CN116900450B - High-efficiency deep-melting arc welding auxiliary welding method - Google Patents
High-efficiency deep-melting arc welding auxiliary welding method Download PDFInfo
- Publication number
- CN116900450B CN116900450B CN202311064998.7A CN202311064998A CN116900450B CN 116900450 B CN116900450 B CN 116900450B CN 202311064998 A CN202311064998 A CN 202311064998A CN 116900450 B CN116900450 B CN 116900450B
- Authority
- CN
- China
- Prior art keywords
- welding
- parameters
- magnetic field
- auxiliary
- deep
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000003466 welding Methods 0.000 title claims abstract description 354
- 238000000034 method Methods 0.000 title claims abstract description 209
- 238000002844 melting Methods 0.000 title claims abstract description 64
- 230000008569 process Effects 0.000 claims abstract description 181
- 239000000463 material Substances 0.000 claims abstract description 98
- 230000026676 system process Effects 0.000 claims abstract description 55
- 238000003062 neural network model Methods 0.000 claims abstract description 44
- 238000005275 alloying Methods 0.000 claims abstract description 32
- 230000008878 coupling Effects 0.000 claims abstract description 28
- 238000010168 coupling process Methods 0.000 claims abstract description 28
- 238000005859 coupling reaction Methods 0.000 claims abstract description 28
- 238000004364 calculation method Methods 0.000 claims description 22
- 238000012360 testing method Methods 0.000 claims description 21
- 238000012549 training Methods 0.000 claims description 14
- 230000006870 function Effects 0.000 claims description 9
- 239000000126 substance Substances 0.000 claims description 9
- 238000012795 verification Methods 0.000 claims description 8
- 239000000203 mixture Substances 0.000 claims description 6
- WFKWXMTUELFFGS-UHFFFAOYSA-N tungsten Chemical compound [W] WFKWXMTUELFFGS-UHFFFAOYSA-N 0.000 claims description 5
- 229910052721 tungsten Inorganic materials 0.000 claims description 5
- 239000010937 tungsten Substances 0.000 claims description 5
- 238000011478 gradient descent method Methods 0.000 claims description 3
- 229910000831 Steel Inorganic materials 0.000 description 22
- 239000010959 steel Substances 0.000 description 22
- PXHVJJICTQNCMI-UHFFFAOYSA-N nickel Substances [Ni] PXHVJJICTQNCMI-UHFFFAOYSA-N 0.000 description 12
- 230000000694 effects Effects 0.000 description 10
- 229910045601 alloy Inorganic materials 0.000 description 7
- 239000000956 alloy Substances 0.000 description 7
- 210000001503 joint Anatomy 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 230000006698 induction Effects 0.000 description 6
- 229910000975 Carbon steel Inorganic materials 0.000 description 5
- 239000010962 carbon steel Substances 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 238000011049 filling Methods 0.000 description 5
- 229910000851 Alloy steel Inorganic materials 0.000 description 3
- 229910000712 Boron steel Inorganic materials 0.000 description 3
- 229910001069 Ti alloy Inorganic materials 0.000 description 3
- 229910001093 Zr alloy Inorganic materials 0.000 description 3
- 238000005260 corrosion Methods 0.000 description 3
- 230000007797 corrosion Effects 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 229910000856 hastalloy Inorganic materials 0.000 description 3
- 238000009863 impact test Methods 0.000 description 3
- 229910052751 metal Inorganic materials 0.000 description 3
- 239000002184 metal Substances 0.000 description 3
- 230000001105 regulatory effect Effects 0.000 description 3
- 229910001220 stainless steel Inorganic materials 0.000 description 3
- 239000010935 stainless steel Substances 0.000 description 3
- 229910052715 tantalum Inorganic materials 0.000 description 3
- GUVRBAGPIYLISA-UHFFFAOYSA-N tantalum atom Chemical compound [Ta] GUVRBAGPIYLISA-UHFFFAOYSA-N 0.000 description 3
- 238000009864 tensile test Methods 0.000 description 3
- 239000010936 titanium Substances 0.000 description 3
- 229910052719 titanium Inorganic materials 0.000 description 3
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 2
- 229910000881 Cu alloy Inorganic materials 0.000 description 2
- RTAQQCXQSZGOHL-UHFFFAOYSA-N Titanium Chemical compound [Ti] RTAQQCXQSZGOHL-UHFFFAOYSA-N 0.000 description 2
- 239000010953 base metal Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000001276 controlling effect Effects 0.000 description 2
- 238000001816 cooling Methods 0.000 description 2
- 229910052802 copper Inorganic materials 0.000 description 2
- 239000010949 copper Substances 0.000 description 2
- 238000005520 cutting process Methods 0.000 description 2
- 210000001787 dendrite Anatomy 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000000227 grinding Methods 0.000 description 2
- 238000011068 loading method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000002360 preparation method Methods 0.000 description 2
- 238000007711 solidification Methods 0.000 description 2
- 230000008023 solidification Effects 0.000 description 2
- 229910000570 Cupronickel Inorganic materials 0.000 description 1
- 229910001209 Low-carbon steel Inorganic materials 0.000 description 1
- 238000007545 Vickers hardness test Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- YOCUPQPZWBBYIX-UHFFFAOYSA-N copper nickel Chemical compound [Ni].[Cu] YOCUPQPZWBBYIX-UHFFFAOYSA-N 0.000 description 1
- 238000012938 design process Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 229910001039 duplex stainless steel Inorganic materials 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 210000005067 joint tissue Anatomy 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000008018 melting Effects 0.000 description 1
- 239000007769 metal material Substances 0.000 description 1
- 229910052750 molybdenum Inorganic materials 0.000 description 1
- 238000000465 moulding Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000000149 penetrating effect Effects 0.000 description 1
- 230000035515 penetration Effects 0.000 description 1
- 238000005498 polishing Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000003014 reinforcing effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000010187 selection method Methods 0.000 description 1
- 238000003756 stirring Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000002195 synergetic effect Effects 0.000 description 1
- 238000005496 tempering Methods 0.000 description 1
- 210000001519 tissue Anatomy 0.000 description 1
- 238000009827 uniform distribution Methods 0.000 description 1
- 229910052720 vanadium Inorganic materials 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23K—SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
- B23K9/00—Arc welding or cutting
- B23K9/16—Arc welding or cutting making use of shielding gas
- B23K9/167—Arc welding or cutting making use of shielding gas and of a non-consumable electrode
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23K—SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
- B23K9/00—Arc welding or cutting
- B23K9/32—Accessories
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Plasma & Fusion (AREA)
- Mechanical Engineering (AREA)
- Arc Welding In General (AREA)
Abstract
The invention discloses a high-efficiency deep-melting arc welding auxiliary welding method, which is characterized in that an auxiliary welding process in an expert system process library is selected according to the welding characteristics of welding materials to weld the welding materials, wherein the auxiliary welding process comprises at least one of a micro-alloying auxiliary process, a magnetic field auxiliary process, a micro-alloying coupling magnetic field auxiliary process and a welding formula generated by a fuzzy neural network model.
Description
Technical Field
The invention relates to the technical field of welding, in particular to a high-efficiency deep-melting arc welding auxiliary welding method.
Background
The high-efficiency deep-melting arc welding is a high-efficiency welding method adopting high current and reinforcing tungsten electrode cooling, and realizes one-step penetration of metal materials with the thickness of 3-16 mm without forming grooves and filling wires by forming free electric arcs with high stiffness and strong penetrating power, thereby realizing single-sided welding and double-sided molding.
However, the high heat input and rapid cooling of the deep-melting arc welding lead to coarse structural grains of the welded joint, reduce the impact toughness of the joint, make the mechanical property of the joint difficult to meet the industrial use requirement, refine the size of the joint grains by regulating and controlling the welding parameters in the conventional method, but the window of the adjustable welding parameters is narrower and the welding materials and the welding process parameters are difficult to be matched rapidly and accurately, so that a long time test is required before welding is performed to determine the proper welding process parameters, and the welding quality and the welding efficiency are both needed to be improved and are difficult to popularize and apply.
Disclosure of Invention
Aiming at the technical problems existing in the prior art, the invention provides the high-efficiency deep-melting arc welding auxiliary welding method, which is characterized in that the micro-alloying and the magnetic field auxiliary process are combined to perform welding under different welding process parameters, and a fuzzy neural network model is used to optimize the welding process parameters and predict the welding effect.
In order to achieve the above purpose, the present invention provides the following technical solutions:
an efficient deep-melting arc welding auxiliary welding method comprises the steps of selecting an auxiliary welding process in an expert system process library according to welding characteristics of welding materials to weld the welding materials, wherein the auxiliary welding process comprises at least one of a microalloying auxiliary process, a magnetic field auxiliary process, a microalloying coupling magnetic field auxiliary process and a welding formula generated by a prediction model established by a fuzzy neural network model.
Further, the welding formula is obtained after training a fuzzy neural network model based on at least one of a micro-alloying auxiliary process, a magnetic field auxiliary process and a micro-alloying coupling magnetic field auxiliary process.
Further, the expert system process library is classified according to material characteristics, and the welding materials select the auxiliary welding process according to the material type and model of the expert system process library.
Preferably, when the welding materials are matched with similar materials but different types from the expert system process library, one of a micro-alloying auxiliary process, a magnetic field auxiliary process and a micro-alloying coupling magnetic field auxiliary process related to the material closest to the chemical composition of the welding materials is selected from the expert system process library, and welding process parameters meeting the requirements are stored in the expert system process library after welding is implemented.
Preferably, when the welding materials cannot be matched with similar materials from the expert system process library, the performance parameters related to the materials closest to the chemical components of the welding materials are selected from the expert system process library to train the fuzzy neural network model, and after the trained fuzzy neural network model is calculated, the welding formula meeting the requirements is obtained and stored in the expert system process library.
Further, forming the micro-alloying assistance process in the expert system process library comprises the steps of:
step one: the microalloy parameters are selected according to the welding characteristics of the welding material,
step two: welding the welding material according to a deep-melting arc welding process using a welding medium, the deep-melting arc welding process having deep-melting arc welding process parameters,
step three: acquiring a welded joint sample and detecting performance parameters of the joint sample,
step four: obtaining the deep-melting arc welding process parameters and the microalloy parameters of which the performance parameters meet requirements, storing the deep-melting arc welding process parameters and the microalloy parameters in the expert system process library to form the microalloying auxiliary process, and/or,
forming the magnetic field assisted process in the expert system process library comprises the steps of:
step one: installing a magnetic field device according to the welding characteristics of the welding materials and setting magnetic field parameters,
step two: welding the welding material according to the deep-melting arc welding process,
step three: obtaining a welded joint sample and detecting the performance parameter of the joint sample,
step four: obtaining the deep-melting arc welding process parameters and the magnetic field parameters of which the performance parameters meet requirements, storing the deep-melting arc welding process parameters and the magnetic field parameters in the expert system process library to form the magnetic field auxiliary process, and/or,
forming the micro-alloyed coupling magnetic field assisting process in the expert system process library comprises the following steps:
step one: selecting the microalloy parameters according to the welding characteristics of the welding materials, installing the magnetic field device and setting the magnetic field parameters,
step two: welding the welding material according to the technological parameters of the deep-melting arc welding,
step three: obtaining a welded joint sample, detecting the performance parameter of the joint sample,
step four: and acquiring the deep-melting arc welding process parameters, the microalloy parameters and the magnetic field parameters of which the performance parameters meet requirements, and storing the deep-melting arc welding process parameters, the microalloy parameters and the magnetic field parameters in the expert system process library to form the microalloying coupling magnetic field auxiliary process.
Further, the process of forming the fuzzy neural network model comprises the following steps:
step one: setting an input layer, a fuzzification layer, a fuzzy rule calculation layer and an output layer for the fuzzy neural network model, wherein the input layer is used for receiving input parameters, the input parameters are performance parameters in the expert system process library, and the output layer is used for extracting output parameters;
step two: and normalizing the input parameters and dividing the normalized input parameters into a training set, a testing set and a verification set.
Step three: and fuzzifying the input parameters, calculating the membership degree of each input parameter by adopting a Gaussian membership function to obtain the fuzzification process, and then calculating a fuzzy rule.
Further, the gaussian membership function is:
wherein x is j For the j th saidInput parameters lambda i j For the input parameter x jj The ith said membership, μ i j Sum sigma i j J=1, 2,., k, k is the number of input parameters, i=1, 2,., n, n is the number of fuzzy subsets, respectively, for the center and width of the gaussian membership function.
Further, the membership degree of each input parameter is subjected to fuzzy calculation in the fuzzy rule calculation layer by using a continuous multiplication operator, so that the continuous product of the membership degree is the fuzzy rule calculation process,
wherein omega is i I=1, 2,..n, which is the continuous product of the membership of each parameter;
and obtaining the output parameters based on the fuzzy rule calculation result and the weight coefficient:
wherein y is i For the ith output parameter, p i k And the weight coefficient is the weight coefficient.
Further, the weight coefficient p i k The gradient descent method is adopted for iterative updating,
wherein p is i j (g) And (3) representing the weight coefficient of the g-th iteration, wherein alpha is the learning rate, and e is the output error.
Further, the priority of the auxiliary welding process is selected as follows: the magnetic field assisting process is more than the micro-alloying coupling magnetic field assisting process.
Further, when the difference between the upper and lower limits of the welding current threshold is less than 50A or the difference between the upper and lower limits of the welding speed threshold is less than 0.5mm/s or the difference between the tip of the tungsten needle and the upper and lower limits of the welding material surface distance threshold is less than 0.1mm, switching the auxiliary welding process, including switching the magnetic field auxiliary process to the micro-alloying auxiliary process and switching the micro-alloying auxiliary process to the micro-alloying coupling magnetic field auxiliary process.
Compared with the prior art, the high-efficiency deep-melting arc welding auxiliary welding method has the following beneficial effects:
1) Precisely regulating and controlling the joint tissue components: the micro-alloy elements are added, so that the structure components of the joint can be accurately regulated and controlled, the components and the forms of the micro-alloy elements are reasonably designed, and the grain size is thinned, so that the service performances of the weld joint such as strength, toughness, corrosion resistance, fatigue life and the like are improved;
2) The externally applied magnetic field optimizes the weld grain structure: the invention introduces an externally applied magnetic field, breaks solidification dendrites of the welding seam by utilizing the stirring effect of the externally applied magnetic field, further refines the grain size, simultaneously enhances the diffusion movement of the micro-alloy elements, promotes the uniform distribution of the micro-alloy elements in the welding seam, and optimizes the organization components and the service performance of the welding seam;
3) Extending the welding process window range: the application of the microalloying auxiliary and magnetic field auxiliary technology expands the process window range of the high-efficiency deep-melting arc welding, and the welding process parameters can be more flexibly adjusted by adding microalloying elements and an externally applied magnetic field, so that the accessibility of obtaining the target use performance is improved, and the welding process design process is simplified;
4) The popularization applicability is wide: the technical scheme of the invention is suitable for various material types, such as carbon steel, alloy steel, stainless steel, special steel, titanium and titanium alloy, zirconium alloy, tantalum, hastelloy, high boron steel, copper and copper alloy, and the like, and has wide application prospect in the all-position welding fields of transverse welding, vertical welding, and the like;
5) The efficiency of the welding process is improved: according to the technical scheme, parameters related to welding process design are more diversified, and the selection of welding parameters and a formula is more standardized and normalized through the support of an expert system process library and a fuzzy neural network model, so that a welding process is simpler and more convenient, trial-and-error and adjustment time is reduced, and welding efficiency and welding quality are greatly improved;
in summary, the high-efficiency deep-melting arc welding auxiliary welding method provided by the invention has excellent advantages in the aspects of improving the welding efficiency, optimizing the weld joint structure, expanding the process window and improving the simplicity of the process design, so that the technical scheme has a wide application prospect in the field of deep-melting arc welding, and is expected to promote the technical progress and industrial development of the field.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the invention, and that other drawings can be obtained from these drawings without inventive faculty for a person skilled in the art.
The structures, proportions, sizes, etc. shown in the drawings are shown only in connection with the present disclosure, and are not intended to limit the scope of the invention, since any modification, variation in proportions, or adjustment of the size, etc. of the structures, proportions, etc. should be considered as falling within the spirit and scope of the invention, without affecting the effect or achievement of the objective.
FIG. 1 is a schematic illustration of a microalloying and magnetic field assisted high efficiency deep melt arc welding process;
FIG. 2 is a process for generating an expert system welding process library recipe;
FIG. 3 is a schematic diagram of magnetic fields of different modes;
FIG. 4 is a test plan for high efficiency deep-melting arc welding of 9Ni steel;
FIG. 5 is the result of a 9Ni steel high efficiency deep melt arc weld joint tensile test;
FIG. 6 is the result of a low temperature impact test of a 9Ni steel high efficiency deep melt arc welded joint.
Detailed Description
In order to make the objects, features and advantages of the present invention more comprehensible, the technical solutions in the embodiments of the present invention are described in detail below with reference to the accompanying drawings, and it is apparent that the embodiments described below are only some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The technical scheme of the invention is further described below by the specific embodiments with reference to the accompanying drawings.
Referring to fig. 1-2, the present invention provides a technical solution:
an efficient deep-melting arc welding auxiliary welding method comprises the steps of selecting an auxiliary welding process in an expert system process library according to welding characteristics of a welding material to weld the welding material, wherein the welding characteristics comprise chemical components, mechanical properties, use requirements, plate thickness, type and size of a groove and welding working conditions of a butt joint gap of the welding material, and the auxiliary welding process comprises at least one of a microalloying auxiliary process, a magnetic field auxiliary process, a microalloying coupling magnetic field auxiliary process and a welding formula generated by a prediction model established by a fuzzy neural network model.
Further, the welding formula is obtained after training a fuzzy neural network model based on at least one of a micro-alloying auxiliary process, a magnetic field auxiliary process and a micro-alloying coupling magnetic field auxiliary process.
The micro-alloying auxiliary process, the magnetic field auxiliary process and the micro-alloying coupling magnetic field auxiliary process in the expert system process library provide data sources for the fuzzy neural network model, the output of the fuzzy neural network model is the selection of optimized welding process parameters, the welding process parameters comprise deep-melting arc welding process parameters, alloy parameters and magnetic field parameters, the fuzzy neural network model not only considers the optimization of the welding process parameters, but also comprehensively considers the influence of the auxiliary welding process on the weld joint structure and performance, so that a more comprehensive and effective welding formula is obtained, the auxiliary welding process can verify the accuracy of the fuzzy neural network model, and the fuzzy neural network model is optimized according to actual conditions, and the two complement each other.
Preferably, the auxiliary welding process may be selected according to the type and model of the welding material.
The expert system process library can be classified according to material characteristics and can be classified into carbon steel, alloy steel, stainless steel, special steel, titanium and titanium alloy, zirconium alloy, tantalum, hastelloy, high boron steel, copper and copper alloy.
The specific welding process selection method comprises the following steps: when the welding materials are matched with the same materials from the expert system process library, the welding materials are welded according to the welding formula related to the materials, the same materials can be understood as the same class and the same type of materials, for example, two materials belong to carbon steel, namely the same class of materials, Q215 carbon steel and Q235 carbon steel belong to the same class and different types of materials, and alloy steel and stainless steel are non-same class of materials.
When the welding materials cannot be matched with the same materials from the expert system process library, preferably, when the welding materials are matched with similar materials but different types from the expert system process library, one of a micro-alloying auxiliary process, a magnetic field auxiliary process and a micro-alloying coupling magnetic field auxiliary process which are related to the materials closest to the chemical components of the welding materials is selected from the expert system process library, and welding process parameters meeting requirements are stored in the expert system process library after welding is implemented.
Preferably, when the welding materials cannot be matched with similar materials from the expert system process library, if only welding experiments are performed for multiple times to find welding process parameters meeting requirements, the welding efficiency and welding quality are low due to great waste of manpower and material resources, and the fuzzy neural network model is adopted at the moment, and the specific method is as follows: and selecting performance parameters related to a material closest to the chemical composition of the welding material from the expert system process library to train the fuzzy neural network model, calculating the trained fuzzy neural network model to obtain the welding formula meeting the requirement, and storing the welding formula in the expert system process library.
Further, forming the micro-alloying assistance process in the expert system process library comprises the steps of:
step one: selecting microalloy parameters according to the welding characteristics of the welding material, wherein the microalloy parameters comprise the types, the shapes and the sizes of microalloy elements,
step two: presetting a welding medium containing micro-alloy elements at a butt joint gap, welding a welding medium wire or a welding lug, welding the welding material by using the welding medium according to a deep-melting arc welding process, wherein the deep-melting arc welding process has deep-melting arc welding process parameters including welding current, welding voltage, welding speed, gas flow rate and distance from a tungsten needle tip to the surface of the welding material,
step three: obtaining corrosion of a welded joint sample after grinding and polishing and detecting performance parameters of the joint sample, wherein the performance parameters comprise strength, tissue composition, low-temperature toughness, corrosion resistance and fatigue life of the joint sample,
step four: judging whether the performance parameter of the welding joint is higher than a specified value of a national standard, acquiring the deep-melting arc welding process parameter and the microalloy parameter of which the performance parameter meets the requirement, storing the deep-melting arc welding process parameter and the microalloy parameter in the expert system process library to form the microalloy auxiliary process, if the joint does not meet the requirement, changing at least one factor of the deep-melting arc welding process parameter or the microalloy parameter, re-welding and detecting the performance parameter of the joint until the deep-melting arc welding process parameter and the microalloy parameter meeting the requirement are obtained; and/or the number of the groups of groups,
forming the magnetic field assisted process in the expert system process library comprises the steps of:
step one: installing a magnetic field device according to the welding characteristics of the welding material and setting magnetic field parameters, wherein the magnetic field parameters comprise a magnetic field type, a magnetic field intensity, a mode and a magnetic field frequency,
step two: welding the welding material according to the deep-melting arc welding process,
step three: obtaining a welded joint sample and detecting the performance parameter of the joint sample,
step four: judging whether the performance parameter of the welding joint is higher than a specified value of a national standard, acquiring the deep-melting arc welding process parameter and the magnetic field parameter of which the performance parameter meets the requirement, storing the deep-melting arc welding process parameter and the magnetic field parameter in the expert system process library to form the magnetic field auxiliary process, if the performance parameter of the joint does not meet the requirement, changing at least one factor of the deep-melting arc welding process parameter or the magnetic field parameter, re-welding and detecting the performance parameter of the joint until the deep-melting arc welding process parameter and the magnetic field parameter meeting the requirement are obtained;
the magnetic field types comprise a transverse magnetic field, a longitudinal magnetic field, an axial magnetic field, a sharp angle magnetic field, a rotating magnetic field and a composite magnetic field thereof, and referring to fig. 3, the magnetic field modes comprise a constant steady magnetic field, a pulse magnetic field, an alternating magnetic field and a bias sinusoidal magnetic field, wherein (a) is a schematic diagram of the constant steady magnetic field, and the magnetic induction intensity is kept unchanged in the welding process if the constant steady magnetic field is applied; (b) The method is characterized in that a pulse magnetic field diagram is provided, and a required magnetic field is output by adjusting four parameters, namely peak magnetic induction Bp, base magnetic induction Bb, pulse frequency f and peak time Tp; (c) As an alternating magnetic field schematic diagram, a required magnetic field is output by adjusting the peak magnetic induction Bm and the pulse frequency f; (d) The magnetic field is a schematic diagram of a bias sinusoidal magnetic field, is equivalent to a magnetic field formed by coupling an alternating magnetic field with a constant magnetic field, and outputs a required magnetic field by adjusting a sinusoidal peak Bm of magnetic induction intensity, a bias value B0 of magnetic induction intensity and a pulse frequency f; and/or the number of the groups of groups,
forming the micro-alloyed coupling magnetic field assisting process in the expert system process library comprises the following steps:
step one: selecting the microalloy parameters according to the welding characteristics of the welding materials, installing the magnetic field device and setting the magnetic field parameters,
step two: welding the welding material according to the technological parameters of the deep-melting arc welding,
step three: obtaining a welded joint sample, detecting the performance parameter of the joint sample,
step four: judging whether the performance parameter of the welding joint is higher than a specified value of a national standard, if the joint meets the requirement, acquiring the deep-melting arc welding process parameter, the microalloy parameter and the magnetic field parameter which meet the requirement, storing the deep-melting arc welding process parameter, the microalloy parameter and the magnetic field parameter in the expert system process library to form the microalloy coupling magnetic field auxiliary process, and if the performance parameter of the joint does not meet the requirement, changing at least one factor of the deep-melting arc welding process parameter, the magnetic field parameter and the microalloy parameter, and re-welding and detecting the performance parameter of the joint until the deep-melting arc welding process parameter, the magnetic field parameter and the microalloy parameter which meet the requirement are obtained.
According to the three auxiliary welding process steps, the most preferable performance parameters and corresponding welding characteristics of the welding materials are stored in the expert system process library by carrying out a large number of welding experiments or welding experiences on various welding materials in the early stage, so that the welding quality, efficiency and economy can be greatly improved in the subsequent engineering practice process compared with the welding characteristics of the welding materials, and the requirements of specific applications can be met.
Because the relation among the factors is complex and mutually influences, the most preferable technological parameters can be determined after comprehensive consideration, the grain structure and performance of the welding seam can be further optimized by reasonably selecting the microalloy parameters and the magnetic field parameters, and when the microalloy coupling magnetic field auxiliary process is selected, the advantages of microalloy and magnetic field auxiliary are comprehensively considered, so that the synergistic effect between the microalloy and the magnetic field auxiliary is realized, and the optimal welding effect is obtained.
Taking 9Ni steel as an example, the process of searching the most preferable performance parameters of the welding materials and the corresponding welding characteristics and storing the welding characteristics in the expert system process library is as follows:
the 9Ni steel is a structural material with high strength (> 700 MPa), good low-temperature impact toughness and low cost, has wide application in the construction of LNG storage tanks, pipelines and transport ships, and the chemical compositions of the 9Ni steel are shown in Table 1.
Table 1 chemical composition (wt.%) of 9Ni steel
In the welding process, because tempering treatment is difficult to carry out, the low-temperature toughness of a welding line in the 9Ni steel joint is obviously lower than that of a base metal in general, in order to improve the welding efficiency and the low-temperature toughness of the welding line of the 9Ni steel joint, on one hand, a high-efficiency deep-melting arc welding technology is adopted to carry out high-blunt-edge backing welding on a medium plate, and on the other hand, a metal element and an externally applied magnetic field auxiliary welding technology are added into the welding line to improve the low-temperature toughness of the welding line, and the specific method of the technology is as follows: firstly, ni and Mo elements are added into a welding seam to change the components and the structural performance of the welding seam, then an exciting coil is preset on a welding gun to generate an axial alternating magnetic field, and the Lorentz force is generated to break the solidification dendrite of a liquid molten pool, so that the grain size of the welding seam is thinned.
FIG. 4 is a test scheme of 9Ni steel high-efficiency deep-melting arc welding, corresponding Ni wires/sheets and Mo wires are filled or preset in a welding line according to different test purposes, and backing welding tests under different conditions are carried out, wherein the backing welding tests are respectively (1) filling the Ni wires in the welding line; (2) filling the welding line with Ni sheets and Mo wires; (3) filling Ni wires in the welding seam and externally applying an alternating magnetic field; (4) Filling Ni sheets and Mo wires in a welding line, externally applying an alternating magnetic field, generating 12 groups of process tests under different welding conditions through different combinations, obtaining joint sample preparation under different conditions after backing welding of each group of butt joint samples by adopting high-efficiency deep-melting arc welding, obtaining the required joint sample preparation by adopting a wire cutting method, and then carrying out corresponding tests by means of a Vickers hardness tester, a universal tensile tester and a pendulum impact tester, as shown in Table 2.
The conditions set in the Vickers hardness test process are as follows: the method comprises the steps of loading a load of 1000g, loading dwell time of 5s, measuring a distance of 0.5mm, drawing a hardness value distribution diagram corresponding to a weld zone, a heat affected zone and a base metal after the test is finished, and performing impact test on the weld zone, the weld line and the heat affected zone by using a metal pendulum impact tester, so that the method is suitable for measuring the performance of the joint sample by using a flat plate tensile test method, transversely cutting the sample along the direction of a vertical weld line, roughly grinding the upper surface, the lower surface and the side surface of the whole sample to remove stress concentration, setting the tensile test speed to be 3mm/min, and setting the initial strain rate to be 0.002/s.
Table 2 9Ni steel high efficiency deep melting arc welding process parameters
Fig. 5 shows the result of the elongation test of the 9Ni steel high-efficiency deep-melting arc welding joint, wherein the breaking positions are all in the base material area during the elongation test, and the tensile strength of the joint sample is slightly higher than the average strength of the base material, which means that the joint weld zone has the tensile strength superior to the base material area after the high-efficiency deep-melting arc welding, and the tensile service performance of the material is not reduced after the welding processing.
FIG. 6 shows the result of the low temperature impact test of the 9Ni steel high-efficiency deep-melting arc welding joint, the impact performance of the welding seam can be effectively improved by the addition or filling of Ni element and Mo element from the low temperature impact result of the joints No. 1-No. 4, researches show that the low temperature toughness of the welding seam is mainly improved by thinning the grain size of the Ni element and the Mo element, in the joints No. 1-No. 3, the low temperature toughness of the welding seam is improved after the Mo element is added, the joints No.6, no.5 and No.4 are respectively improved by 16.3J (139%), 16.7J (17.2%) and 24J (52.9%) relative to the joints No.1, no.2 and No.3, and the improvement effect of the poor impact performance of the welding seam is more obvious, which shows that the Mo element has outstanding effect in improving the low temperature toughness of the welding seam of the 9Ni steel, the addition of the Mo element can further improve the low temperature toughness of the welding seam on the basis of good toughness, and after the external magnetic field, the low temperature toughness of the joint No.7 is improved compared with the low temperature toughness of the joint No.1, the joint No.9, and the external magnetic field is improved by the toughness of the joint No.9, compared with the low temperature toughness of the joint No.9, and the joint No.8, the material has improved toughness of the joint No. 19.
As can be seen from the low-temperature toughness results of the joint with different Ni element contents by comparing the magnetic field and the Mo element, in the conventional 9Ni steel material, the low-temperature toughness of the welding seam can be improved to be more than the standard value by adding the Mo element, the external magnetic field and the Mo element coupling magnetic field (27J), wherein the external magnetic field has the best effect of improving the low-temperature toughness of the welding seam, and in the joint with the 0.5mm Ni piece, the external magnetic field and the Mo element can improve the low-temperature toughness of the welding seam, but the low-temperature toughness of the welding seam is reduced when the Mo element is coupled with the magnetic field.
For 9Ni steel, the effect of improving the low-temperature toughness of the welding line by adding Ni element is most obvious, and the coupling of the Ni element and the external magnetic field is also beneficial to improving the low-temperature toughness of the welding line, so that the effect of improving the low-temperature toughness of the welding line of the 9Ni steel by high-efficiency deep-melting arc welding and adding Ni element, the external magnetic field and the coupling of the Ni element is better, and finally, the welding characteristics and the performance parameters of the 9Ni steel are stored in the expert system process library for later selection.
Further, the fuzzy neural network model comprises an input layer, a fuzzification layer, a fuzzy rule calculation layer and an output layer, wherein the input layer is used for receiving input parameters, the output layer is used for extracting output parameters, and the input parameters pass through the input layer, the fuzzification layer, the fuzzy rule calculation layer and the output layer in sequence to finally obtain the output parameters;
the process for forming the fuzzy neural network model comprises the following steps:
step one: setting an input layer, a fuzzification layer, a fuzzy rule calculation layer and an output layer for the fuzzy neural network model, wherein the input layer is used for receiving input parameters, the input parameters are performance parameters in the expert system process library, the output parameters are the welding formulas, and the output layer is used for extracting the output parameters and inputting the input parameters into the neural network model;
step two: the input parameters are normalized, the purpose of the normalization is to enable the unified measurement standard of each parameter to facilitate subsequent calculation, the normalized input parameters are divided into three data sets, namely a training set, a testing set and a verification set, and the training set, the testing set and the verification set are all normalized welding process parameter sets;
step three: respectively carrying out fuzzification on the input parameters normalized in the training set, the testing set and the verification set and carrying out fuzzy rule calculation, namely firstly inputting the welding process parameters in the training set into the neural network model, training to complete the neural network model, inputting the welding process parameters in the testing set into the neural network model to test the performance of the neural network model, finally inputting the welding process parameters in the verification into the neural network model to verify the accuracy of the model, and calculating the membership degree of each input parameter by adopting a Gaussian membership function to be the fuzzification process;
preferably, 80% of data is the training set, 15% of data is the test set, 5% of data is the verification set, the training set is used for training the fuzzy neural network model, the test set is used for evaluating the performance of the fuzzy neural network model, and the verification set is used for adjusting the hyper-parameters of the fuzzy neural network model and preventing overfitting;
step four: and extracting the output parameters.
The fuzzy neural network model can be continuously optimized, for example, target performance parameters of the welding materials are input into the fuzzy neural network model to be calculated to obtain the welding formula, then the welding materials are welded according to the auxiliary welding process related by the welding formula, performance parameters of welded joint samples are detected, the welding efficiency can be greatly improved by utilizing the fuzzy neural network model, and if the detected result deviates from the target, the internal structural parameters of the fuzzy neural network model can be adjusted in a targeted manner to improve the accuracy.
The fuzzy neural network model can establish complex relevance among a plurality of factors, and considers interaction among various factors, so that a welding formula is more accurate and comprehensive, a large amount of experimental data can be learned and generalized, the existing knowledge and experience are fully utilized to avoid repeatability tests, a welding formula meeting requirements can be quickly generated according to performance parameter requirements of an actual joint, the welding formula guides an actual welding process, and stability, controllability and welding efficiency of a welding process are improved.
The formula generated based on the fuzzy neural network model can more comprehensively and accurately optimize welding process parameters, so that better joint performance parameters are realized, and welding quality and efficiency are improved.
Further, calculating the membership degree of each input parameter by using a Gaussian membership function, wherein the Gaussian membership function is as follows:
wherein x is j Lambda for the j-th said input parameter i j For the input parameter x jj The ith said membership, μ i j Sum sigma i j J=1, 2,., k, k is the number of input parameters, i=1, 2,., n, n is the number of fuzzy subsets;
performing fuzzy calculation on the membership degree of each input parameter in the fuzzy rule calculation layer by using a continuous multiplication operator to obtain a continuous product of the membership degree, namely the fuzzy rule calculation process,
wherein omega is i I=1, 2,..n, which is the continuous product of the membership of each parameter;
the output parameter obtained based on the fuzzy rule calculation result and the weight coefficient is the process of extracting the output parameter, and the output parameter is the welding formula:
wherein y is i For the ith output parameter, p i k And the weight coefficient is the weight coefficient.
Further, a gradient descent method is adopted to calculate the weight coefficient of each input parameter, the weight coefficient is obtained by iterative calculation of the input parameter and the output parameter, so as to improve the training effect and the prediction accuracy of the fuzzy neural network model, for example, the weight coefficient of the ith step is obtained by calculation of the input parameter and the output parameter of the ith step, and the output parameter of the (i+1) th step is obtained by calculation of the weight coefficient of the ith step:
wherein p is i j (g) And (3) representing the weight coefficient of the g-th iteration, wherein alpha is the learning rate, and e is the output error.
Further, how to select the welding process during specific execution needs to make a corresponding rule, the magnetic field auxiliary process is prioritized according to the welding cost and the simplicity of operation, the micro-alloying auxiliary process is considered, the micro-alloying coupling magnetic field auxiliary process is considered finally, the magnetic field device is convenient to install and can be continuously used once, and welding wires or welding sheets are preset for each welding of the micro-alloying technology, which increases the time cost, so that the priority of the auxiliary welding process is selected as follows: the magnetic field assisting process is more than the micro-alloying coupling magnetic field assisting process.
Further, when the difference between the upper limit and the lower limit of the welding current threshold is smaller than 50A or the difference between the upper limit and the lower limit of the welding speed threshold is smaller than 0.5mm/s or the difference between the upper limit and the lower limit of the distance from the tip of the tungsten needle to the surface of the welding material to the upper limit and the lower limit of the threshold is smaller than 0.1mm, the auxiliary welding process is switched, and the magnetic field auxiliary process is switched to the micro-alloying auxiliary process and the micro-alloying auxiliary process is switched to the micro-alloying coupling magnetic field auxiliary process, wherein the difference between the upper limit and the lower limit of the threshold of a certain parameter is the difference between the maximum value and the minimum value of the parameter.
The high-efficiency deep-melting arc welding can be used for once welding through a plate with the thickness of 3-16 mm, a groove is needed to be formed in the plate with the thickness of large thickness to be welded through once, the groove is of a V shape, the constraint relation between the plate thickness of the welding material and the groove is as follows, if the plate thickness is smaller than 12mm, the welding material does not need to be provided with the groove, if the plate thickness is larger than or equal to 12mm, the included angle of the groove is 56-64 degrees, and the blunt edge thickness of the groove is 8-12mm.
In the design of the welding process specification, different microelements are selected for different materials. Welding materials include, but are not limited to: low carbon steel, duplex stainless steel, high strength steel, special steel, titanium alloy, zirconium alloy, tantalum, hastelloy, high boron steel, cupronickel (nickel copper), and the like, the microalloy elements commonly involved in welding include Ti, mn, ni, mg, V, cr, co, nb, mo, zr, al, ca, and for inactive microalloy elements, the components thereof exist in pure metal form, and for active microalloy elements, the components thereof exist in alloy form, the welding medium formed by the microalloy elements comprises a welding wire or a welding lug, the diameter of the welding wire is in the range of 0.1mm to 3mm, the width dimension of the welding lug is in the range of 0.1mm to 1mm, the welding medium is processed into the welding wire when the demand of the microalloy elements is small, the welding lug is processed into the welding lug when the demand of the microalloy elements is large or the blunt edge thickness of a groove of the welding material is large, the thickness dimension of the welding lug is smaller than the plate thickness of the welding material or the blunt edge thickness of the groove of the welding material, and the length dimension of the welding lug is equal to or slightly smaller than the length of the welding seam of the welding material.
The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. An efficient deep-melting arc welding auxiliary welding method is characterized in that: selecting an auxiliary welding process in an expert system process library according to welding characteristics of a welding material to weld the welding material, wherein the auxiliary welding process comprises at least one of a micro-alloying auxiliary process, a magnetic field auxiliary process, a micro-alloying coupling magnetic field auxiliary process and a welding formula generated by a prediction model established by a fuzzy neural network model;
forming the micro-alloying assistance process in the expert system process library comprises the steps of:
step one: the microalloy parameters are selected according to the welding characteristics of the welding material,
step two: welding the welding material according to a deep-melting arc welding process using a welding medium, the deep-melting arc welding process having deep-melting arc welding process parameters,
step three: acquiring a welded joint sample and detecting performance parameters of the joint sample,
step four: obtaining the deep-melting arc welding process parameters and the microalloy parameters of which the performance parameters meet requirements, storing the deep-melting arc welding process parameters and the microalloy parameters in the expert system process library to form the microalloying auxiliary process, and/or,
forming the magnetic field assisted process in the expert system process library comprises the steps of:
step one: installing a magnetic field device according to the welding characteristics of the welding materials and setting magnetic field parameters,
step two: welding the welding material according to the deep-melting arc welding process,
step three: obtaining a welded joint sample and detecting the performance parameter of the joint sample,
step four: obtaining the deep-melting arc welding process parameters and the magnetic field parameters of which the performance parameters meet requirements, storing the deep-melting arc welding process parameters and the magnetic field parameters in the expert system process library to form the magnetic field auxiliary process, and/or,
forming the micro-alloyed coupling magnetic field assisting process in the expert system process library comprises the following steps:
step one: selecting the microalloy parameters according to the welding characteristics of the welding materials, installing the magnetic field device and setting the magnetic field parameters,
step two: welding the welding material according to the technological parameters of the deep-melting arc welding,
step three: obtaining a welded joint sample, detecting the performance parameter of the joint sample,
step four: acquiring the deep-melting arc welding process parameters, the microalloy parameters and the magnetic field parameters of which the performance parameters meet requirements, and storing the deep-melting arc welding process parameters, the microalloy parameters and the magnetic field parameters in the expert system process library to form the microalloying coupling magnetic field auxiliary process;
the process for forming the fuzzy neural network model comprises the following steps:
step one: setting an input layer, a fuzzification layer, a fuzzy rule calculation layer and an output layer for the fuzzy neural network model, wherein the input layer is used for receiving input parameters, the input parameters are performance parameters in the expert system process library, and the output layer is used for extracting output parameters;
step two: normalizing the input parameters and dividing the normalized input parameters into a training set, a testing set and a verification set;
step three: and fuzzifying the input parameters, calculating the membership degree of each input parameter by adopting a Gaussian membership function to obtain the fuzzification process, and then calculating a fuzzy rule.
2. The method of claim 1, wherein the welding recipe is obtained by training a fuzzy neural network model based on at least one of a microalloying auxiliary process, a magnetic field auxiliary process, and a microalloying coupling magnetic field auxiliary process.
3. The method of claim 1, wherein the expert system process library is categorized according to material characteristics, and the welding materials select the auxiliary welding process according to the type and model of the expert system process library.
4. The method according to claim 3, wherein when the welding materials are matched to similar materials but different types from the expert system process library, one of a micro-alloying auxiliary process, a magnetic field auxiliary process and a micro-alloying coupling magnetic field auxiliary process related to the material closest to the chemical composition of the welding materials is selected from the expert system process library, and welding process parameters meeting requirements are stored in the expert system process library after welding is implemented.
5. The method according to claim 3, wherein when the welding materials cannot be matched with similar materials from the expert system process library, the expert system process library is selected to train the fuzzy neural network model according to performance parameters related to materials closest to the chemical components of the welding materials, and the trained fuzzy neural network model is calculated to obtain the welding formula meeting the requirements and the welding formula is stored in the expert system process library.
6. The efficient deep arc welding-assisted welding method of claim 1, wherein the gaussian membership function is:
wherein x is j Lambda for the j-th said input parameter i j For the input parameter x j The ith said membership, μ i j Sum sigma i j J=1, 2,., k, k is the number of input parameters, i=1, 2,., n, n is the number of fuzzy subsets, respectively, for the center and width of the gaussian membership function.
7. The method of claim 6, wherein performing fuzzy calculation on the membership of each input parameter using a continuous multiplication operator in the fuzzy rule calculation layer to obtain a continuous product of the membership is the fuzzy rule calculation process,
wherein omega is i I=1, 2,..n, which is the continuous product of the membership of each parameter;
and obtaining the output parameters based on the result of the fuzzy rule calculation and the weight coefficient:
wherein y is i For the ith output parameter, p i k And the weight coefficient is the weight coefficient.
8. The efficient deep-arc welding-assisted welding method according to claim 7, characterized in that the weight coefficient p i k The iterative updating is carried out by adopting a gradient descent method,
wherein p is i j (g) And (3) representing the weight coefficient of the g-th iteration, wherein alpha is the learning rate, and e is the output error.
9. The efficient deep-arc welding-assisted method of any one of claims 1-8, wherein the priority of selecting the auxiliary welding process is: the magnetic field assisting process is more than the micro-alloying coupling magnetic field assisting process.
10. The efficient deep-arc welding-assisted welding method of claim 9, wherein switching the assisted welding process when a difference between upper and lower limits of a welding current threshold is less than 50A or a difference between upper and lower limits of a welding speed threshold is less than 0.5mm/s or a difference between a tungsten needle tip and an upper and lower limit of a welding material surface distance threshold is less than 0.1mm comprises switching the magnetic field-assisted process to the microalloyed-assisted process and the microalloyed-assisted process to the microalloyed-coupled magnetic field-assisted process.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311064998.7A CN116900450B (en) | 2023-08-22 | 2023-08-22 | High-efficiency deep-melting arc welding auxiliary welding method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311064998.7A CN116900450B (en) | 2023-08-22 | 2023-08-22 | High-efficiency deep-melting arc welding auxiliary welding method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116900450A CN116900450A (en) | 2023-10-20 |
| CN116900450B true CN116900450B (en) | 2024-01-02 |
Family
ID=88366877
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311064998.7A Active CN116900450B (en) | 2023-08-22 | 2023-08-22 | High-efficiency deep-melting arc welding auxiliary welding method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116900450B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101862913A (en) * | 2010-05-13 | 2010-10-20 | 重庆大学 | Electromagnetic current coupling field assisted hybrid melting-brazing method for laser-TIG arc and equipment |
| CN109865916A (en) * | 2019-03-19 | 2019-06-11 | 山东大学 | A kind of robot welding process parameter optimizing method based on CBR and RBR |
| CN111177976A (en) * | 2019-12-25 | 2020-05-19 | 广东省焊接技术研究所（广东省中乌研究院） | Arc welding seam forming accurate prediction method based on deep learning |
| CN112122758A (en) * | 2020-09-22 | 2020-12-25 | 哈尔滨工业大学（威海） | Ni element-regulated magnetic field-assisted resistance unit welding method for aluminum alloy and steel |
| CN112643175A (en) * | 2020-12-16 | 2021-04-13 | 天津大学 | Method and device for manufacturing nickel-based alloy-low alloy high-strength steel functionally gradient material |
| CN112809135A (en) * | 2021-01-15 | 2021-05-18 | 广东福维德焊接股份有限公司 | Automatic efficient deep-melting argon arc welding process for 9Ni steel |
| CN113385820A (en) * | 2021-06-11 | 2021-09-14 | 绍兴文理学院 | Double-magnetic-field and ultrasonic-wave cooperative auxiliary laser deep melting welding device |
| CN115255555A (en) * | 2022-08-09 | 2022-11-01 | 惠州丰采贵金属制造有限公司 | Welding process |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6950813B2 (en) * | 2001-04-23 | 2005-09-27 | Hrl Laboratories, Llc | Fuzzy inference network for classification of high-dimensional data |
| US20150122781A1 (en) * | 2013-11-04 | 2015-05-07 | Illinois Tool Works Inc. | System and method for selecting weld parameters |
-
2023
- 2023-08-22 CN CN202311064998.7A patent/CN116900450B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101862913A (en) * | 2010-05-13 | 2010-10-20 | 重庆大学 | Electromagnetic current coupling field assisted hybrid melting-brazing method for laser-TIG arc and equipment |
| CN109865916A (en) * | 2019-03-19 | 2019-06-11 | 山东大学 | A kind of robot welding process parameter optimizing method based on CBR and RBR |
| CN111177976A (en) * | 2019-12-25 | 2020-05-19 | 广东省焊接技术研究所（广东省中乌研究院） | Arc welding seam forming accurate prediction method based on deep learning |
| CN112122758A (en) * | 2020-09-22 | 2020-12-25 | 哈尔滨工业大学（威海） | Ni element-regulated magnetic field-assisted resistance unit welding method for aluminum alloy and steel |
| CN112643175A (en) * | 2020-12-16 | 2021-04-13 | 天津大学 | Method and device for manufacturing nickel-based alloy-low alloy high-strength steel functionally gradient material |
| CN112809135A (en) * | 2021-01-15 | 2021-05-18 | 广东福维德焊接股份有限公司 | Automatic efficient deep-melting argon arc welding process for 9Ni steel |
| CN113385820A (en) * | 2021-06-11 | 2021-09-14 | 绍兴文理学院 | Double-magnetic-field and ultrasonic-wave cooperative auxiliary laser deep melting welding device |
| CN115255555A (en) * | 2022-08-09 | 2022-11-01 | 惠州丰采贵金属制造有限公司 | Welding process |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116900450A (en) | 2023-10-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Suresh et al. | Sustainable friction stir spot welding of 6061-T6 aluminium alloy using improved non-dominated sorting teaching learning algorithm | |
| Katherasan et al. | Simulation and parameter optimization of flux cored arc welding using artificial neural network and particle swarm optimization algorithm | |
| Bandhu et al. | Assessment of weld bead geometry in modified shortcircuiting gas metal arc welding process for low alloy steel | |
| Saad et al. | Evaluation of welding processes based on multi-dimensional sustainability assessment model | |
| Guo et al. | Microstructure and mechanical properties of an underwater wet welded dissimilar ferritic/austenitic steel joint | |
| Wang et al. | Effect of heat input on MA constituent and toughness of coarse grain heat-affected zone in an X100 pipeline steel | |
| Pathak et al. | Three-dimensional finite element analysis to predict the different zones of microstructure in submerged arc welding | |
| Katherasan et al. | Flux cored arc welding parameter optimization using particle swarm optimization algorithm | |
| Mohammadijoo et al. | Characterization of HAZ of API X70 microalloyed steel welded by cold-wire tandem submerged arc welding | |
| Rajalingam et al. | Optimization of laser beam spot welding (LBSW) parameters to maximize the load bearing capability of AHS-DP1000 steel lap joints | |
| Carvalho et al. | Development of optimal deposition strategies for cladding of Inconel 625 on carbon steel using wire arc additive manufacturing | |
| Yin et al. | Microstructures and their distribution within HAZ of X80 pipeline steel welded using hybrid laser-MIG welding | |
| Kumar et al. | On the influence of welding stainless steel on microstructural development and mechanical performance | |
| CN116900450B (en) | High-efficiency deep-melting arc welding auxiliary welding method | |
| Kumar et al. | Effect of process parameters on microhardness and microstructure of heat affected zone in submerged arc welding | |
| Vykunta Rao et al. | Vibratory weld conditioning during gas tungsten arc welding of al 5052 alloy on the mechanical and micro-structural behavior | |
| Katherasan et al. | Modeling and optimization of flux cored arc welding by genetic algorithm and simulated annealing algorithm | |
| Math et al. | Analysis optimization and modelling of CO2 welding process parameters in fabrication of mild steel plates | |
| Dadi et al. | A review paper on optimization of shielded metal arc welding parameters for welding of (Ms) Sa-516 Gr. 70 plate by using Taguchi approach | |
| Komerla et al. | The effect of beam oscillations on the microstructure and mechanical properties of electron beam welded steel joints | |
| Tashev et al. | Mathematical modeling and optimization of parameters of the mode for tungsten-inert gas remelting with nanomodification of the surface layer | |
| Kalpana et al. | Implementation of generalized regression neural network to establish a relation between vibration parameters and time of vibration for welded joints | |
| Wiednig et al. | Toughness evaluation of EB welds | |
| Poonguzhali et al. | Application of ANN modelling and GA optimization for improved creep and corrosion properties of spin-arc welded AA5083-H111 alloy | |
| Datta et al. | Optimisation of percent dilution and HAZ width of submerged arc weldment using Taguchi philosophy coupled with fuzzy inference system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |