0198] In addition, the logic instructions in the above-mentioned memory 830 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0199] In a possible implementation manner, an embodiment of the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for determining the tendency of weld porosity generation provided in the above embodiments is implemented.

[0200] In a possible implementation, an embodiment of the present invention further provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the method for determining the tendency of weld porosity generation provided in the above-mentioned method embodiments.

[0201] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, i.e., they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative effort.

[0202] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each embodiment or some parts of the embodiment.

[0203] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for determining the tendency of weld porosity, characterized in that: include: Obtaining preset welding parameters during welding; Inputting the preset welding parameters into a molten pool mimicry model, and outputting a porosity generation tendency value corresponding to the preset welding parameters, wherein the molten pool mimicry model is obtained based on molten pool mimicry sample training; Determining that the pore generation tendency value meets a preset pore generation threshold value, then determining that the preset welding parameters meet the welding requirements; If it is determined that the pore generation tendency value does not meet a preset pore generation threshold, the preset welding parameters are discarded; The step of inputting the preset welding parameters into the molten pool simulation model and outputting the porosity generation tendency value corresponding to the preset welding parameters specifically includes: Obtaining characteristic values ​​of the preset welding parameters; Extracting a first eigenvector of the eigenvalue, where the first eigenvector points to a starting point of a sampling period, and the number of first eigenvectors is N, where N is a positive integer greater than or equal to 2; Inputting the first characteristic vector into the molten pool mimicry model, and outputting the corresponding instant pore tendency parameter; Generating the pore generation tendency value according to the instant pore tendency parameter, wherein the pore generation tendency value represents the instant pore generation tendency at the corresponding moment; Alternatively, the step of inputting the preset welding parameters into the molten pool simulation model and outputting the porosity generation tendency value corresponding to the preset welding parameters specifically includes: Obtaining characteristic values ​​of the preset welding parameters; Extracting a first eigenvector and a second eigenvector of the eigenvalue, wherein the first eigenvector points to a starting point of a sampling period, the second eigenvector points to an ending point of the sampling period, the number of the first eigenvectors is M, M is a positive integer greater than or equal to two, and the number of the second eigenvectors corresponds to the number of the first eigenvectors; Inputting the first eigenvector and the second eigenvector into the molten pool mimicry model, and outputting corresponding cumulative pore tendency parameters; The pore generation tendency value is generated according to the cumulative pore generation tendency parameter, and the pore generation tendency value represents the cumulative parameter of the pore generation tendency.

2. A method for determining the tendency of weld porosity generation according to claim 1, characterized in that: The step of obtaining the preset welding parameters during the welding process specifically includes: Acquiring temperature field characteristics, flow field characteristics, material characteristics and welding process characteristics of the molten pool during the welding process; The preset welding parameters are generated according to the temperature field characteristics, the flow field characteristics, the material characteristics and the welding process characteristics.

3. A method for determining the tendency of weld porosity generation according to claim 1, characterized in that: The pore generation tendency value output by the molten pool simulation model is the cavitation tendency of metallurgical pores during the welding process.

4. A method for determining the tendency of weld porosity generation according to any one of claims 1 to 3, characterized in that: The molten pool mimicry model is obtained based on the steps of training the molten pool mimicry sample, specifically including: obtaining multiple welding parameter samples; Generate a plurality of the molten pool simulation samples according to a plurality of the welding parameter samples; The molten pool mimicry model is obtained by training based on a plurality of the molten pool mimicry samples.

5. A method for determining the tendency of weld porosity generation according to claim 4, characterized in that: The step of obtaining the molten pool mimicry model by training a plurality of the molten pool mimicry samples specifically includes: Obtaining a sample characteristic value of the molten pool mimicry sample; Obtaining a first sample vector, a second sample vector, a third sample vector and a fourth sample vector in the sample characteristic value, wherein the first sample vector points to the starting point of a sampling period, the second sample vector points to the cavitation pressure in the molten pool, the third sample vector points to the instantaneous pressure in the molten pool, and the fourth sample vector points to the additional pressure in the cavitation process of the molten pool; Constructing an instant cavitation tendency function of the molten pool according to the first sample vector, the second sample vector, the third sample vector and the fourth sample vector; The molten pool mimicry model is trained according to the instant cavitation tendency function.

6. A method for determining the tendency of weld porosity generation according to claim 5, characterized in that: The step of obtaining the first sample vector, the second sample vector, the third sample vector and the fourth sample vector in the sample eigenvalue specifically includes: Obtain atmospheric pressure, welding material molar mass, gas constant, welding material vaporization heat, welding material boiling point temperature and molten pool instant temperature; Constructing a saturated vapor pressure function of the welding material according to the atmospheric pressure, the molar mass of the welding material, the gas constant, the heat of vaporization of the welding material, the boiling point temperature of the welding material and the instantaneous temperature of the molten pool; The cavitation pressure is generated by the saturated vapor pressure function.

7. A method for determining the tendency of weld porosity generation according to claim 5, characterized in that: The step of obtaining the first sample vector, the second sample vector, the third sample vector and the fourth sample vector in the sample eigenvalue specifically includes: Obtain the surface tension of welding materials and the critical nucleation radius of pores; Constructing a surface additional pressure function of the welding material according to the surface tension of the welding material and the critical nucleation radius of the pores; The additional pressure is generated by the surface additional pressure function.

8. A method for determining the tendency of weld porosity generation according to claim 5, characterized in that: After the step of obtaining the first sample vector, the second sample vector, the third sample vector and the fourth sample vector in the sample characteristic value, the method further includes: Obtaining a fifth sample vector in the sample characteristic value, wherein the fifth sample vector points to the end point of the sampling period; constructing a cumulative cavitation tendency function of the molten pool according to the first sample vector, the second sample vector, the third sample vector, the fourth sample vector and the fifth sample vector; The molten pool mimicry model is trained according to the cumulative cavitation tendency function.

9. A device for determining the tendency of weld porosity, characterized in that: include: An acquisition module, a generation module, a first judgment module and a second judgment module; The acquisition module is used to acquire preset welding parameters during the welding process; The generation module is used to input the preset welding parameters into the molten pool mimicry model, and output the porosity generation tendency value corresponding to the preset welding parameters, wherein the molten pool mimicry model is obtained based on the molten pool mimicry sample training; The first judgment module is used to determine that the pore generation tendency value meets the preset pore generation threshold, and then determine that the preset welding parameters meet the welding requirements; The second judgment module is used to determine that the pore generation tendency value does not meet the preset pore generation threshold, and then discard the preset welding parameters; The step of inputting the preset welding parameters into the molten pool simulation model and outputting the porosity generation tendency value corresponding to the preset welding parameters specifically includes: Obtaining characteristic values ​​of the preset welding parameters; Extracting a first eigenvector of the eigenvalue, where the first eigenvector points to a starting point of a sampling period, and the number of first eigenvectors is N, where N is a positive integer greater than or equal to 2; Inputting the first characteristic vector into the molten pool mimicry model, and outputting the corresponding instant pore tendency parameter; Generating the pore generation tendency value according to the instant pore tendency parameter, wherein the pore generation tendency value represents the instant pore generation tendency at the corresponding moment; Alternatively, the step of inputting the preset welding parameters into the molten pool simulation model and outputting the porosity generation tendency value corresponding to the preset welding parameters specifically includes: Obtaining characteristic values ​​of the preset welding parameters; Extracting a first eigenvector and a second eigenvector of the eigenvalue, wherein the first eigenvector points to a starting point of a sampling period, the second eigenvector points to an ending point of the sampling period, the number of the first eigenvectors is M, M is a positive integer greater than or equal to two, and the number of the second eigenvectors corresponds to the number of the first eigenvectors; Inputting the first eigenvector and the second eigenvector into the molten pool mimicry model, and outputting corresponding cumulative pore tendency parameters; The pore generation tendency value is generated according to the cumulative pore generation tendency parameter, and the pore generation tendency value represents the cumulative parameter of the pore generation tendency.

10. An electronic device, characterized in that: include: Memory and processor; The memory and the processor communicate with each other via a bus; The memory stores computer instructions that can be executed on the processor; When the processor calls the computer instructions, it can execute the method for determining the tendency of weld porosity generation as described in any one of claims 1 to 8.

11. A computer program product comprising a non-transitory machine-readable medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for determining the tendency of weld porosity generation as described in any one of claims 1 to 8 are implemented.

Images