CN117260053B - Special steel welding control method and system - Google Patents
Special steel welding control method and system Download PDFInfo
- Publication number
- CN117260053B CN117260053B CN202311519228.7A CN202311519228A CN117260053B CN 117260053 B CN117260053 B CN 117260053B CN 202311519228 A CN202311519228 A CN 202311519228A CN 117260053 B CN117260053 B CN 117260053B
- Authority
- CN
- China
- Prior art keywords
- welding
- low
- temperature toughness
- joint
- parameters
- 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 335
- 229910000831 Steel Inorganic materials 0.000 title claims abstract description 134
- 239000010959 steel Substances 0.000 title claims abstract description 134
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000004458 analytical method Methods 0.000 claims abstract description 125
- 239000011229 interlayer Substances 0.000 claims abstract description 41
- 238000012937 correction Methods 0.000 claims abstract description 39
- 239000010410 layer Substances 0.000 claims description 37
- 238000010438 heat treatment Methods 0.000 claims description 28
- 238000010276 construction Methods 0.000 claims description 24
- 238000012360 testing method Methods 0.000 claims description 17
- 238000003066 decision tree Methods 0.000 claims description 8
- 238000012795 verification Methods 0.000 claims description 8
- 238000013527 convolutional neural network Methods 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 5
- 238000005457 optimization Methods 0.000 abstract description 8
- 230000000694 effects Effects 0.000 abstract description 5
- 238000012545 processing Methods 0.000 abstract description 3
- 239000000463 material Substances 0.000 description 15
- 230000008569 process Effects 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000011176 pooling Methods 0.000 description 3
- 230000004913 activation Effects 0.000 description 2
- 238000005314 correlation function Methods 0.000 description 2
- 239000003949 liquefied natural gas Substances 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 229910000997 High-speed steel Inorganic materials 0.000 description 1
- 229910000639 Spring steel Inorganic materials 0.000 description 1
- 229910000746 Structural steel Inorganic materials 0.000 description 1
- 229910001315 Tool steel Inorganic materials 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 238000000137 annealing Methods 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000007373 indentation Methods 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 229910001220 stainless steel Inorganic materials 0.000 description 1
- 239000010935 stainless steel Substances 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 239000013598 vector 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
- B23K31/00—Processes relevant to this subclass, specially adapted for particular articles or purposes, but not covered by only one of the preceding main groups
- B23K31/02—Processes relevant to this subclass, specially adapted for particular articles or purposes, but not covered by only one of the preceding main groups relating to soldering or welding
-
- 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
- B23K37/00—Auxiliary devices or processes, not specially adapted to a procedure covered by only one of the preceding main groups
-
- 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
- B23K2103/00—Materials to be soldered, welded or cut
- B23K2103/02—Iron or ferrous alloys
- B23K2103/04—Steel or steel alloys
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Physics & Mathematics (AREA)
- Optics & Photonics (AREA)
- Investigating And Analyzing Materials By Characteristic Methods (AREA)
Abstract
The invention relates to the technical field of welding processing, and provides a special steel welding control method and system, wherein the method comprises the following steps: acquiring preset parameters and basic low-temperature toughness parameters, and setting constraint conditions; randomly combining a plurality of welding parameter combinations, constructing an objective function, optimizing, randomly selecting a first welding parameter combination, and acquiring interlayer temperature and initial fitness; when the constraint condition is met, a metallographic image set is acquired and is input into a model, the target function and the initial fitness are combined, the correction fitness is calculated and the optimization is continued, finally, the optimal welding parameter set is acquired and is combined for welding control, the technical problem that the low-temperature toughness of the low-temperature special steel welding joint is low and joint fracture is likely to occur is solved, excessive residual stress and deformation are avoided, the low-temperature toughness of the welding joint is improved, metallographic analysis is synchronously carried out, the welding control parameters are optimized in time, the fracture resistance of the joint when bearing impact load is improved, and further the quality of the welding joint is ensured to meet the technical effect of requirements.
Description
Technical Field
The invention relates to the technical field related to welding processing, in particular to a special steel welding control method and system.
Background
The special steel is a special-purpose steel, has specific chemical components and special performance requirements, and is suitable for specific engineering or application fields, including various types of stainless steel, tool steel, heat-resistant steel, low-temperature steel, spring steel, non-magnetic steel, high-speed steel and the like.
The low-temperature steel has good toughness and crack sensitivity under low-temperature environment, is commonly used for manufacturing Liquefied Natural Gas (LNG) storage tanks, ships and the like, and is used for structural steel with working environment of-20-196 ℃ so that the low-temperature steel needs to be welded with special attention to the low-temperature toughness and crack sensitivity.
However, if the welding is bad, the low temperature toughness parameter of the welded joint is not consistent with the low temperature toughness parameter of the steel itself, or the quality of the welded special steel is poor, so that the low temperature toughness of the welding area needs to be matched with the low temperature toughness of the steel itself, excessive residual stress and deformation are avoided, the low temperature toughness of the welded joint is improved, and the quality of the welded joint is ensured to meet the requirements.
In summary, the low-temperature toughness of the low-temperature special steel welding joint in the prior art is low, and the technical problem of joint fracture may occur.
Disclosure of Invention
The application aims to solve the technical problems that in the prior art, the low-temperature toughness of a low-temperature special steel welding joint is low and joint fracture possibly occurs by providing a special steel welding control method and a special steel welding control system.
In view of the above problems, the present application provides a method and a system for controlling welding of special steels.
In a first aspect of the disclosure, a special steel welding control method is provided, where the method includes: acquiring preset welding parameters and preset postweld heat treatment parameters of the special steel for welding, wherein the special steel is low-temperature special steel; acquiring basic low-temperature toughness parameters of the special steel, and setting acquisition constraint conditions based on the basic low-temperature toughness parameters; randomly adjusting and combining the preset welding parameters and the preset post-welding heat treatment parameters in a welding parameter range and a post-welding heat treatment parameter range to obtain a plurality of welding parameter combinations to be optimized; constructing an objective function according to the basic low-temperature toughness parameters, optimizing in the welding parameter combinations, randomly selecting a first welding parameter combination, and analyzing to obtain a first initial fitness by acquiring the interlayer temperature of the first welding parameter combination when welding operation is performed; when the first welding parameter combination meets the constraint condition, acquiring a metallographic image set of a special steel welding joint welded by the first welding parameter combination, inputting the metallographic image set into a second low-temperature toughness analysis model, combining the objective function and the first initial fitness, calculating to obtain a first correction fitness, and continuing optimizing to obtain an optimal welding parameter combination, wherein the second low-temperature toughness analysis model comprises a first analysis branch and a second analysis branch; and adopting the optimal welding parameter combination to carry out welding control on the special steel.
In another aspect of the disclosure, a special steel welding control system is provided, wherein the system comprises: the device comprises a preset parameter acquisition module, a preset welding parameter acquisition module and a preset post-welding heat treatment module, wherein the preset welding parameter acquisition module is used for acquiring preset welding parameters and preset post-welding heat treatment parameters of special steel currently welded, and the special steel is low-temperature special steel; the constraint condition setting module is used for obtaining basic low-temperature toughness parameters of the special steel, and setting and obtaining constraint conditions based on the basic low-temperature toughness parameters; the welding parameter combination obtaining module is used for randomly adjusting and combining the preset welding parameters and the preset post-welding heat treatment parameters in a welding parameter range and a post-welding heat treatment parameter range to obtain a plurality of welding parameter combinations to be optimized; the initial fitness obtaining module is used for constructing an objective function according to the basic low-temperature toughness parameters, optimizing in the welding parameter combinations, randomly selecting a first welding parameter combination, and obtaining a first initial fitness through analysis by obtaining the interlayer temperature of the first welding parameter combination when welding operation is carried out; the optimizing module is used for acquiring a metallographic image set of the special steel welding joint welded by the first welding parameter combination when the first welding parameter combination meets the constraint condition, inputting the metallographic image set into a second low-temperature toughness analysis model, combining the objective function and the first initial fitness, calculating to obtain a first correction fitness, and continuing optimizing to obtain an optimal welding parameter combination, wherein the second low-temperature toughness analysis model comprises a first analysis branch and a second analysis branch; and the welding control module is used for performing welding control on the special steel by adopting the optimal welding parameter combination.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
due to the adoption of the method for acquiring preset welding parameters and preset postweld heat treatment parameters; obtaining basic low-temperature toughness parameters, and setting obtaining constraint conditions; randomly adjusting and combining to obtain a plurality of welding parameter combinations, constructing an objective function, optimizing, randomly selecting a first welding parameter combination, and obtaining interlayer temperature and first initial fitness; when the constraint condition is met, a metallographic image set is acquired and input into a model, an objective function and a first initial fitness are combined, a first correction fitness is calculated and optimization is continued, an optimal welding parameter set is finally acquired and welding control is carried out, the technical effects of avoiding excessive residual stress and deformation, improving the low-temperature toughness of a welding joint, synchronously carrying out metallographic analysis, timely optimizing welding control parameters, improving the fracture resistance of the joint when bearing impact load and further ensuring the quality of the welding joint to meet the requirements are achieved.
The foregoing description is only an overview of the technical solutions of the present application, and may be implemented according to the content of the specification in order to make the technical means of the present application more clearly understood, and in order to make the above-mentioned and other objects, features and advantages of the present application more clearly understood, the following detailed description of the present application will be given.
Drawings
FIG. 1 is a schematic diagram of a possible flow chart of a special steel welding control method according to an embodiment of the present application;
fig. 2 is a schematic flow chart of a possible process for obtaining low-temperature toughness parameters of T first initial joints in the special steel welding control method according to the embodiment of the present application;
FIG. 3 is a schematic diagram of a possible flow chart for constructing a second low-temperature toughness analysis model in a special steel welding control method according to an embodiment of the present application; fig. 4 is a schematic diagram of a possible structure of a special steel welding control system according to an embodiment of the present application.
Reference numerals illustrate: the welding control system comprises a preset parameter acquisition module 100, a constraint condition setting module 200, a welding parameter combination acquisition module 300, an initial fitness acquisition module 400, an optimizing module 500 and a welding control module 600.
Detailed Description
The embodiment of the application provides a special steel welding control method and system, which solve the technical problem that the low-temperature toughness of a low-temperature special steel welding joint is low and joint fracture possibly occurs, realize avoiding generating excessive residual stress and deformation, improve the low-temperature toughness of the welding joint, synchronously perform metallographic analysis, optimize welding control parameters in time, improve the fracture resistance of the joint when bearing impact load, and further ensure the technical effect that the quality of the welding joint meets the requirements.
Having described the basic principles of the present application, various non-limiting embodiments of the present application will now be described in detail with reference to the accompanying drawings.
Example 1
As shown in fig. 1, an embodiment of the present application provides a special steel welding control method, where the method includes:
s10: acquiring preset welding parameters and preset postweld heat treatment parameters of the special steel for welding, wherein the special steel is low-temperature special steel;
s20: acquiring basic low-temperature toughness parameters of the special steel, and setting acquisition constraint conditions based on the basic low-temperature toughness parameters;
step S20 includes the steps of:
s21: acquiring low-temperature toughness performance parameters of the welded joint meeting the low-temperature toughness performance requirements of the special steel in the historical time, and acquiring a historical joint low-temperature toughness parameter set;
s22: calculating the average value of a plurality of historical joint low-temperature toughness parameters in the historical joint low-temperature toughness parameter set to obtain the average value of the historical joint low-temperature toughness parameters;
s23: calculating a basic ratio of the average value of the low-temperature toughness parameters of the historical joint to the basic low-temperature toughness parameters, and taking the ratio of the low-temperature toughness performance parameters of the joint welded by the special steel to the basic low-temperature toughness parameters as the constraint condition, wherein the ratio is larger than or equal to the basic ratio.
In particular, the low-temperature toughness of the low-temperature special steel welding joint may cause problems such as cracks, breakage and the like in a low-temperature environment, thereby affecting the mechanical properties and the service life of the welding piece. The low-temperature toughness refers to crack extension resistance of a material when the material bears impact load at low temperature, and is one of important indexes for evaluating the service performance of the material at low temperature. Therefore, when special steel is welded, special steel low-temperature toughness is required to be paid attention to, proper welding parameters and control measures are adopted, the low-temperature toughness of a welding area is ensured to be matched with the low-temperature toughness of the steel, and the service performance is improved;
the preset welding parameters refer to preset parameters which need to be controlled in the welding process, including welding current, voltage, welding speed and the like; the preset post-welding heat treatment parameters refer to heat treatment parameters which need to be carried out after welding, and comprise normalizing temperature, annealing temperature, heat preservation time and the like; the special steel is low-temperature special steel, and preset welding parameters and preset postweld heat treatment parameters of the special steel for welding are obtained before the special steel is welded; the basic low-temperature toughness parameter refers to crack expansion resistance of special steel when bearing impact load at low temperature, is one of important indexes for evaluating the service performance of materials at low temperature, comprises impact toughness, plastic toughness and hardness, and is obtained, and based on the basic low-temperature toughness parameter, constraint conditions are set to ensure that the low-temperature toughness of a welded joint meets the requirement;
The impact toughness is used for representing the energy absorption capacity of the material before fracture, and the joint fracture toughness of the special steel material is high enough under a low-temperature environment to ensure that the special steel material cannot generate brittle fracture when being subjected to external impact or load; the plastic toughness is used for representing the plastic deformation capacity of the material when the material is loaded, and the joint of the special steel material has enough plastic toughness under the low-temperature environment so as to prevent brittle fracture when the material is loaded; the hardness is used for representing the scratch or indentation resistance of the material, and the joint hardness of the special steel material is moderate under a low-temperature environment, so that brittle fracture cannot be caused due to too high hardness, and the service life of the special steel material cannot be influenced due to too low hardness;
based on the basic low-temperature toughness parameters, setting obtaining constraint conditions comprises: evaluating whether the low-temperature toughness performance parameters of the welded special steel meet the requirements or not through constraint conditions, collecting historical data of the low-temperature toughness performance parameters of the welded joint of the special steel, wherein the historical data of the low-temperature toughness performance parameters of the joint can come from a welding production process or related test records of the welded joint meeting the low-temperature toughness performance requirements after the welding in the past year, and integrating the collected data to obtain a historical joint low-temperature toughness parameter set;
After collecting and obtaining a historical joint low-temperature toughness parameter set, respectively calculating average values of a plurality of historical joint low-temperature toughness parameters, and calculating to obtain a historical joint low-temperature toughness parameter average value, wherein the historical joint low-temperature toughness parameter average value can be an impact toughness parameter average value, a plastic toughness parameter average value and a hardness parameter average value;
the basic ratio can be a numerical value which is custom set by a person skilled in the art on the basis of meeting industry standards, and can be generally set to be 1, the basic ratio of the average value of the low-temperature toughness parameters of the historical joint to the basic low-temperature toughness parameters is calculated, and the average value of the low-temperature toughness parameters of the historical joint is compared with the basic ratio: if the ratio of the average value of the low-temperature toughness parameters of the historical joint to the basic ratio is larger than or equal to the basic ratio, the condition is used as a constraint condition, so that whether the low-temperature toughness performance of the joint welded by the special steel meets the requirement is judged.
S30: randomly adjusting and combining the preset welding parameters and the preset post-welding heat treatment parameters in a welding parameter range and a post-welding heat treatment parameter range to obtain a plurality of welding parameter combinations to be optimized;
S40: constructing an objective function according to the basic low-temperature toughness parameters, optimizing in the welding parameter combinations, randomly selecting a first welding parameter combination, and analyzing to obtain a first initial fitness by acquiring the interlayer temperature of the first welding parameter combination when welding operation is performed;
step S40 includes the steps of:
s41: and constructing the objective function according to the low-temperature toughness performance parameters, wherein the objective function comprises the following formula:；
s42: wherein, L is the fitness,for the average value of the low-temperature toughness parameters of the historical joint, </i >>For the j-th test of the joint low-temperature toughness parameter of the welded joint of the special steel after welding, < +.>For the basic ratio, T is the number of times of testing the low-temperature toughness parameter of the special steel welded joint after welding;
s43: randomly selecting a first welding parameter combination from the plurality of welding parameter combinations, and taking the first welding parameter combination as a historical optimal solution;
s44: acquiring T first interlayer temperatures of the first welding parameter combination when welding operation is performed;
s45: inputting the temperature between the T first layers into a first low-temperature toughness analysis model to obtain T first initial joint low-temperature toughness parameters;
s46: and inputting the low-temperature toughness parameters of the T first initial joints into the objective function to obtain the first initial fitness.
Specifically, randomly adjusting and combining the preset welding parameters and the preset post-welding heat treatment parameters in a welding parameter range and a post-welding heat treatment parameter range to obtain a plurality of welding parameter combinations to be optimized, wherein the plurality of welding parameter combinations are used for representing randomly generating a plurality of welding parameter combinations in the preset welding parameters and the heat treatment parameters so as to find an optimal combination;
the objective function is used for finding an optimal combination of welding parameters so as to generate an optimal result in terms of low-temperature toughness, the objective function is constructed according to the basic low-temperature toughness parameters, optimization is performed in the welding parameter combinations, a first welding parameter combination is randomly selected, the first initial fitness is obtained through analysis by acquiring the interlayer temperature of the first welding parameter combination when the welding operation is performed, the first welding parameter combination refers to a series of parameters such as welding current, voltage, welding speed and the like which are set in the welding process, different welding parameter combinations have different influences on the quality and performance of a welding joint, and therefore the optimal parameter combination needs to be determined through optimization;
Constructing an objective function according to the basic low-temperature toughness parameters, and optimizing in the welding parameter combinations, wherein the objective function is constructed according to the low-temperature toughness performance parameters, and the objective function comprises the following formula:wherein L is fitness, ++>For the average value of the low-temperature toughness parameters of the historical joint, </i >>For the j-th test of the joint low-temperature toughness parameter of the welded joint of the special steel after welding, < +.>For the basic ratio, T is the number of times of testing the low-temperature toughness parameter of the special steel welded joint after welding;
optimizing a plurality of welding parameter combinations in the plurality of welding parameter combinations, comparing fitness obtained by calculating an objective function to determine an optimal solution, randomly selecting a first welding parameter combination from the plurality of welding parameter combinations, and taking the first welding parameter combination as a historical optimal solution, wherein the historical optimal solution is possibly updated along with substitution of a second welding parameter combination and a third welding parameter combination, and meanwhile, the first welding parameter combination is the starting point of the historical optimal solution;
predicting low-temperature toughness parameters according to the interlayer temperature of welding, and calculating the fitness, wherein the method specifically comprises the following steps: for the selected first welding parameter combination, performing welding operation and acquiring T first interlayer temperatures, inputting the T first interlayer temperatures into a first low-temperature toughness analysis model, and calculating T first initial joint low-temperature toughness parameters through the first low-temperature toughness analysis model; inputting the low-temperature toughness parameters of the T first initial joints into an objective function to evaluate the low-temperature toughness performance of the welding parameter combination, and calculating to obtain a first initial fitness; by constantly iterating and optimizing, it is meant that the weld parameters are combined and evaluated in an optimization problem by constantly adjusting the parameters to gradually find the optimal weld parameters under given constraints to achieve the desired weld quality and low temperature toughness performance.
As shown in fig. 2, step S45 includes the steps of:
s451: acquiring a sample interlayer temperature set and a sample joint low-temperature toughness parameter set based on welding data of the special steel in the historical time;
s452: the sample interlayer temperature set and the sample joint low-temperature toughness parameter set are used as construction data, the first low-temperature toughness analysis model is constructed based on a decision tree, a plurality of layers of decision nodes are included in the first low-temperature toughness analysis model, and multi-layer division decision is carried out on the input interlayer temperature to obtain output joint low-temperature toughness parameters;
s453: inputting the T first interlayer temperatures into the first low-temperature toughness analysis model to obtain the T first initial joint low-temperature toughness parameters.
Specifically, inputting the T first interlayer temperatures into a first low-temperature toughness analysis model to obtain T first initial joint low-temperature toughness parameters, wherein the T first initial joint low-temperature toughness parameters comprise the steps of constructing a decision tree model from given experience data, predicting joint low-temperature toughness parameters by using the model, collecting welding data of special steels in the past year, wherein the welding data of the special steels in the year comprise a sample interlayer temperature set and a sample joint low-temperature toughness parameter set;
Using a decision tree algorithm, wherein a sample interlayer temperature set and a sample joint low-temperature toughness parameter set can be used as construction data to construct a first low-temperature toughness analysis model, and the algorithm model of the decision tree algorithm should be provided with a plurality of decision nodes so as to carry out multi-layer division decision on the input interlayer temperature and obtain an output joint low-temperature toughness parameter; inputting the T first interlayer temperatures into a first low-temperature toughness analysis model, constructing mapping correlation functions between the T first interlayer temperatures and joint low-temperature toughness parameters, storing the mapping correlation functions into the first low-temperature toughness analysis model, and obtaining T first initial joint low-temperature toughness parameters through the first low-temperature toughness analysis model; substituting the T first initial joint low-temperature toughness parameters into the objective function to obtain a first initial fitness;
the decision tree is a classification model based on a tree structure and is used for carrying out multi-layer division decision on input data and outputting corresponding results, the sample interlayer temperature set and the sample joint low-temperature toughness parameter set are adopted as construction data, the first low-temperature toughness analysis model is constructed based on the decision tree, the first low-temperature toughness analysis model comprises multi-layer decision nodes, the multi-layer division decision is carried out on the input interlayer temperature, the output joint low-temperature toughness parameters are obtained, and model support is provided for low-temperature toughness analysis.
S50: when the first welding parameter combination meets the constraint condition, acquiring a metallographic image set of a special steel welding joint welded by the first welding parameter combination, inputting the metallographic image set into a second low-temperature toughness analysis model, combining the objective function and the first initial fitness, calculating to obtain a first correction fitness, and continuing optimizing to obtain an optimal welding parameter combination, wherein the second low-temperature toughness analysis model comprises a first analysis branch and a second analysis branch;
s60: and adopting the optimal welding parameter combination to carry out welding control on the special steel.
Step S50 includes the steps of:
s51: judging whether the first initial adaptability is greater than 0, if so, acquiring a metallographic image set of a special steel welding joint welded by the first welding parameter combination, and if not, randomly selecting a second welding parameter combination again in the welding parameter combinations, wherein the metallographic image set comprises a first metallographic image set and a second metallographic image set at a first position and a second position on the joint, and the first metallographic image set and the second running image set respectively comprise T first metallographic images and T second metallographic images;
S52: constructing the second low-temperature toughness analysis model based on welding data in the history time of the special steel;
s53: combining the T first metallographic images and the T second metallographic images to obtain T input data, inputting the T input data into the first analysis branch and the second analysis branch in the second low-temperature toughness analysis model to obtain T first correction joint low-temperature toughness parameters, and calculating to obtain first adjustment fitness according to the objective function;
s54: weighting and calculating the first adjustment fitness and the first initial fitness to obtain the first correction fitness;
s55: and continuing optimizing according to the first correction fitness to obtain the optimal welding parameter combination.
Specifically, welding special steel materials by using a first welding parameter combination, and ensuring that the first welding parameter combination meets the constraint conditions so as to ensure the safety and feasibility of a welding process; once the first welding parameter combination is welded, acquiring a metallographic image set of a special steel welding joint welded by the first welding parameter combination, wherein the metallographic image set relates to information of welding quality and joint characteristics;
Inputting a metallographic image set into a second low-temperature toughness analysis model, wherein the second low-temperature toughness analysis model comprises a first analysis branch and a second analysis branch, and the analysis branches are arranged for joint positions; calculating to obtain a first corrected fitness by combining the objective function and the first initial fitness, wherein the first corrected fitness is based on a first welding parameter combination and a low-temperature toughness analysis result; continuing iteration and optimization to find an optimal welding parameter combination, and gradually approaching an optimal solution by adjusting the parameter combination and evaluating the performance of the parameter combination so as to find the optimal welding parameter combination under the given constraint condition; after the optimal welding parameter combination is found, the optimal welding parameter combination is adopted to carry out welding control on special steel, so that expected welding quality and low-temperature toughness performance are ensured to be obtained in the welding process, and the welding quality and the performance of the joint are improved.
When the first welding parameter combination meets the constraint condition, acquiring a metallographic image set of a special steel welding joint welded by the first welding parameter combination, inputting the metallographic image set into a second low-temperature toughness analysis model, combining the objective function and the first initial fitness, calculating to obtain a first correction fitness, and continuing optimizing to obtain an optimal welding parameter combination, wherein the first welding parameter combination is substituted into the objective function to calculate to obtain the first initial fitness; judging whether the first initial adaptability is larger than 0: when the constraint condition is met, namely the first initial fitness is greater than 0, acquiring a metallographic image set of the special steel welding joint subjected to the first welding parameter combination welding; if the constraint condition is not met, namely the first initial fitness is smaller than 0, randomly selecting a second welding parameter combination from the welding parameter combinations again, and then judging whether the fitness is larger than 0 again;
When the first initial fitness is greater than 0, the metallographic images of two positions of the joint are collected, the low-temperature toughness parameter is predicted, the prediction model is constructed based on two channels, the input data of the first analysis branch is a first metallographic image of the first position of the joint, and the input data of the second analysis branch is a second metallographic image of the second position; the first metallographic image set and the second metallographic image set respectively comprise T first metallographic images and T second metallographic images, wherein the first position is the surface of the special steel welding joint, and the second position is the inside of the special steel welding joint;
constructing the second low-temperature toughness analysis model based on welding data in the history time of the special steel; comparing the first position with the second position, and combining and splicing the T first metallographic images and the T second metallographic images to obtain T input data; inputting the T input data into the first analysis branch and the second analysis branch in the second low-temperature toughness analysis model to obtain T first correction joint low-temperature toughness parameters, and calculating to obtain first adjustment fitness according to the objective function; taking the first adjustment fitness as a weight ratio, carrying out weighted adjustment on the first initial fitness, and carrying out weighted calculation to obtain a first correction fitness; and according to the first correction fitness, continuing optimizing to obtain the optimal welding parameter combination, and effectively carrying out the optimal design of the special steel welding joint by combining a metallographic image and a low-temperature toughness analysis model, thereby improving the low-temperature toughness and the reliability of the joint.
As shown in fig. 3, step S52 includes the steps of:
s521: acquiring a plurality of historical first metallographic image sets, a plurality of historical second metallographic image sets and a plurality of historical joint low-temperature toughness parameters of the joint of the special steel welded joint at a first position and a second position after welding based on the welding data in the special steel historical time;
s522: dividing and combining the plurality of historical first metallographic image sets, the plurality of historical second metallographic image sets and the plurality of historical joint low-temperature toughness parameters of the joint to obtain a plurality of groups of construction data, wherein each group of construction data comprises the historical first metallographic image, the historical second metallographic image and the historical joint low-temperature toughness parameters;
s523: based on a convolutional neural network, constructing a first analysis branch, a second analysis branch and a full-connection layer, wherein input data of the first analysis branch is a first metallographic image, input data of the second analysis branch is a second metallographic image, and output of the full-connection layer is a joint low-temperature toughness parameter;
s524: and performing supervision training, verification and test on the first analysis branch, the second analysis branch and the full-connection layer by adopting the plurality of groups of construction data to obtain the second low-temperature toughness analysis model meeting convergence conditions.
Specifically, the second low-temperature toughness analysis model is constructed based on welding data in the history time of the special steel, and comprises the steps of comparing a first position and a second position of a welding joint of the special steel based on the welding data in the history time of the special steel, obtaining a plurality of historical first metallographic images and a plurality of historical second metallographic images in the past year, obtaining a plurality of historical first metallographic image sets, a plurality of historical second metallographic image sets and a plurality of historical joint low-temperature toughness parameters of the joint after the welding of the first position and the second position of the welding joint of the special steel is finished, wherein the time sequence information of the low-temperature toughness parameters of the plurality of historical joints is consistent with the time sequence information of the historical first metallographic images and the time sequence information of the historical second metallographic images;
dividing and combining the plurality of historical first metallographic image sets, the plurality of historical second metallographic image sets and the plurality of historical joint low-temperature toughness parameters of the joint according to the correspondence of the time sequence information to obtain a plurality of groups of construction data, wherein each group of construction data comprises the historical first metallographic image, the historical second metallographic image and the historical joint low-temperature toughness parameters;
Constructing the first analysis branch, the second analysis branch and the full connection layer based on the convolutional neural network, wherein the first analysis branch of the convolutional neural network is constructed by using the convolutional layer, the pooling layer and the activation function: taking the first metallographic image as input data, adding a plurality of convolution layers and pooling layers to extract the features of the image, converting the extracted features into one-dimensional vectors by using a flattening layer, and constructing a first analysis branch; a second analysis branch of the convolutional neural network is also constructed using the convolutional layer, the pooling layer, and the activation function: taking the second metallographic image as input data, wherein the second analysis branch has the same structure as the first analysis branch; adding a full-connection layer to the first analysis branch and the second analysis branch, connecting the outputs of the first analysis branch and the second analysis branch to serve as the input of the full-connection layer, combining and processing the characteristics by the full-connection layer, generating the output of the low-temperature toughness parameters of the joint, and using the second low-temperature toughness analysis model to evaluate the toughness performance of the special steel welding joint;
the output of the full-connection layer is the low-temperature toughness parameter of the joint; performing supervision training on the first analysis branch, the second analysis branch and the full connection layer by using the plurality of groups of construction data; randomly extracting 10% and 5% of data which are not put back in the plurality of groups of construction data respectively to obtain a verification set and a test set; performing model training by using the plurality of groups of construction data; and (3) performing verification and testing by using a verification set and a test set (the verification passing probability is not lower than 85%, and the test passing probability is not lower than 85%, so that the verification process can perform model parameter tuning and the test process does not allow model parameter tuning) to ensure the stability of the constructed model.
Step S55 includes the steps of:
s551: continuously randomly selecting and acquiring a second correction fitness of a second welding parameter combination according to the objective function, judging whether the second correction fitness is larger than the first correction fitness, if so, taking the second welding parameter combination as a historical optimal solution, and if not, taking the second welding parameter combination as a historical optimal solution according to probability, wherein the probability is reduced along with the increase of optimizing times;
s552: and continuing optimizing until the preset optimizing times are reached, and outputting a final historical optimal solution to obtain the optimal welding parameter combination.
Specifically, according to the first correction fitness, continuing optimizing to obtain the optimal welding parameter combination, including, according to the objective function, continuing to randomly select and obtain a second correction fitness of a second welding parameter combination, judging whether the second correction fitness is greater than the first correction fitness, if so, taking the second welding parameter combination as a historical optimal solution, if not, taking the probability as the historical optimal solution, wherein the probability decreases along with the increase of optimizing times, and preferably, adopting a random selection mode to avoid sinking into a local optimal solution, namely randomly selecting some parameter combinations from the welding parameter combinations for evaluation and comparison;
And (3) continuing optimizing by referring to the process, recording a history optimal solution, and judging whether the current parameter combination is better than the history optimal solution according to the current correction fitness: if yes, the current parameter combination is used as a history optimal solution; if not, a certain probability is given to take the current parameter combination as a historical optimal solution, the probability can be reduced along with the increase of the optimizing times, iteration is stopped until the preset optimizing times are reached, the final historical optimal solution is output, and the optimal welding parameter combination is obtained, and the optimal welding parameter combination is even the optimal parameter configuration with optimized objective function, so that welding control parameters are optimized.
In summary, the special steel welding control method and system provided by the embodiment of the application have the following technical effects:
1. due to the adoption of the method for acquiring preset welding parameters and preset postweld heat treatment parameters; obtaining basic low-temperature toughness parameters, and setting obtaining constraint conditions; randomly adjusting and combining to obtain a plurality of welding parameter combinations, constructing an objective function, optimizing, randomly selecting a first welding parameter combination, and obtaining interlayer temperature and first initial fitness; when the constraint condition is met, a metallographic image set is acquired and input into a model, an objective function and a first initial fitness are combined, a first correction fitness is calculated and optimization is continued, and finally an optimal welding parameter set is acquired and welding control is carried out.
2. Due to the adoption of the performance parameters according to the low-temperature toughness, an objective function is constructed:the method comprises the steps of carrying out a first treatment on the surface of the Randomly selecting a first welding parameter combination from a plurality of welding parameter combinations, and taking the first welding parameter combination as a historical optimal solution; acquiring T first interlayer temperatures of the first welding parameter combination when welding operation is performed; inputting the temperature between the T first layers into a first low-temperature toughness analysis model to obtain T first initial joint low-temperature toughness parameters; inputting the low-temperature toughness parameters of the T first initial joints into an objective function to obtain first initial fitness so as to gradually find out the optimal welding parameter combination under given constraint conditions, so as to achieve the expected welding quality and low-temperature toughness performance.
Example 2
Based on the same inventive concept as the special steel welding control method in the foregoing embodiments, as shown in fig. 4, an embodiment of the present application provides a special steel welding control system, where the system includes:
the preset parameter obtaining module 100 is configured to obtain preset welding parameters and preset post-welding heat treatment parameters of a special steel currently being welded, where the special steel is a low-temperature special steel;
the constraint condition setting module 200 is configured to obtain a basic low-temperature toughness parameter of the special steel, and set a constraint condition to be obtained based on the basic low-temperature toughness parameter;
A welding parameter combination obtaining module 300, configured to randomly adjust and combine the preset welding parameter and the preset post-welding heat treatment parameter in a welding parameter range and a post-welding heat treatment parameter range, so as to obtain a plurality of welding parameter combinations to be optimized;
the initial fitness obtaining module 400 is configured to construct an objective function according to the basic low-temperature toughness parameter, perform optimization in the plurality of welding parameter combinations, randomly select a first welding parameter combination, obtain an interlayer temperature of the first welding parameter combination during welding operation, and obtain a first initial fitness through analysis;
the optimizing module 500 is configured to obtain a metallographic image set of a special steel welded joint welded by the first welding parameter combination when the first welding parameter combination meets the constraint condition, input the metallographic image set into a second low-temperature toughness analysis model, calculate to obtain a first correction fitness by combining the objective function and the first initial fitness, and continue optimizing to obtain an optimal welding parameter combination, where the second low-temperature toughness analysis model includes a first analysis branch and a second analysis branch;
and the welding control module 600 is used for performing welding control on the special steel by adopting the optimal welding parameter combination.
Further, the system includes:
the historical joint low-temperature toughness parameter set acquisition module is used for acquiring low-temperature toughness performance parameters of the welded joint meeting the low-temperature toughness performance requirements after welding of the special steel in historical time to acquire a historical joint low-temperature toughness parameter set;
the historical joint low-temperature toughness parameter average value acquisition module is used for calculating the average value of a plurality of historical joint low-temperature toughness parameters in the historical joint low-temperature toughness parameter set to obtain a historical joint low-temperature toughness parameter average value;
the constraint condition determining module is used for calculating a basic ratio of the average value of the low-temperature toughness parameters of the historical joint to the basic low-temperature toughness parameters, and taking the ratio of the low-temperature toughness performance parameters of the joint welded by the special steel to the basic low-temperature toughness parameters as the constraint condition, wherein the ratio is larger than or equal to the basic ratio.
Further, the system includes:
and the objective function construction module is used for constructing the objective function according to the low-temperature toughness performance parameters, and the formula is as follows:；
the parameter substitution module is used for substituting the parameters into the module, wherein L is the fitness,for the average value of the low-temperature toughness parameters of the historical joint, </i > >For the j-th test of the joint low-temperature toughness parameter of the welded joint of the special steel after welding, < +.>For the basic ratio, T is the number of times of testing the low-temperature toughness parameter of the special steel welded joint after welding;
the historical optimal solution determining module is used for randomly selecting and obtaining a first welding parameter combination from the plurality of welding parameter combinations and taking the first welding parameter combination as a historical optimal solution;
the interlayer temperature acquisition module is used for acquiring T first interlayer temperatures of the first welding parameter combination when welding operation is performed;
the first interlayer temperature input module is used for inputting the T first interlayer temperatures into a first low-temperature toughness analysis model to obtain T first initial joint low-temperature toughness parameters;
and the initial fitness obtaining module is used for inputting the low-temperature toughness parameters of the T first initial joints into the objective function to obtain the first initial fitness.
Further, the system includes:
the sample data acquisition module is used for acquiring a sample interlayer temperature set and a sample joint low-temperature toughness parameter set based on the welding data of the special steel in the history time;
the construction data determining module is used for adopting the sample interlayer temperature set and the sample joint low-temperature toughness parameter set as construction data, constructing the first low-temperature toughness analysis model based on a decision tree, wherein the first low-temperature toughness analysis model comprises a plurality of layers of decision nodes, and carrying out multi-layer division decision on the input interlayer temperature to obtain output joint low-temperature toughness parameters;
The initial joint low-temperature toughness parameter acquisition module is used for inputting the T first interlayer temperatures into the first low-temperature toughness analysis model to obtain T first initial joint low-temperature toughness parameters.
Further, the system includes:
the random selection module is used for judging whether the first initial adaptability is greater than 0, if yes, acquiring a metallographic image set of the special steel welding joint welded by the first welding parameter combination, and if not, randomly selecting a second welding parameter combination again in the welding parameter combinations, wherein the metallographic image set comprises a first metallographic image set and a second metallographic image set at a first position and a second position on the joint, and the first metallographic image set and the second running image set respectively comprise T first metallographic images and T second metallographic images;
the low-temperature toughness analysis model acquisition module is used for constructing the second low-temperature toughness analysis model based on welding data in the history time of the special steel;
the first adjustment fitness calculation module is used for combining the T first metallographic images and the T second metallographic images to obtain T input data, inputting the T input data into the first analysis branch and the second analysis branch in the second low-temperature toughness analysis model to obtain T first correction joint low-temperature toughness parameters, and calculating to obtain first adjustment fitness according to the objective function;
The first correction fitness obtaining module is used for carrying out weighted calculation on the first adjustment fitness and the first initial fitness to obtain the first correction fitness;
and the optimal welding parameter combination obtaining module is used for continuing optimizing according to the first correction fitness to obtain the optimal welding parameter combination.
Further, the system includes:
the correction fitness judging module is used for continuing to randomly select and acquire a second correction fitness of a second welding parameter combination according to the objective function, judging whether the second correction fitness is larger than the first correction fitness, if so, taking the second welding parameter combination as a historical optimal solution, and if not, taking the second welding parameter combination as a historical optimal solution according to probability, wherein the probability is reduced along with the increase of optimizing times;
and the optimal welding parameter combination acquisition module is used for continuing optimizing until the preset optimizing times are reached, and outputting a final historical optimal solution to obtain the optimal welding parameter combination.
Further, the system includes:
the history index acquisition module is used for acquiring a plurality of history first metallographic image sets, a plurality of history second metallographic image sets and a plurality of history joint low-temperature toughness parameters of the joint at a first position and a second position of the welded joint of the special steel based on the welding data in the history time of the special steel;
The multi-group construction data acquisition module is used for dividing and combining the plurality of historical first metallographic image sets, the plurality of historical second metallographic image sets and the plurality of historical joint low-temperature toughness parameters of the joint to obtain a plurality of groups of construction data, wherein each group of construction data comprises the historical first metallographic image, the historical second metallographic image and the historical joint low-temperature toughness parameters;
the device comprises a first analysis branch, a second analysis branch and a full-connection layer construction module, wherein the first analysis branch, the second analysis branch and the full-connection layer construction module are used for constructing the first analysis branch, the second analysis branch and the full-connection layer based on a convolutional neural network, input data of the first analysis branch are first metallographic images, input data of the second analysis branch are second metallographic images, and output of the full-connection layer is a joint low-temperature toughness parameter;
and the second low-temperature toughness analysis model acquisition module is used for performing supervision training, verification and test on the first analysis branch, the second analysis branch and the full-connection layer by adopting the plurality of groups of construction data to obtain the second low-temperature toughness analysis model meeting convergence conditions.
Any of the steps of the methods described above may be stored as computer instructions or programs in a non-limiting computer memory and may be called by a non-limiting computer processor to identify any of the methods to implement embodiments of the present application, without unnecessary limitations.
Further, the first or second element may not only represent a sequential relationship, but may also represent a particular concept, and/or may be selected individually or in whole among a plurality of elements. It will be apparent to those skilled in the art that various modifications and variations can be made in the present application without departing from the scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the present application and the equivalents thereof, the present application is intended to cover such modifications and variations.
Claims (3)
1. A special steel welding control method, characterized in that the method comprises the following steps:
acquiring preset welding parameters and preset postweld heat treatment parameters of the special steel for welding, wherein the special steel is low-temperature special steel;
acquiring basic low-temperature toughness parameters of the special steel, and setting acquisition constraint conditions based on the basic low-temperature toughness parameters;
randomly adjusting and combining the preset welding parameters and the preset post-welding heat treatment parameters in a welding parameter range and a post-welding heat treatment parameter range to obtain a plurality of welding parameter combinations to be optimized;
constructing an objective function according to the basic low-temperature toughness parameters, optimizing in the welding parameter combinations, randomly selecting a first welding parameter combination, and analyzing to obtain a first initial fitness by acquiring the interlayer temperature of the first welding parameter combination when welding operation is performed;
When the first welding parameter combination meets the constraint condition, acquiring a metallographic image set of a special steel welding joint welded by the first welding parameter combination, inputting the metallographic image set into a second low-temperature toughness analysis model, combining the objective function and the first initial fitness, calculating to obtain a first correction fitness, and continuing optimizing to obtain an optimal welding parameter combination, wherein the second low-temperature toughness analysis model comprises a first analysis branch and a second analysis branch;
adopting the optimal welding parameter combination to carry out welding control on the special steel;
wherein, based on the basic low-temperature toughness parameter, setting and obtaining constraint conditions comprises:
acquiring low-temperature toughness performance parameters of the welded joint meeting the low-temperature toughness performance requirements of the special steel in the historical time, and acquiring a historical joint low-temperature toughness parameter set;
calculating the average value of a plurality of historical joint low-temperature toughness parameters in the historical joint low-temperature toughness parameter set to obtain the average value of the historical joint low-temperature toughness parameters;
calculating a basic ratio of the average value of the low-temperature toughness parameters of the historical joint to the basic low-temperature toughness parameters, and taking the ratio of the low-temperature toughness performance parameters of the joint welded by the special steel to the basic low-temperature toughness parameters as the constraint condition, wherein the ratio is greater than or equal to the basic ratio;
Constructing an objective function according to the basic low-temperature toughness parameters, and optimizing in the welding parameter combinations, wherein the method comprises the following steps:
and constructing the objective function according to the low-temperature toughness performance parameters, wherein the objective function comprises the following formula:
；
wherein, L is the fitness,for the average value of the low-temperature toughness parameters of the historical joint, </i >>For the j-th test of the joint low-temperature toughness parameter of the welded joint of the special steel after welding, < +.>For the basic ratio, T is the number of times of testing the low-temperature toughness parameter of the special steel welded joint after welding;
randomly selecting a first welding parameter combination from the plurality of welding parameter combinations, and taking the first welding parameter combination as a historical optimal solution;
acquiring T first interlayer temperatures of the first welding parameter combination when welding operation is performed;
inputting the temperature between the T first layers into a first low-temperature toughness analysis model to obtain T first initial joint low-temperature toughness parameters;
inputting the low-temperature toughness parameters of the T first initial joints into the objective function to obtain the first initial fitness;
judging whether the first initial fitness is larger than 0, if so, acquiring a metallographic image set of a special steel welding joint welded by the first welding parameter combination, and if not, randomly selecting a second welding parameter combination again in the welding parameter combinations, wherein the metallographic image set comprises a first metallographic image set and a second metallographic image set at a first position and a second position on the joint, and the first metallographic image set and the second metallographic image set respectively comprise T first metallographic images and T second metallographic images;
Constructing the second low-temperature toughness analysis model based on welding data in the history time of the special steel;
combining the T first metallographic images and the T second metallographic images to obtain T input data, inputting the T input data into the first analysis branch and the second analysis branch in the second low-temperature toughness analysis model to obtain T first correction joint low-temperature toughness parameters, and calculating to obtain first adjustment fitness according to the objective function;
weighting and calculating the first adjustment fitness and the first initial fitness to obtain the first correction fitness;
continuing optimizing according to the first correction fitness to obtain the optimal welding parameter combination;
continuing optimizing according to the first correction fitness to obtain the optimal welding parameter combination, wherein the optimizing comprises the following steps:
continuously randomly selecting and acquiring a second correction fitness of a second welding parameter combination according to the objective function, judging whether the second correction fitness is larger than the first correction fitness, if so, taking the second welding parameter combination as a historical optimal solution, and if not, taking the second welding parameter combination as a historical optimal solution according to probability, wherein the probability is reduced along with the increase of optimizing times;
Continuing optimizing until reaching the preset optimizing times, outputting a final historical optimal solution to obtain the optimal welding parameter combination;
based on the welding data in the history time of the special steel, constructing the second low-temperature toughness analysis model, which comprises the following steps:
acquiring a plurality of historical first metallographic image sets, a plurality of historical second metallographic image sets and a plurality of historical joint low-temperature toughness parameters of the joint of the special steel welded joint at a first position and a second position after welding based on the welding data in the special steel historical time;
dividing and combining the plurality of historical first metallographic image sets, the plurality of historical second metallographic image sets and the plurality of historical joint low-temperature toughness parameters of the joint to obtain a plurality of groups of construction data, wherein each group of construction data comprises the historical first metallographic image, the historical second metallographic image and the historical joint low-temperature toughness parameters;
based on a convolutional neural network, constructing a first analysis branch, a second analysis branch and a full-connection layer, wherein input data of the first analysis branch is a first metallographic image, input data of the second analysis branch is a second metallographic image, and output of the full-connection layer is a joint low-temperature toughness parameter;
And performing supervision training, verification and test on the first analysis branch, the second analysis branch and the full-connection layer by adopting the plurality of groups of construction data to obtain the second low-temperature toughness analysis model meeting convergence conditions.
2. The method of claim 1, wherein inputting the T first interlayer temperatures into a first low temperature toughness analysis model to obtain T first initial joint low temperature toughness parameters comprises:
acquiring a sample interlayer temperature set and a sample joint low-temperature toughness parameter set based on welding data of the special steel in the historical time;
the sample interlayer temperature set and the sample joint low-temperature toughness parameter set are used as construction data, the first low-temperature toughness analysis model is constructed based on a decision tree, a plurality of layers of decision nodes are included in the first low-temperature toughness analysis model, and multi-layer division decision is carried out on the input interlayer temperature to obtain output joint low-temperature toughness parameters;
inputting the T first interlayer temperatures into the first low-temperature toughness analysis model to obtain the T first initial joint low-temperature toughness parameters.
3. A special steel welding control system for implementing a special steel welding control method according to any one of claims 1-2, comprising:
The device comprises a preset parameter acquisition module, a preset welding parameter acquisition module and a preset post-welding heat treatment module, wherein the preset welding parameter acquisition module is used for acquiring preset welding parameters and preset post-welding heat treatment parameters of special steel currently welded, and the special steel is low-temperature special steel;
the constraint condition setting module is used for obtaining basic low-temperature toughness parameters of the special steel, and setting and obtaining constraint conditions based on the basic low-temperature toughness parameters;
the welding parameter combination obtaining module is used for randomly adjusting and combining the preset welding parameters and the preset post-welding heat treatment parameters in a welding parameter range and a post-welding heat treatment parameter range to obtain a plurality of welding parameter combinations to be optimized;
the initial fitness obtaining module is used for constructing an objective function according to the basic low-temperature toughness parameters, optimizing in the welding parameter combinations, randomly selecting a first welding parameter combination, and obtaining a first initial fitness through analysis by obtaining the interlayer temperature of the first welding parameter combination when welding operation is carried out;
the optimizing module is used for acquiring a metallographic image set of the special steel welding joint welded by the first welding parameter combination when the first welding parameter combination meets the constraint condition, inputting the metallographic image set into a second low-temperature toughness analysis model, combining the objective function and the first initial fitness, calculating to obtain a first correction fitness, and continuing optimizing to obtain an optimal welding parameter combination, wherein the second low-temperature toughness analysis model comprises a first analysis branch and a second analysis branch;
And the welding control module is used for performing welding control on the special steel by adopting the optimal welding parameter combination.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311519228.7A CN117260053B (en) | 2023-11-15 | 2023-11-15 | Special steel welding control method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311519228.7A CN117260053B (en) | 2023-11-15 | 2023-11-15 | Special steel welding control method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117260053A CN117260053A (en) | 2023-12-22 |
| CN117260053B true CN117260053B (en) | 2024-04-02 |
Family
ID=89202830
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311519228.7A Active CN117260053B (en) | 2023-11-15 | 2023-11-15 | Special steel welding control method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117260053B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003042916A (en) * | 2001-07-30 | 2003-02-13 | Nippon Steel Corp | Quality control method for steel sheet of superior tenacity in welding heat-affected part |
| CN115542866A (en) * | 2022-11-28 | 2022-12-30 | 江苏未来网络集团有限公司 | Welding production monitoring method and system based on industrial internet full-connection management |
| CN116501003A (en) * | 2023-06-29 | 2023-07-28 | 张家港广大特材股份有限公司 | Processing control method and system for smelting special steel |
| CN116560322A (en) * | 2023-05-25 | 2023-08-08 | 深圳市新天泽消防工程有限公司 | Production control method and system for assembly production line |
| CN116842768A (en) * | 2023-09-01 | 2023-10-03 | 日照鼎立钢构股份有限公司 | Steel structural member production process optimization method and system |
-
2023
- 2023-11-15 CN CN202311519228.7A patent/CN117260053B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003042916A (en) * | 2001-07-30 | 2003-02-13 | Nippon Steel Corp | Quality control method for steel sheet of superior tenacity in welding heat-affected part |
| CN115542866A (en) * | 2022-11-28 | 2022-12-30 | 江苏未来网络集团有限公司 | Welding production monitoring method and system based on industrial internet full-connection management |
| CN116560322A (en) * | 2023-05-25 | 2023-08-08 | 深圳市新天泽消防工程有限公司 | Production control method and system for assembly production line |
| CN116501003A (en) * | 2023-06-29 | 2023-07-28 | 张家港广大特材股份有限公司 | Processing control method and system for smelting special steel |
| CN116842768A (en) * | 2023-09-01 | 2023-10-03 | 日照鼎立钢构股份有限公司 | Steel structural member production process optimization method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117260053A (en) | 2023-12-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108898251A (en) | Consider the marine wind electric field power forecasting method of meteorological similitude and power swing | |
| CN110570030A (en) | Wind power cluster power interval prediction method and system based on deep learning | |
| CN110837223A (en) | Combustion optimization control method and system for gas turbine | |
| CN114118789B (en) | Radar transmitter state evaluation method based on fuzzy comprehensive judgment and comprehensive weighting | |
| CN111340248A (en) | Transformer fault diagnosis method and system based on intelligent integration algorithm | |
| CN113343581B (en) | Transformer fault diagnosis method based on graph Markov neural network | |
| CN110458039A (en) | A kind of construction method of industrial process fault diagnosis model and its application | |
| CN107909212A (en) | Climbing event prediction method based on mesoscale wind power evolution serializing | |
| CN117260053B (en) | Special steel welding control method and system | |
| CN117096871A (en) | Wind power probability density prediction method based on space-time distribution | |
| CN116544934B (en) | Power scheduling method and system based on power load prediction | |
| CN117232809A (en) | Fan main shaft fault pre-diagnosis method based on DEMATEL-ANP-CRITIC combined weighting | |
| RU2703874C1 (en) | Method of monitoring and predicting operation of a gas turbine plant using a matrix of defects | |
| CN116526478A (en) | Short-term wind power prediction method and system based on improved snake group optimization algorithm | |
| CN114819382B (en) | LSTM-based photovoltaic power prediction method | |
| KR20230063905A (en) | Heatwave Probability Prediction System based on Recurrent Neural Network | |
| CN114187977B (en) | Equipment material spheroidization degree prediction method and system | |
| CN118016202B (en) | Chemical equipment operation analysis method and system based on steam-water quality | |
| CN116432519A (en) | Residual life interval prediction method based on long-period memory network and upper and lower limit interval estimation | |
| CN116400434A (en) | Fog weather forecasting method based on deep learning | |
| CN116362125A (en) | Deep learning-based turbofan engine multistage predictive maintenance method | |
| CN116256686A (en) | MRI equipment abnormality detection method and system based on Internet of things data | |
| CN118088923A (en) | Safety monitoring method and system based on hydrogen storage and transportation | |
| KR20230056351A (en) | System and Method for estimating physical properties of power generating equipment part materials based on deep learning | |
| CN117709524A (en) | Bayesian optimization-based carbon emission prediction method and system for steel industry |
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 |