CN111461398A - Welding process parameter optimization method and device and readable storage medium - Google Patents
Welding process parameter optimization method and device and readable storage medium Download PDFInfo
- Publication number
- CN111461398A CN111461398A CN202010126442.6A CN202010126442A CN111461398A CN 111461398 A CN111461398 A CN 111461398A CN 202010126442 A CN202010126442 A CN 202010126442A CN 111461398 A CN111461398 A CN 111461398A
- Authority
- CN
- China
- Prior art keywords
- welding
- process parameter
- parameter combination
- preset
- penetration data
- 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.)
- Pending
Links
- 238000003466 welding Methods 0.000 title claims abstract description 328
- 238000000034 method Methods 0.000 title claims abstract description 296
- 230000008569 process Effects 0.000 title claims abstract description 245
- 238000005457 optimization Methods 0.000 title claims abstract description 44
- 238000003860 storage Methods 0.000 title claims abstract description 12
- 230000035515 penetration Effects 0.000 claims abstract description 130
- 238000012549 training Methods 0.000 claims abstract description 47
- 238000003062 neural network model Methods 0.000 claims abstract description 45
- 238000013507 mapping Methods 0.000 claims abstract description 42
- 238000013386 optimize process Methods 0.000 claims description 84
- 238000004088 simulation Methods 0.000 claims description 23
- 238000012360 testing method Methods 0.000 claims description 23
- 230000008859 change Effects 0.000 claims description 15
- 230000003247 decreasing effect Effects 0.000 claims description 10
- 230000000694 effects Effects 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000009529 body temperature measurement Methods 0.000 claims description 6
- 238000001816 cooling Methods 0.000 claims description 5
- 238000013528 artificial neural network Methods 0.000 abstract description 14
- 238000013459 approach Methods 0.000 abstract description 4
- 230000035882 stress Effects 0.000 description 8
- 238000004891 communication Methods 0.000 description 6
- 238000002474 experimental method Methods 0.000 description 6
- 238000004519 manufacturing process Methods 0.000 description 6
- 229910052782 aluminium Inorganic materials 0.000 description 5
- 238000009826 distribution Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 230000008878 coupling Effects 0.000 description 4
- 238000010168 coupling process Methods 0.000 description 4
- 238000005859 coupling reaction Methods 0.000 description 4
- 230000007423 decrease Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000004927 fusion Effects 0.000 description 4
- 238000012546 transfer Methods 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 238000002076 thermal analysis method Methods 0.000 description 3
- 230000001052 transient effect Effects 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000005484 gravity Effects 0.000 description 2
- GNFTZDOKVXKIBK-UHFFFAOYSA-N 3-(2-methoxyethoxy)benzohydrazide Chemical compound COCCOC1=CC=CC(C(=O)NN)=C1 GNFTZDOKVXKIBK-UHFFFAOYSA-N 0.000 description 1
- 229910000831 Steel Inorganic materials 0.000 description 1
- 239000011149 active material Substances 0.000 description 1
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 description 1
- 238000005452 bending Methods 0.000 description 1
- 238000002425 crystallisation Methods 0.000 description 1
- 230000008025 crystallization Effects 0.000 description 1
- 230000008020 evaporation Effects 0.000 description 1
- 238000001704 evaporation Methods 0.000 description 1
- 230000004907 flux Effects 0.000 description 1
- 230000008018 melting Effects 0.000 description 1
- 238000002844 melting Methods 0.000 description 1
- 238000005272 metallurgy Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000010079 rubber tapping Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000007711 solidification Methods 0.000 description 1
- 230000008023 solidification Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 238000012916 structural analysis Methods 0.000 description 1
- 230000008646 thermal stress Effects 0.000 description 1
- 229920001187 thermosetting polymer Polymers 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Laser Beam Processing (AREA)
Abstract
The invention discloses a welding process parameter optimization method, equipment and a readable storage medium, wherein the welding process parameter optimization method trains a neural network model through a training sample so as to obtain a nonlinear mapping relation for predicting penetration data corresponding to actual welding process parameters; the method has the advantages that the actual process parameter combination is continuously optimized and adjusted towards the direction of target penetration data by utilizing the prediction capability of the trained neural network, so that the process of adjusting the welding parameters is simplified, and welding technicians can quickly adapt to high-quality process parameters according to the parameters of welding workpieces; the actual process parameter combination is continuously adjusted to approach the process parameter combination corresponding to the target penetration data, so that the actual process parameters are finally optimized, the mechanical property of the weld joint is improved, the process parameter debugging is flexible, the requirement of changeable welding scenes is met, and the welding quality and efficiency are greatly improved.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a welding process parameter optimization method, welding process parameter optimization equipment and a readable storage medium.
Background
With the rapid development of robotics, automated welding using industrial robots has become common. However, since the welding process has high complexity, uncertainty, variability and multivariable coupling, in the actual welding process, engineers with rich welding experience are often required to continuously adjust various parameters such as arc striking, arc closing, gas supply, welding gun speed and the like according to the current actual welding conditions, and the welding effect is continuously optimized by adjusting the parameters, so as to meet the expected product requirements. The debugging process of the traditional welding process is very complex, so that the technical problem of low welding production efficiency through the traditional welding mode is caused.
The above is only for the purpose of assisting understanding of the technical aspects of the present invention, and does not represent an admission that the above is prior art.
Disclosure of Invention
The invention mainly aims to provide a welding process parameter optimization method, and aims to solve the technical problem that the welding production efficiency is low through a traditional welding mode.
In order to achieve the above object, the present invention provides a welding process parameter optimization method applied to a welding process parameter optimization apparatus, the welding process parameter optimization method including the steps of:
training a preset neural network model by using a preset training sample to obtain a nonlinear mapping relation between welding process parameters and penetration data;
determining an optimized process parameter combination according to the preset target penetration data and the nonlinear mapping relation;
judging whether the difference value between the penetration data mapped by the optimized process parameter combination and the preset target penetration data is smaller than the preset threshold value or not;
and if the difference value is not less than the preset threshold value, adjusting the optimized process parameter combination until the difference value is less than the preset threshold value, and taking the optimized process parameter combination at the moment as the optimal process parameter combination.
Optionally, before the step of training the preset neural network model by using the preset training sample, the method further includes:
establishing a target laser welding model;
designing an orthogonal simulation test according to a preset welding process parameter range, and performing the orthogonal simulation test on the target laser welding model according to a finite element calculation mode;
and obtaining penetration data under different welding process parameter combinations obtained through the orthogonal simulation test, and taking the penetration data under the different welding process parameter combinations as the preset training sample.
Optionally, the step of establishing a target laser welding model comprises:
establishing an initial laser welding model based on a preset initial boundary condition;
acquiring a preset Gaussian heat surface heat source model, and correcting the preset Gaussian heat surface heat source model by utilizing preset experimental temperature measurement;
and combining the corrected Gaussian heat surface heat source model with the initial laser welding model to generate the target laser welding model.
Optionally, after the step of taking the optimized process parameter combination as the optimal process parameter combination until the difference is smaller than the preset threshold, the method further includes:
determining the change rule of the stress field in the welding process and the cooling process under the optimal technological parameter combination condition based on the target laser welding model;
acquiring welding surface information of a welding joint under the condition of optimal process parameter combination, and determining the mechanical property of the welding joint according to the welding surface information;
and judging the actual application effect of the optimal process parameter combination according to the change rule and the mechanical property.
Optionally, the step of determining an optimized process parameter combination according to the preset target penetration data and the nonlinear mapping relationship includes:
determining process parameters to be optimized according to the nonlinear mapping relation and the target penetration data;
and increasing or decreasing the process parameters to be optimized by a step length, and taking the adjusted process parameters to be optimized as the optimized process parameter combination.
Optionally, the neural network model is a BP neural network model, the welding process parameters include welding power, welding speed, and defocus amount, and the step of training the preset neural network model by using a preset training sample to obtain a nonlinear mapping relationship between the welding process parameters and the penetration data includes:
and training a BP neural network model with momentum factors by using a preset training sample to obtain a nonlinear mapping relation among the welding power, the welding speed, the defocusing amount and the penetration data.
Optionally, if the difference is not smaller than the preset threshold, adjusting the optimized process parameter combination until the difference is smaller than the preset threshold, and taking the optimized process parameter combination at this time as an optimal process parameter combination includes:
if the difference value between the penetration data mapped by the optimized process parameter combination and the preset target penetration data is not smaller than a preset threshold value, increasing or decreasing a step length for the welding power, the welding speed and the defocusing amount in the optimized process parameter combination, and determining a new optimized process parameter combination;
inputting a new optimized process parameter combination into the neural network model, and outputting current penetration data by the neural network model according to the nonlinear mapping relation;
and taking the welding power, the welding speed and the defocusing amount at the moment as the optimal process parameter combination until the difference value between the current penetration data and the preset target penetration data is smaller than a preset threshold value.
Optionally, after the step of determining whether the difference between the penetration data mapped by the optimized process parameter combination and the preset target penetration data is smaller than the preset threshold, the method further includes:
and if the difference value between the penetration data mapped by the optimized process parameter combination and the preset target penetration data is smaller than a preset threshold value, taking the optimized process parameter combination as the optimal process parameter combination.
In addition, in order to achieve the above object, the present invention further provides a welding process parameter optimizing apparatus, including:
the mapping relation obtaining module is used for training a preset neural network model by using a preset training sample to obtain a nonlinear mapping relation between welding process parameters and penetration data;
the optimization parameter determination module is used for determining an optimization process parameter combination according to the preset target penetration data and the nonlinear mapping relation;
the data difference value judging module is used for judging whether the difference value between the penetration data mapped by the optimized process parameter combination and the preset target penetration data is smaller than the preset threshold value or not;
and the optimal parameter determining module is used for adjusting the optimal process parameter combination if the difference is not less than a preset threshold value, and taking the optimal process parameter combination as the optimal process parameter combination when the difference is less than the preset threshold value.
In addition, in order to achieve the above object, the present invention also provides a welding process parameter optimizing apparatus, including: a memory, a processor, and a welding process parameter optimization program stored on the memory and executable on the processor, the welding process parameter optimization program when executed by the processor implementing the steps of the welding process parameter optimization method as described above.
In addition, to achieve the above object, the present invention also provides a computer readable storage medium, on which a welding process parameter optimization program is stored, which when executed by a processor implements the steps of the welding process parameter optimization method as described above.
The invention provides a welding process parameter optimization method, equipment and a computer readable storage medium. The welding process parameter optimization method is characterized in that a preset neural network model is trained by utilizing a preset training sample, and a nonlinear mapping relation between welding process parameters and penetration data is obtained; determining an optimized process parameter combination according to the preset target penetration data and the nonlinear mapping relation; judging whether the difference value between the penetration data mapped by the optimized process parameter combination and the preset target penetration data is smaller than the preset threshold value or not; and if the difference value is not less than the preset threshold value, adjusting the optimized process parameter combination until the difference value is less than the preset threshold value, and taking the optimized process parameter combination at the moment as the optimal process parameter combination. By the mode, the neural network model is trained through the training sample, so that the nonlinear mapping relation of the penetration data corresponding to the actual welding process parameter is obtained; the prediction capability of the neural network is utilized to continuously optimize and adjust the actual process parameter combination towards the direction of target penetration data, so that the process of adjusting the welding parameters is simplified, and welding technicians can quickly adapt to high-quality process parameters according to the parameters of the welding workpiece; the actual process parameter combination is continuously adjusted to approach the process parameter combination corresponding to the target penetration data, so that the actual process parameter is finally optimized, the mechanical property of a weld joint is improved, the process parameter is flexibly adjusted, the requirement of changeable welding scenes is met, the welding quality and efficiency are greatly improved, and the technical problem of low welding production efficiency in the traditional welding mode is solved.
Drawings
FIG. 1 is a schematic diagram of an apparatus architecture of a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a first embodiment of a method for optimizing parameters of a welding process according to the present invention;
FIG. 3 is a schematic diagram of a topology of a single hidden layer neural network according to the present invention;
FIG. 4 is a schematic flow chart of laser welding process parameter optimization;
fig. 5 is a functional block diagram of an embodiment of the apparatus of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
As shown in fig. 1, fig. 1 is a schematic terminal structure diagram of a hardware operating environment according to an embodiment of the present invention.
The terminal of the embodiment of the invention can be a PC, and can also be a mobile terminal device with a display function, such as a smart phone, a tablet computer and the like.
As shown in fig. 1, the terminal may include: a processor 1001, such as a CPU, a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface). The memory 1005 may be a high-speed RAM memory or a non-volatile memory (e.g., a magnetic disk memory). The memory 1005 may alternatively be a memory device separate from the processor 1001 described above.
Optionally, the terminal may further include a camera, a Radio Frequency (RF) circuit, a sensor, an audio circuit, a WiFi module, and the like. Such as light sensors, motion sensors, and other sensors. Specifically, the light sensor may include an ambient light sensor that may adjust the brightness of the display screen according to the brightness of ambient light, and a proximity sensor that may turn off the display screen and/or the backlight when the mobile terminal is moved to the ear. As one of the motion sensors, the gravity acceleration sensor can detect the magnitude of acceleration in each direction (generally, three axes), detect the magnitude and direction of gravity when the mobile terminal is stationary, and can be used for applications (such as horizontal and vertical screen switching, related games, magnetometer attitude calibration), vibration recognition related functions (such as pedometer and tapping) and the like for recognizing the attitude of the mobile terminal; of course, the mobile terminal may also be configured with other sensors such as a gyroscope, a barometer, a hygrometer, a thermometer, and an infrared sensor, which are not described herein again.
Those skilled in the art will appreciate that the terminal structure shown in fig. 1 is not intended to be limiting and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.
As shown in fig. 1, memory 1005, which is one type of computer storage medium, may include an operating system, a network communication module, a user interface module, and a welding process parameter optimization program.
In the terminal shown in fig. 1, the network interface 1004 is mainly used for connecting to a backend server and performing data communication with the backend server; the user interface 1003 is mainly used for connecting a client (user side) and performing data communication with the client; and processor 1001 may be configured to invoke the welding process parameter optimization program stored in memory 1005 and perform the following operations:
training a preset neural network model by using a preset training sample to obtain a nonlinear mapping relation between welding process parameters and penetration data;
determining an optimized process parameter combination according to the preset target penetration data and the nonlinear mapping relation;
judging whether the difference value between the penetration data mapped by the optimized process parameter combination and the preset target penetration data is smaller than the preset threshold value or not;
and if the difference value is not less than the preset threshold value, adjusting the optimized process parameter combination until the difference value is less than the preset threshold value, and taking the optimized process parameter combination at the moment as the optimal process parameter combination.
Further, processor 1001 may invoke a welding process parameter optimization program stored in memory 1005 to also perform the following operations:
establishing a target laser welding model;
designing an orthogonal simulation test according to a preset welding process parameter range, and performing the orthogonal simulation test on the target laser welding model according to a finite element calculation mode;
and obtaining penetration data under different welding process parameter combinations obtained through the orthogonal simulation test, and taking the penetration data under the different welding process parameter combinations as the preset training sample.
Further, processor 1001 may invoke a welding process parameter optimization program stored in memory 1005 to also perform the following operations:
establishing an initial laser welding model based on a preset initial boundary condition;
acquiring a preset Gaussian heat surface heat source model, and correcting the preset Gaussian heat surface heat source model by utilizing preset experimental temperature measurement;
and combining the corrected Gaussian heat surface heat source model with the initial laser welding model to generate the target laser welding model.
Further, processor 1001 may invoke a welding process parameter optimization program stored in memory 1005 to also perform the following operations:
determining the change rule of the stress field in the welding process and the cooling process under the optimal technological parameter combination condition based on the target laser welding model;
acquiring welding surface information of a welding joint under the condition of optimal process parameter combination, and determining the mechanical property of the welding joint according to the welding surface information;
and judging the actual application effect of the optimal process parameter combination according to the change rule and the mechanical property.
Further, processor 1001 may invoke a welding process parameter optimization program stored in memory 1005 to also perform the following operations:
determining process parameters to be optimized according to the nonlinear mapping relation and the target penetration data;
and increasing or decreasing the process parameters to be optimized by a step length, and taking the adjusted process parameters to be optimized as the optimized process parameter combination.
Further, processor 1001 may invoke a welding process parameter optimization program stored in memory 1005 to also perform the following operations:
and training a BP neural network model with momentum factors by using a preset training sample to obtain a nonlinear mapping relation among the welding power, the welding speed, the defocusing amount and the penetration data.
Further, processor 1001 may invoke a welding process parameter optimization program stored in memory 1005 to also perform the following operations:
if the difference value between the penetration data mapped by the optimized process parameter combination and the preset target penetration data is not smaller than a preset threshold value, increasing or decreasing a step length for the welding power, the welding speed and the defocusing amount in the optimized process parameter combination, and determining a new optimized process parameter combination;
inputting a new optimized process parameter combination into the neural network model, and outputting current penetration data by the neural network model according to the nonlinear mapping relation;
and taking the welding power, the welding speed and the defocusing amount at the moment as the optimal process parameter combination until the difference value between the current penetration data and the preset target penetration data is smaller than a preset threshold value.
Further, processor 1001 may invoke a welding process parameter optimization program stored in memory 1005 to also perform the following operations:
and if the difference value between the penetration data mapped by the optimized process parameter combination and the preset target penetration data is smaller than a preset threshold value, taking the optimized process parameter combination as the optimal process parameter combination.
Based on the hardware structure, the invention provides various embodiments of the welding process parameter optimization method.
Referring to fig. 2, fig. 2 is a schematic flow chart of a first embodiment of a welding process parameter optimization method.
With the rapid development of robotics, automated welding using industrial robots has become common. However, since the welding process has high complexity, uncertainty, variability and multivariable coupling, in the actual welding process, engineers with rich welding experience are often required to continuously adjust various parameters such as arc striking, arc closing, gas supply, welding gun speed and the like according to the current actual welding conditions, and the welding effect is continuously optimized by adjusting the parameters, so as to meet the expected product requirements. The debugging process of the traditional welding process is very complex, so that the technical problem of low welding production efficiency through the traditional welding mode is caused.
In this embodiment, to solve the above problem, the present invention provides a method for optimizing welding process parameters, that is, training a neural network model through a training sample so as to obtain a nonlinear mapping relationship for predicting penetration data corresponding to actual welding process parameters; the prediction capability of the neural network is utilized to continuously optimize and adjust the actual process parameter combination towards the direction of target penetration data, so that the process of adjusting the welding parameters is simplified, and welding technicians can quickly adapt to high-quality process parameters according to the parameters of the welding workpiece; the actual process parameter combination is continuously adjusted to approach the process parameter combination corresponding to the target penetration data, so that the actual process parameter is finally optimized, the mechanical property of a weld joint is improved, the process parameter is flexibly adjusted, the requirement of changeable welding scenes is met, the welding quality and efficiency are greatly improved, and the technical problem of low welding production efficiency in the traditional welding mode is solved. The welding process parameter optimization method is applied to terminal equipment.
The first embodiment of the present invention provides a welding process parameter optimization method, which includes the following steps:
step S10, training a preset neural network model by using a preset training sample to obtain a nonlinear mapping relation between welding process parameters and penetration data;
in this embodiment, the preset training samples are welding penetration data under different process parameters, which are obtained after a technician performs a large number of welding tests based on a reasonable welding model before step S10. The penetration is a distance between the deepest position of the molten portion of the base material and the surface of the base material. The preset neural network model may be a Back Propagation (BP) neural network, a Radial Basis Function (RBF) neural network, or the like. The BP neural network is a multi-layer feedforward network trained according to an error inverse propagation algorithm, can learn and store a large number of input and output mode mapping relations, and enables the sum of squares of errors of the network to be minimum by continuously adjusting the weight and the threshold of the network. The BP neural network mainly comprises an input layer, a hidden layer, an output layer and a transfer function among the layers, and can comprise different hidden layers. For the laser welding mode, the welding process parameters can be welding power, welding speed, defocusing amount and the like. Defocus is the distance between the laser focus and the active material. During the welding process, the influence of the defocusing amount on the welding quality is great. Laser welding usually requires a certain defocusing amount, because the power density of the spot center at the laser focus is too high, and holes are easily formed by evaporation. The power density distribution is relatively uniform in each plane away from the laser focal point. The actual welding task may be performed automatically by the welding robot according to a preset preprogrammed program, or may be performed by the welding robot by receiving commands sent by a welding technician. Specifically, a steel aluminum sheet is taken as a welding object, laser welding is taken as a welding implementation mode, and a BP neural network model is taken as the preset neural network model. The method comprises the steps that a terminal obtains welding penetration data under a plurality of different welding power, welding speed and defocusing amount conditions obtained through a large number of steel-aluminum laser welding tests, the welding penetration data are used as training samples, and a BP neural network for steel-aluminum laser welding is trained in a supervised learning mode, so that a nonlinear mapping relation among the welding power, the welding speed, the defocusing amount and the welding penetration is established, namely the trained BP neural network model has the capability of predicting the welding penetration mapped by the actual welding power, the welding speed and the defocusing amount.
Step S20, determining an optimized process parameter combination according to the preset target penetration data and the nonlinear mapping relation;
in this embodiment, the preset target penetration data is the optimal penetration data for completing the current welding task. The optimized technological parameters are a set consisting of different technological parameters such as welding power, welding speed, defocusing amount and the like after adjustment. And the terminal adjusts the values of different process parameters near the selected target penetration data according to the nonlinear mapping relation, so as to obtain a group of new process parameters, and combines the new process parameters to serve as optimized process parameters. Specifically, the terminal determines the welding power, the welding speed and the defocusing amount near the target welding depth data according to the nonlinear mapping relation among the welding power, the welding speed, the defocusing amount and the welding depth, and respectively increases or decreases a certain tiny step length for the welding power, the welding speed and the defocusing amount to obtain a new set of process parameter combinations of the welding power, the welding speed and the defocusing amount, namely the optimized process parameter combination.
Step S30, determining whether a difference between the penetration data mapped by the optimized process parameter combination and the preset target penetration data is less than the preset threshold;
in this embodiment, the terminal inputs the adjusted optimized process parameter combination into the trained neural network model, predicts the welding penetration data mapped by the optimized process parameter combination through the model, obtains the predicted actual welding penetration data, and compares the predicted actual welding penetration data with the target penetration data. And the terminal compares the difference between the actual welding penetration data and the target penetration data predicted by the model with a preset threshold value, and judges whether the difference is smaller than the preset threshold value. The preset threshold may be flexibly set according to actual conditions, which is not specifically limited in this embodiment. Specifically, taking a BP neural network model of a single hidden layer as an example, a network topology result is shown in fig. 3, for a laser welding mode, laser power P, welding speed V and defocusing amount f in optimized process parameters are used as input variables, the trained BP neural network model is input, the model comprises an input layer, a hidden layer, an output layer and transfer functions among the layers, and finally, the model can predict fusion depth D mapped by P, V, f which is currently input.
And step S40, if the difference value is not less than the preset threshold value, adjusting the optimized process parameter combination until the difference value is less than the preset threshold value, and taking the optimized process parameter combination at the moment as the optimal process parameter combination.
In this embodiment, if the terminal determines that the difference between the actual penetration data mapped by the optimized process parameters predicted by the model and the target penetration data is greater than or equal to the preset threshold, then the optimization process parameter combination can be further judged to not reach the ideal state, the optimization is further needed to be continued, the terminal respectively increases or decreases a certain tiny step length for each parameter in the current optimization process parameter combination again, continuously optimizing the current optimized process parameter combination, predicting corresponding actual penetration data through the model again, judging the size relationship between the difference value between the actual penetration data and the target penetration data and the preset threshold value again until the optimized process parameter combination is adjusted to the corresponding actual penetration data, and when the difference value between the target fusion depth data and the target fusion depth data is smaller than a preset threshold value, finishing the adjustment of the parameters, and taking the optimized process parameter combination at the moment as the optimal process parameter combination. In addition, in the actual welding process, the maximum adjustment times for optimizing the process parameter combination can be set so as to avoid the excessive consumption of resources. Specifically, as shown in fig. 4, the skilled artisan designs the orthogonal test based on the selected range of laser welding process parameters. Carrying out numerical simulation on the terminal to obtain a test result, and obtaining welding penetration data under different process parameters as a training sample of the neural network; the terminal trains the BP neural network model by using the training sample to obtain a nonlinear mapping relation between welding process parameters and welding depth; the terminal increases or decreases a certain tiny step length for each process parameter near the selected target penetration data point to obtain a new group of process parameters, and redesigns the orthogonal experiment to obtain a new process parameter combination; the terminal predicts the penetration data under new process parameters through BP neural network simulation; and the terminal searches a point which is most approximate to the proper penetration data in the new penetration data, if the penetration meets the requirement, the optimization is finished, otherwise, the terminal returns to the step of adjusting the process parameters to continue the optimization until the optimal process parameter combination is obtained.
In the embodiment, a preset neural network model is trained by using a preset training sample to obtain a nonlinear mapping relation between welding process parameters and penetration data; determining an optimized process parameter combination according to the preset target penetration data and the nonlinear mapping relation; judging whether the difference value between the penetration data mapped by the optimized process parameter combination and the preset target penetration data is smaller than the preset threshold value or not; and if the difference value is not less than the preset threshold value, adjusting the optimized process parameter combination until the difference value is less than the preset threshold value, and taking the optimized process parameter combination at the moment as the optimal process parameter combination. By the mode, the neural network model is trained through the training sample, so that the nonlinear mapping relation of the penetration data corresponding to the actual welding process parameter is obtained; the prediction capability of the neural network is utilized to continuously optimize and adjust the actual process parameter combination towards the direction of target penetration data, so that the process of adjusting the welding parameters is simplified, and welding technicians can quickly adapt to high-quality process parameters according to the parameters of the welding workpiece; the actual process parameter combination is continuously adjusted to approach the process parameter combination corresponding to the target penetration data, so that the actual process parameter is finally optimized, the mechanical property of a weld joint is improved, the process parameter is flexibly adjusted, the requirement of changeable welding scenes is met, the welding quality and efficiency are greatly improved, and the technical problem of low welding production efficiency in the traditional welding mode is solved.
Not shown, a second embodiment of the method for optimizing parameters of a welding process according to the present invention is provided based on the first embodiment shown in fig. 2. In this embodiment, before step S10, the method further includes:
step a, establishing a target laser welding model;
in this embodiment, it can be understood that, in order to obtain training sample data for training a neural network model, a technician needs to establish a welding model on a terminal first, and then perform a large number of welding tests based on the welding model. In the embodiment, a laser welding mode is taken as an example, and a target laser welding model can be simulated through finite element analysis software ABAQUS, ANSYS, MSC and the like in an actual operation process. It should be noted that, since the welding process is a complex process involving multiple aspects of physical change, heat transfer, mechanics, metallurgy, etc., including the phase processes of electromagnetism, heat transfer, melting solidification, crystallization, phase change, etc., all the processes cannot be taken into account by the finite element analysis software, when the laser welding model is established, some reasonable assumptions and simplifications can be made on the variables that have weak influence, so as to avoid the problems of excessive data, excessive calculation amount, long consumed time, difficult calculation convergence, etc.
B, designing an orthogonal simulation test according to a preset welding process parameter range, and performing the orthogonal simulation test on the target laser welding model according to a finite element calculation mode;
in this embodiment, the preset welding process parameter ranges may be specifically set according to actual conditions, the welding modes are different, the welding materials are different, and the corresponding welding process parameter ranges may also be different, which is not specifically limited in this embodiment. The technician designs an orthogonal simulation test according to a preset welding process parameter range, and performs the orthogonal simulation test on the laser welding model established by using finite element analysis software.
And c, obtaining penetration data under different welding process parameter combinations obtained through the orthogonal simulation test, and taking the penetration data under the different welding process parameter combinations as the preset training sample.
In this embodiment, a technician performs an orthogonal test on the laser welding model, and analyzes the change rule of the calculated temperature field and stress field to obtain each welding penetration data corresponding to a plurality of sets of different welding process parameter combinations. And the terminal takes the welding penetration data under the combination of a plurality of groups of different welding process parameters obtained by calculation as training sample data for training the neural network model.
Further, in this embodiment, step a includes:
step d, establishing an initial laser welding model based on a preset initial boundary condition;
in this embodiment, taking the used finite element software as ANSYS as an example, the initial boundary conditions are preset as initial conditions and boundary conditions. The initial conditions were: at a temperature t of 0, the workpiece has a uniform initial temperature, typically the ambient temperature. The boundary condition needs to consider the Gaussian heat flow distribution acted by a heat source, the symmetrical plane of welding is considered as an adiabatic boundary condition, and for a high-temperature area of a welding seam, the convection boundary condition and the radiation boundary condition are considered by covering a layer of surface effect unit on the surface of a solid unit. And the terminal establishes a geometric model of the initial laser welding by using ANSYS software according to the initial conditions and the boundary conditions. In the simulation process, for three parts of the model, hexahedral meshes are divided by adopting a scanning method, and three layers of meshes are defined in the thickness direction of the plate to capture the bending deformation effect. The Ansys simulation platform can be used for directly carrying out thermosetting coupling numerical solution on the welding process, and further obtaining the temperature field and stress field distribution under the condition of given process parameters.
Step e, acquiring a preset Gaussian heat surface heat source model, and correcting the preset Gaussian heat surface heat source model by utilizing preset experiment temperature measurement;
in this embodiment, a gaussian surface heat source model is selected in consideration of the fact that the welding target in this embodiment is a steel-aluminum thin plate. In particular, in order to simulate the thermal field distribution generated by the laser welding process, a precise heat source must be established. For a Moving Heat source application problem, a gaussian Heat source load setting can be achieved with the ACT tool "Moving _ Heat _ Flux" of ANSYS software: moving the heat flow rate or moving the heat energy. And the terminal acquires the experiment temperature recorded in the actual welding experiment, and corrects the heat source model according to the experiment temperature so that the model is more suitable for the actual welding condition.
And f, combining the corrected Gaussian heat surface heat source model with the initial laser welding model to generate the target laser welding model.
In this embodiment, the terminal combines the gaussian hot surface heat source model corrected according to the experimental temperature measurement with the initial laser welding model established according to the initial conditions and the boundary conditions based on ANSYS software to generate the target laser welding model.
Further, in this embodiment, after step S40, the method further includes:
step g, determining the change rule of the stress field in the welding process and the cooling process under the optimal process parameter combination condition based on the target laser welding model;
in this embodiment, the terminal sets an optimal process parameter combination for the target laser welding model on an ANSYS simulation platform, performs welding process simulation on the target laser welding model, and analyzes the change rule of the stress field in the welding process and the cooling process under the condition. It should be noted that when the terminal performs simulation on the laser welding model on the ANSYS simulation platform according to various experimental parameters, transient thermal analysis and thermal stress analysis in the laser welding process are correspondingly performed. And the terminal transmits the temperature distribution data obtained by the transient thermal analysis to the structural module to simulate the phenomena of thermal warping and thermal deformation in the laser welding process according to the sequential coupling analysis of the transient thermal analysis and the static structural analysis.
H, acquiring welding surface information of the welding joint under the condition of optimal technological parameter combination, and determining the mechanical property of the welding joint according to the welding surface information;
in this embodiment, a technician can observe the surface formability and surface defects of the welded joint after welding under the condition of the optimal process parameter combination, and then determine the mechanical properties of the welded joint based on the surface formability and the surface defects. Specifically, the higher the surface formability of the welded joint, the less the surface defects, and the better the mechanical properties of the welded joint can be determined.
And i, judging the actual application effect of the optimal process parameter combination according to the change rule and the mechanical property.
In this embodiment, the terminal may determine the actual application effect of the optimal process parameter combination by combining the change rule of the stress field of the welded workpiece and the mechanical property of the welded joint under the welding condition of the optimal process parameter combination. If the actual application effect is not good, the optimal process parameter combination can be continuously optimized.
In this embodiment, a large amount of effective training sample data is provided for the neural network model by further establishing a target laser welding model and performing an orthogonal simulation test; the heat source model used in the laser welding model is corrected through preset experimental temperature measurement, so that the data obtained by the experiment more conforms to the actual welding condition, and the practicability of the data is improved; by analyzing the change rule and the mechanical property of the stress field under the optimal process parameter combination condition, feedback information is provided for the welding process, and meanwhile, a real basis is provided for the subsequent welding test.
Not shown, a third embodiment of the method for optimizing parameters of a welding process according to the present invention is provided based on the first embodiment shown in fig. 2. In the present embodiment, step S20 includes:
j, determining a process parameter to be optimized according to the nonlinear mapping relation and the target penetration data;
in this embodiment, the terminal selects the welding power, the welding speed and the defocusing amount near the target penetration data based on the nonlinear mapping relationship between the welding power, the welding speed, the defocusing amount and the welding penetration determined by the trained BP neural network model, and uses the selected welding power, welding speed and defocusing amount as the process parameters to be optimized.
And k, increasing or decreasing a step length for the process parameter to be optimized, and taking the adjusted process parameter to be optimized as the optimized process parameter combination.
In this embodiment, the terminal respectively increases or decreases a certain micro step length for the welding power, the welding speed, and the defocus parameter to be optimized, and combines the new welding power, the welding speed, and the defocus parameter as the optimization process parameter.
Further, in the present embodiment, step S10 includes:
and step l, training a BP neural network model with the momentum factor by using a preset training sample to obtain a nonlinear mapping relation among the welding power, the welding speed, the defocusing amount and the penetration data.
In this embodiment, it should be noted that the learning convergence rate of the standard BP algorithm is generally slow and is easily trapped in a local minimum, and selecting the BP algorithm with momentum can suppress the weight change and ensure a stable learning process. Specifically, through repeated tests, the momentum factor value suitable for the laser welding process of the steel-aluminum thin plate in the scheme is 0.5.
Further, in the present embodiment, step S40 includes:
step m, if the difference value between the penetration data mapped by the optimized process parameter combination and the preset target penetration data is not smaller than a preset threshold value, increasing or decreasing a step length for the welding power, the welding speed and the defocusing amount in the optimized process parameter combination, and determining a new optimized process parameter combination;
in this embodiment, if the optimized process parameter combination is input into the trained BP neural network model via the terminal, the penetration data corresponding to the optimized process parameter combination predicted by the model is obtained, and the difference value between the target penetration data and the optimized process parameter combination is greater than or equal to the preset threshold, a certain tiny step length is respectively increased or decreased for the welding power, the welding speed and the defocus in the optimized process parameter combination, and the adjusted welding power, the welding speed and the defocus are used as a new optimized process parameter combination.
N, inputting a new optimized process parameter combination into the neural network model, and outputting current fusion depth data by the neural network model according to the nonlinear mapping relation;
in this embodiment, the terminal inputs the new optimized process parameter combination as an input variable of the input model into the trained BP neural network model, and predicts the penetration data corresponding to the new optimized process parameter combination according to the nonlinear mapping relationship obtained by model training to obtain the predicted current penetration data.
And step o, taking the welding power, the welding speed and the defocusing amount at the moment as the optimal process parameter combination until the difference value between the current penetration data and the preset target penetration data is smaller than a preset threshold value.
In this embodiment, the terminal continuously adjusts the optimized process parameter combination including the welding power, the welding speed, and the defocus amount until it is detected that the difference between the current penetration data and the target penetration data corresponding to the current optimized process parameter combination is smaller than the preset threshold, it may be determined that the expected target has been reached, the adjustment of the process parameters is stopped, and the welding power, the welding speed, and the defocus amount at this time are used as the optimal process parameter combination.
Further, in this embodiment, after step S30, the method further includes:
and p, if the difference value between the penetration data mapped by the optimized process parameter combination and the preset target penetration data is smaller than a preset threshold value, taking the optimized process parameter combination as the optimal process parameter combination.
In this embodiment, if the terminal detects that the difference between the penetration data corresponding to the optimized process parameter combination and the target penetration data is smaller than the preset threshold, it may determine that the current target is reached, and no adjustment is required to the process parameters, and the optimized process parameter combination is used as the optimal process parameter combination. And the welding robot welds the workpiece to be welded by taking the optimal process parameter combination as a welding parameter setting condition.
In this embodiment, the optimization adjustment of the process parameter to be optimized is further realized by increasing or decreasing a certain tiny step length for the process parameter to be optimized; by adopting the BP neural network with momentum, compared with the standard BP neural network, the learning process is more stable, the convergence speed is higher, and the optimization efficiency of the process parameters is further improved; optimizing and adjusting the process parameters continuously until the expected target data range is reached, so that the optimization of each process parameter is completed; by directly using the optimized process parameter combination meeting the expected target data range as the optimal process parameter combination, the optimal process parameters can be quickly obtained, and the efficiency of process parameter optimization is improved.
The invention also provides welding process parameter optimization equipment.
The welding process parameter optimization device comprises a processor, a memory and a welding process parameter optimization program stored on the memory and operable on the processor, wherein the welding process parameter optimization program, when executed by the processor, implements the steps of the welding process parameter optimization method as described above.
The method implemented when the welding process parameter optimization program is executed may refer to various embodiments of the welding process parameter optimization method of the present invention, and details thereof are not repeated herein.
The invention also provides a computer readable storage medium.
The computer readable storage medium of the present invention has stored thereon a welding process parameter optimization program that, when executed by a processor, implements the steps of the welding process parameter optimization method as described above.
The method implemented when the welding process parameter optimization program is executed may refer to each embodiment of the welding process parameter optimization method of the present invention, and details are not repeated herein.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A welding process parameter optimization method is characterized by comprising the following steps:
training a preset neural network model by using a preset training sample to obtain a nonlinear mapping relation between welding process parameters and penetration data;
determining an optimized process parameter combination according to the preset target penetration data and the nonlinear mapping relation;
judging whether the difference value between the penetration data mapped by the optimized process parameter combination and the preset target penetration data is smaller than the preset threshold value or not;
and if the difference value is not less than the preset threshold value, adjusting the optimized process parameter combination until the difference value is less than the preset threshold value, and taking the optimized process parameter combination at the moment as the optimal process parameter combination.
2. The method for optimizing parameters for a welding process according to claim 1, wherein said step of training a predetermined neural network model using predetermined training samples is preceded by the steps of:
establishing a target laser welding model;
designing an orthogonal simulation test according to a preset welding process parameter range, and performing the orthogonal simulation test on the target laser welding model according to a finite element calculation mode;
and obtaining penetration data under different welding process parameter combinations obtained through the orthogonal simulation test, and taking the penetration data under the different welding process parameter combinations as the preset training sample.
3. The method of optimizing welding process parameters of claim 2, wherein the step of establishing a target laser weld model comprises:
establishing an initial laser welding model based on a preset initial boundary condition;
acquiring a preset Gaussian heat surface heat source model, and correcting the preset Gaussian heat surface heat source model by utilizing preset experimental temperature measurement;
and combining the corrected Gaussian heat surface heat source model with the initial laser welding model to generate the target laser welding model.
4. The welding process parameter optimization method according to claim 2, wherein the step of using the optimized process parameter combination as the optimal process parameter combination until the difference is smaller than the preset threshold further comprises:
determining the change rule of the stress field in the welding process and the cooling process under the optimal technological parameter combination condition based on the target laser welding model;
acquiring welding surface information of a welding joint under the condition of optimal process parameter combination, and determining the mechanical property of the welding joint according to the welding surface information;
and judging the actual application effect of the optimal process parameter combination according to the change rule and the mechanical property.
5. The welding process parameter optimization method of claim 1, wherein the step of determining an optimized process parameter combination based on the pre-set target penetration data and the non-linear mapping relationship comprises:
determining process parameters to be optimized according to the nonlinear mapping relation and the target penetration data;
and increasing or decreasing the process parameters to be optimized by a step length, and taking the adjusted process parameters to be optimized as the optimized process parameter combination.
6. The method for optimizing parameters of a welding process according to claim 1, wherein said neural network model is a BP neural network model, said parameters of the welding process include welding power, welding speed and defocus, said training the neural network model with preset training samples to obtain a non-linear mapping relationship between the parameters of the welding process and the penetration data comprises:
and training a BP neural network model with momentum factors by using a preset training sample to obtain a nonlinear mapping relation among the welding power, the welding speed, the defocusing amount and the penetration data.
7. The welding process parameter optimization method according to any one of claims 1 to 6, wherein if the difference is not less than a preset threshold, the step of adjusting the optimized process parameter combination until the difference is less than the preset threshold, and taking the optimized process parameter combination at that time as the optimal process parameter combination comprises:
if the difference value between the penetration data mapped by the optimized process parameter combination and the preset target penetration data is not smaller than a preset threshold value, increasing or decreasing a step length for the welding power, the welding speed and the defocusing amount in the optimized process parameter combination, and determining a new optimized process parameter combination;
inputting a new optimized process parameter combination into the neural network model, and outputting current penetration data by the neural network model according to the nonlinear mapping relation;
and taking the welding power, the welding speed and the defocusing amount at the moment as the optimal process parameter combination until the difference value between the current penetration data and the preset target penetration data is smaller than a preset threshold value.
8. The welding process parameter optimization method of claim 1, wherein after the step of determining whether the difference between the penetration data mapped by the optimized process parameter combination and the preset target penetration data is less than the preset threshold, the method further comprises:
and if the difference value between the penetration data mapped by the optimized process parameter combination and the preset target penetration data is smaller than a preset threshold value, taking the optimized process parameter combination as the optimal process parameter combination.
9. A welding process parameter optimizing device, characterized in that the welding process parameter optimizing device comprises: memory, a processor and a welding process parameter optimization program stored on the memory and executable on the processor, the welding process parameter optimization program when executed by the processor implementing the steps of the welding process parameter optimization method of any one of claims 1 to 8.
10. A computer readable storage medium, characterized in that the computer readable storage medium has stored thereon a welding process parameter optimization program, which when executed by a processor implements the steps of the welding process parameter optimization method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010126442.6A CN111461398A (en) | 2020-02-27 | 2020-02-27 | Welding process parameter optimization method and device and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010126442.6A CN111461398A (en) | 2020-02-27 | 2020-02-27 | Welding process parameter optimization method and device and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111461398A true CN111461398A (en) | 2020-07-28 |
Family
ID=71684193
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010126442.6A Pending CN111461398A (en) | 2020-02-27 | 2020-02-27 | Welding process parameter optimization method and device and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111461398A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112380743A (en) * | 2020-11-02 | 2021-02-19 | 湖北文理学院 | Method for determining dissimilar steel laser penetration welding parameters |
| CN112555451A (en) * | 2020-10-29 | 2021-03-26 | 成都成高阀门有限公司 | Pressing process parameter determination method for all-welded ball valve seat sealing groove and semi-finished valve seat |
| CN112710490A (en) * | 2020-12-21 | 2021-04-27 | 歌尔光学科技有限公司 | Performance detection method for laser spraying welding machine |
| CN113111006A (en) * | 2021-05-06 | 2021-07-13 | 上海三一重机股份有限公司 | Debugging method and system for operating machine control system |
| CN113305853A (en) * | 2021-07-28 | 2021-08-27 | 季华实验室 | Optimized welding parameter obtaining method and device, electronic equipment and storage medium |
| CN113369753A (en) * | 2021-07-01 | 2021-09-10 | 中铁磁浮科技（成都）有限公司 | Welding parameter determination method based on finite element analysis and welding method |
| CN114202262A (en) * | 2022-02-21 | 2022-03-18 | 德州联合拓普复合材料科技有限公司 | Prepreg process improvement method and system based on neural network and storage medium |
| CN114548610A (en) * | 2022-04-27 | 2022-05-27 | 季华实验室 | Automatic arrangement method and device for engine cover outer plate stamping process |
| CN114871577A (en) * | 2022-05-13 | 2022-08-09 | 武汉锐科光纤激光技术股份有限公司 | Method and apparatus for welding gear cutter head, storage medium, and electronic apparatus |
| WO2023045237A1 (en) * | 2021-09-27 | 2023-03-30 | 深圳市联赢激光股份有限公司 | Intelligent welding method, intelligent welding system, and computer storage medium |
| CN115922061A (en) * | 2022-12-07 | 2023-04-07 | 长沙大科激光科技有限公司 | Copper-aluminum dissimilar metal lap welding method based on ultrasonic real-time measurement |
| CN117483954A (en) * | 2023-12-29 | 2024-02-02 | 深圳市恒永达科技股份有限公司 | Thin-wall metal laser welding method, system and medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102999676A (en) * | 2012-12-24 | 2013-03-27 | 湖南大学 | Process optimization method of steel/aluminum laser welding brazing |
| CN106909727A (en) * | 2017-02-20 | 2017-06-30 | 武汉理工大学 | Laser welding temperature field Finite Element Method based on BP neural network and Genetic Algorithms |
-
2020
- 2020-02-27 CN CN202010126442.6A patent/CN111461398A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102999676A (en) * | 2012-12-24 | 2013-03-27 | 湖南大学 | Process optimization method of steel/aluminum laser welding brazing |
| CN106909727A (en) * | 2017-02-20 | 2017-06-30 | 武汉理工大学 | Laser welding temperature field Finite Element Method based on BP neural network and Genetic Algorithms |
Non-Patent Citations (1)
| Title |
|---|
| 乔小杰: "基于 BP 神经网络钢/铝激光焊工艺优化及组织性能研究", 《中国优秀硕士学位论文全文数据库 (电子刊)》 * |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112555451A (en) * | 2020-10-29 | 2021-03-26 | 成都成高阀门有限公司 | Pressing process parameter determination method for all-welded ball valve seat sealing groove and semi-finished valve seat |
| CN112555451B (en) * | 2020-10-29 | 2022-03-18 | 成都成高阀门有限公司 | Pressing process parameter determination method for all-welded ball valve seat sealing groove and semi-finished valve seat |
| CN112380743A (en) * | 2020-11-02 | 2021-02-19 | 湖北文理学院 | Method for determining dissimilar steel laser penetration welding parameters |
| CN112710490B (en) * | 2020-12-21 | 2022-11-11 | 歌尔光学科技有限公司 | Performance detection method for laser spraying welding machine |
| CN112710490A (en) * | 2020-12-21 | 2021-04-27 | 歌尔光学科技有限公司 | Performance detection method for laser spraying welding machine |
| CN113111006A (en) * | 2021-05-06 | 2021-07-13 | 上海三一重机股份有限公司 | Debugging method and system for operating machine control system |
| CN113369753A (en) * | 2021-07-01 | 2021-09-10 | 中铁磁浮科技（成都）有限公司 | Welding parameter determination method based on finite element analysis and welding method |
| CN113305853A (en) * | 2021-07-28 | 2021-08-27 | 季华实验室 | Optimized welding parameter obtaining method and device, electronic equipment and storage medium |
| WO2023045237A1 (en) * | 2021-09-27 | 2023-03-30 | 深圳市联赢激光股份有限公司 | Intelligent welding method, intelligent welding system, and computer storage medium |
| CN114202262A (en) * | 2022-02-21 | 2022-03-18 | 德州联合拓普复合材料科技有限公司 | Prepreg process improvement method and system based on neural network and storage medium |
| CN114548610B (en) * | 2022-04-27 | 2022-07-08 | 季华实验室 | Automatic arrangement method and device for engine cover outer plate stamping process |
| CN114548610A (en) * | 2022-04-27 | 2022-05-27 | 季华实验室 | Automatic arrangement method and device for engine cover outer plate stamping process |
| CN114871577A (en) * | 2022-05-13 | 2022-08-09 | 武汉锐科光纤激光技术股份有限公司 | Method and apparatus for welding gear cutter head, storage medium, and electronic apparatus |
| CN115922061A (en) * | 2022-12-07 | 2023-04-07 | 长沙大科激光科技有限公司 | Copper-aluminum dissimilar metal lap welding method based on ultrasonic real-time measurement |
| CN117483954A (en) * | 2023-12-29 | 2024-02-02 | 深圳市恒永达科技股份有限公司 | Thin-wall metal laser welding method, system and medium |
| CN117483954B (en) * | 2023-12-29 | 2024-03-22 | 深圳市恒永达科技股份有限公司 | Thin-wall metal laser welding method, system and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111461398A (en) | Welding process parameter optimization method and device and readable storage medium | |
| CN110666321B (en) | Welding method, automatic welding device, and storage medium | |
| CN105234599B (en) | Welding temperature station control system and method | |
| US10786849B2 (en) | Systems and methods for performing microstructure simulation and implementation of additive manufacturing processes | |
| WO2019103772A1 (en) | Detection and root cause analysis of welding defects | |
| Pires et al. | Advances in robotics for additive/hybrid manufacturing: robot control, speech interface and path planning | |
| CN103909516A (en) | Robot teaching system, robot teaching assistant device and robot teaching method | |
| CN111283307A (en) | Simulation welding method and device, terminal equipment and storage medium | |
| Wang et al. | Intelligent modelling of back-side weld bead geometry using weld pool surface characteristic parameters | |
| Pan et al. | Automated offline programming for robotic welding system with high degree of freedoms | |
| Liu et al. | Control of human arm movement in machine-human cooperative welding process | |
| CN113840675B (en) | In-situ monitoring system auxiliary material and parameter development for additive manufacturing | |
| US11733678B2 (en) | Method for determining building instructions for an additive manufacturing method, method for generating a database with correction measures for controlling the process of an additive manufacturing method | |
| CN109029453A (en) | Cladding head posture path planning method, device, terminal, storage medium and system | |
| Wu et al. | Weld penetration in situ prediction from keyhole dynamic behavior under time-varying VPPAW pools via the OS-ELM model | |
| Jović et al. | Estimation of the laser cutting operating cost by support vector regression methodology | |
| CN110893515B (en) | Machining condition adjustment device and machine learning device | |
| CN116038163A (en) | Laser intelligent welding system and method | |
| Fergani et al. | A machine learning-based digital twin of the manufacturing process: metal powder-bed fusion case | |
| EP4389337A1 (en) | Deformation predicting system and program | |
| EP3412381A1 (en) | Library of predefined shapes for additive manufacturing processes | |
| Wang et al. | Visual sensing and controlling of the keyhole in robotic plasma arc welding | |
| JP2012053556A (en) | Analysis model generation method, structure analysis method, program, and analyzer | |
| Mendizabal et al. | Improved accuracy of the inherent shrinkage method for fast and more reliable welding distortion calculations | |
| CN114357850A (en) | Welding process parameter generation method, generation device and welding method |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200728 |
|
| RJ01 | Rejection of invention patent application after publication |