A method and device for constructing a welding process parameter optimization model

Abstract

The purpose of this application is to provide a method and device for constructing a welding process parameter optimization model, the method comprising: constructing a heat-affected zone width prediction model based on training sample data using a neural network model, wherein the training sample data includes first welding process parameter information and first heat-affected zone width information corresponding to the first welding process parameter information; based on the heat-affected zone width prediction model, combined with a particle swarm algorithm, constructing a welding process parameter optimization model. This application proposes to construct a heat-affected zone width prediction model to reflect the relationship between welding process parameters and welding quality, and to determine a welding process parameter optimization model by combining the model with a particle swarm algorithm, so that the particle swarm algorithm can be used to determine the welding process parameters with the best welding quality, so as to determine the optimal welding process parameters faster and more accurately.

Description

Technical Field

[0001] The present application relates to the field of welding, and in particular to a technology for constructing a welding process parameter optimization model. Background Art

[0002] In the process of automatic welding, the welding quality is affected by a variety of welding process parameters. For example, when the welding speed is too fast, the weld may become narrower, the penetration depth may become shallower, and the weld excess height may become lower; when the welding current increases, the weld may become wider, the penetration depth may become deeper, and the weld excess height may become higher; when the gas flow is insufficient, quality defects such as pores are very likely to occur. In order to ensure the quality of welding, companies often need to combine multiple departments such as process, production, and quality to carry out a large number of welding process experiments, and polish and section the welds, and use flaw detection or X-ray to detect the welding quality, in order to finally determine a set of suitable welding process parameters. This method of determining welding process parameters often requires a lot of manpower and material resources, and the welding process parameters finally determined are not necessarily the best. Summary of the invention

[0003] One object of the present application is to provide a method and device for constructing a welding process parameter optimization model.

[0004] According to one aspect of the present application, a method for constructing a welding process parameter optimization model is provided, the method comprising:

[0005] Based on the training sample data, a heat-affected zone width prediction model is constructed using a neural network model, wherein the training sample data includes first welding process parameter information and first heat-affected zone width information corresponding to the first welding process parameter information;

[0006] Based on the heat affected zone width prediction model and combined with the particle swarm algorithm, a welding process parameter optimization model is constructed.

[0007] According to one aspect of the present application, a computer device for constructing a welding process parameter optimization model is provided, comprising a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of any of the methods described above.

[0008] According to one aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored, characterized in that when the computer program is executed by a processor, the steps of any of the methods described above are implemented.

[0009] According to one aspect of the present application, a computer program product is provided, including a computer program, characterized in that when the computer program is executed by a processor, the steps of any of the methods described above are implemented.

[0010] According to one aspect of the present application, a device for constructing a welding process parameter optimization model is provided, the device comprising:

[0011] A module for constructing a heat-affected zone width prediction model based on training sample data and using a neural network model, wherein the training sample data includes first welding process parameter information and first heat-affected zone width information corresponding to the first welding process parameter information;

[0012] The first and second modules are used to construct a welding process parameter optimization model based on the heat affected zone width prediction model combined with the particle swarm algorithm.

[0013] Compared with the prior art, the present application constructs a heat-affected zone width prediction model based on training sample data and a neural network model, wherein the training sample data includes the first welding process parameter information and the first heat-affected zone width information corresponding to the first welding process parameter information. Based on the heat-affected zone width prediction model, a welding process parameter optimization model is constructed in combination with a particle swarm algorithm. The present application takes into account that in the actual welding process, the heat-affected zone absorbs enough heat for a long time, and the microstructure and performance of the zone will change, resulting in performance differences from the original parent material. These differences will make the heat-affected zone the weakest part of the component. Therefore, the wider the heat-affected zone, the worse the corresponding welding quality and performance. The present application proposes to construct a heat-affected zone width prediction model to reflect the relationship between welding process parameters and welding quality, and to determine the welding process parameter optimization model by combining the heat-affected zone width prediction model with a particle swarm algorithm, so that the particle swarm algorithm can be used to determine the welding process parameters with the best welding quality. The present application determines the optimal welding process parameters faster and more accurately by constructing a welding process parameter optimization model. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings:

[0015] Figure 1 A flow chart of a method for constructing a welding process parameter optimization model according to an embodiment of the present application is shown;

[0016] Figure 2 A structural diagram of a device for constructing a welding process parameter optimization model according to an embodiment of the present application is shown;

[0017] Figure 3 An exemplary system is shown that can be used to implement the various embodiments described in this application.

[0018] The same or similar reference numerals in the drawings represent the same or similar components. DETAILED DESCRIPTION

[0019] The present application is described in further detail below in conjunction with the accompanying drawings.

[0020] In a typical configuration of the present application, the terminal, the device of the service network and the trusted party all include one or more processors (eg, a central processing unit (CPU)), an input / output interface, a network interface and a memory.

[0021] Memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash memory. Memory is an example of a computer-readable medium.

[0022] Computer readable media include permanent and non-permanent, removable and non-removable media that can be used to store information by any method or technology. Information can be computer readable instructions, data structures, modules of programs or other data. Examples of computer storage media include, but are not limited to, Phase-Change Memory (PCM), Programmable Random Access Memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of random access memory (RAM), Read-Only Memory (ROM), Electrically-Erasable Programmable Read-Only Memory (EEPROM), Flash memory or other memory technology, Compact Disc Read-Only Memory (CD-ROM), Digital Versatile Disc (DVD) or other optical storage, magnetic cassettes, tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0023] The devices referred to in this application include but are not limited to user devices, network devices, or devices formed by integrating user devices and network devices through a network. The user devices include but are not limited to any mobile electronic products that can interact with users (for example, interact with users through a touchpad), such as smart phones, tablet computers, etc. The mobile electronic products can use any operating system, such as Android operating system, iOS operating system, etc. Among them, the network device includes an electronic device that can automatically perform numerical calculations and information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable logic devices (Programmable Logic Device, PLD), field programmable gate arrays (Field Programmable Gate Array, FPGA), digital signal processors (Digital Signal Processor, DSP), embedded devices, etc. The network devices include but are not limited to computers, network hosts, single network servers, multiple network server sets or multiple servers. The cloud is composed of a large number of computers or network servers based on cloud computing (Cloud Computing), wherein cloud computing is a type of distributed computing, a virtual supercomputer composed of a group of loosely coupled computer sets. The network includes but is not limited to the Internet, a wide area network, a metropolitan area network, a local area network, a VPN network, a wireless self-organizing network (Ad Hoc network), etc. Preferably, the device may also be a program running on the user device, the network device, or a device formed by integrating the user device and the network device, the network device, the touch terminal, or the network device and the touch terminal through a network.

[0024] Of course, those skilled in the art should understand that the above-mentioned devices are only examples, and other existing or future devices that are applicable to the present application should also be included in the scope of protection of the present application and are included here by reference.

[0025] In the description of the present application, “plurality” means two or more, unless otherwise clearly and specifically defined.

[0026] Figure 1A flow chart of a method for constructing a welding process parameter optimization model according to an embodiment of the present application is shown, and the method includes: step S11 and step S12. In step S11, the device 1 constructs a heat-affected zone width prediction model based on training sample data and using a neural network model, wherein the training sample data includes first welding process parameter information and first heat-affected zone width information corresponding to the first welding process parameter information; in step S12, the device 1 constructs a welding process parameter optimization model based on the heat-affected zone width prediction model in combination with a particle swarm algorithm.

[0027] In step S11, the device 1 constructs a heat-affected zone width prediction model based on the training sample data and the neural network model, wherein the training sample data includes the first welding process parameter information and the first heat-affected zone width information corresponding to the first welding process parameter information. In some embodiments, the device 1 includes but is not limited to user equipment and network equipment with information processing or computing capabilities, such as a tablet computer, a computer, and a server. In some embodiments, the neural network model includes but is not limited to a feedforward neural network model, such as a BP (Back Propagation) neural network model. In some embodiments, the training sample data includes the first welding process parameter information obtained from actual welding, and the first heat-affected zone width information measured when welding based on the corresponding first welding process parameter information. The first welding process parameter information includes a plurality of value combinations corresponding to the welding process parameters. The welding process parameters include but are not limited to welding current, welding voltage, gas flow rate, welding speed and / or wire feeding speed. For example, welding current 240A, welding voltage 20V, gas flow rate 15L / min, welding speed 4mm / s, and wire feeding speed 4m / min can correspond to a value combination in the first welding process parameter information. The heat affected zone (HAZ) width information is the width of the area where microstructure and performance changes occur within a certain range near both sides of the weld under the action of a high-temperature heat source during welding. The first heat affected zone width information includes the heat affected zone width corresponding to each value combination in the first welding process parameter information. In some embodiments, the device 1 can use the first welding process parameter information in the training sample data as the input of the model and the first heat affected zone width information as the output of the model to establish a heat affected zone width prediction model based on the neural network model.

[0028] In step S12, the device 1 constructs a welding process parameter optimization model based on the heat affected zone width prediction model and in combination with the particle swarm algorithm. In some embodiments, there are many dimensions of welding process parameters that affect welding quality. Some of the relationships between these welding process parameters and quality are linear, some are nonlinear; some are continuous, some are discrete; some are single peaks, and some are multi-peaks; it is often difficult to directly combine the welding process parameters that make the welding quality the best. The constructed heat affected zone width prediction model can be used to reflect the relationship between welding process parameters and welding quality. The smaller the heat affected zone width, the better the corresponding welding quality and performance, and the corresponding welding process parameters are also better. The heat affected zone width is optimized under different welding process parameter settings in combination with the particle swarm algorithm. Thus, a welding process parameter optimization model is constructed, so that the welding process parameter optimization model can be used to find a welding process parameter combination that can minimize the heat affected zone width (that is, the best welding quality) as the welding process parameter in actual welding.

[0029] In some embodiments, the step S11 further includes: the device 1 updates the heat-affected zone width prediction model based on the test sample data. In some embodiments, the test sample data includes welding process parameter test information and heat-affected zone width test information corresponding to the welding process parameter test information. The welding process parameter test information includes multiple value combinations corresponding to the welding process parameters. The heat-affected zone width test information includes the heat-affected zone width corresponding to each value combination in the welding process parameter test information. The test sample data is similar to the training sample data and is obtained from actual welding experiments. For example, for the data obtained from the actual welding experiment, part of it can be used as training sample data and the other part can be used as test sample data. In some embodiments, the device 1 inputs the welding process parameter test information into the heat-affected zone width prediction model to obtain the corresponding heat-affected zone width prediction information, and optimizes the heat-affected zone width prediction model based on the heat-affected zone width prediction information and the heat-affected zone width test information, so that the output result of the heat-affected zone width prediction model is more accurate.

[0030] In some embodiments, the updating of the heat affected zone width prediction model based on the test sample data includes: the device 1 determines the corresponding error information based on the test sample data and the heat affected zone width prediction model; and updates the heat affected zone width prediction model based on the error information. In some embodiments, the device 1 inputs the welding process parameter test information into the heat affected zone width prediction model to obtain the corresponding heat affected zone width prediction information, and determines the corresponding error information based on the heat affected zone width prediction information and the heat affected zone width test information. The error information includes the mean square error between the heat affected zone width prediction information and the heat affected zone width test information. The device 1 evaluates the prediction effect of the heat affected zone width prediction model based on the error information, thereby updating the heat affected zone width prediction model until the number of iterations is met, or the number of times the determined error information is less than the threshold satisfies the corresponding number threshold.

[0031] In some embodiments, the method further includes: step S13 (not shown), the device 1 determines the target welding process parameter information based on the welding process parameters and the parameter ranges corresponding to the welding process parameters using the welding process parameter optimization model. In some embodiments, referring to Table 1 below, the welding process parameters include but are not limited to welding current, welding voltage, gas flow, welding speed and / or wire feeding speed. Those skilled in the art should understand that the values ​​corresponding to the parameter ranges shown in the table below are only examples, and other existing or future parameter ranges that may appear should also be included in the scope of protection of the present application if they are applicable to the present application, and are included here by reference. In some embodiments, the device 1 determines the optimal value combination of the welding process parameters from the parameter range based on the parameter ranges corresponding to each welding process parameter using the welding process parameter optimization model, and outputs the value as the corresponding target welding process parameter information.

[0032] Table 1 Example of welding process parameters and corresponding parameter ranges

[0033] Serial number Welding process parameters Parameter range 1 Welding current 240-260(A) 2 Welding voltage 20-27(V) 3 Gas flow 17-18(L / min) 4 Welding speed 4-4.9(mm / s) 5 Wire feeding speed 4-5.2(m / min)

[0034] In some embodiments, the method further comprises: step S14 (not shown), the device 1 determines a parameter range corresponding to the welding process parameter. In some embodiments, the parameter range can be pre-set based on historical welding experience, or can be determined through a small range of experiments.

[0035] In some embodiments, the step S14 includes: the device 1 determines the parameter range information corresponding to the welding process parameter by using an orthogonal test method based on the original parameter range information corresponding to the welding process parameter.

[0036] In some embodiments, the original parameter range information includes a value range corresponding to the welding process parameter preset based on welding experience. This value range is usually large. If it is directly used in subsequent steps to determine the target welding process parameter information, it will often reduce the calculation efficiency and affect the accuracy of the results. Therefore, the orthogonal test method can be used to determine the degree of influence of the welding process parameter on the welding quality within the minimum number of tests, so as to optimize the value range corresponding to the welding process parameter and determine the optimal parameter range information.

[0037] In some embodiments, the device 1 can determine the second welding process parameter information for the orthogonal test based on the level number corresponding to the welding process parameter and the corresponding parameter range. The level number can be determined based on the sensitivity of the change in the width of the heat-affected zone to the change in the value of the welding process parameter. The stronger the sensitivity, the smaller the step size of the corresponding welding process parameter value change, and the higher the level number. For example, referring to the example of some second welding process parameter information shown in Table 2 below, the level number corresponding to the welding current and welding voltage is set to 9, the level number corresponding to the gas flow rate is 4, and the level number corresponding to the welding speed and wire feeding speed is 8, and the second welding process parameter information for the test is determined based on the level number.

[0038] In some embodiments, the device 1 can obtain the second heat-affected zone width information determined by the corresponding welding test based on the second welding process parameter information. The device 1 can optimize the original parameter range information based on the second welding process parameter information and the corresponding second heat-affected zone width information to determine the optimal parameter range information. For example, based on the second heat-affected zone width information, the second target welding process parameter information is determined from the second welding process parameter information, wherein the heat-affected zone width corresponding to the second target welding process parameter information is the smallest width in the second heat-affected zone width information. The device 1 can optimize the parameter range based on the second target welding process parameter information to determine the parameter range corresponding to the welding process parameter. The device 1 can determine the relationship between each parameter in the welding process parameter and the heat-affected zone width according to the second welding process parameter information and the corresponding second heat-affected zone width information. According to the relationship between each parameter in the welding process parameter and the heat-affected zone width, on the basis of the second target welding process parameter information, each parameter is expanded in the optimization direction to determine the optimal parameter range information. For another example, the device 1 can sort the value combinations of various welding process parameters in the second welding process parameter information according to the corresponding heat-affected zone width from small to large according to the second heat-affected zone width information. Based on the value combinations of several welding process parameters ranked first, the corresponding parameter range information is determined. Here, determining the corresponding parameter range through orthogonal experiments can effectively narrow the parameter range used to determine the target welding process parameter information with the least number of experiments, avoid carpet search, and improve calculation efficiency.

[0039] In some embodiments, in order to ensure the effectiveness of the heat affected zone width prediction model obtained by training based on the training sample data, it is necessary to ensure the coverage (representativeness) of the training sample data. The device 1 can obtain the required training sample data with sufficient coverage (representativeness) with the least number of experiments through the aforementioned orthogonal experiment. In some embodiments, the device 1 can first perform the orthogonal experiment described in step S14, and use the second welding process parameter information and the corresponding second heat affected zone width information obtained by the orthogonal experiment in step S14 as training sample data for building the model. Here, the data of the orthogonal experiment described in step S14 can be used as samples for model training, and can also be used to optimize parameter range information, improve data utilization, and avoid waste of resources from repeated welding experiments.

[0040] Table 2 Example of the second welding process parameter information

[0041]

[0042] In some embodiments, the step S13 includes: step S131 (not shown), the device 1 initializes a particle group based on the welding process parameters and the parameter range corresponding to the welding process parameters, wherein the particle group includes multiple particles, and each of the multiple particles corresponds to a candidate welding process parameter information; step S132 (not shown), the device 1 determines the fitness information corresponding to each particle in the particle group based on the heat affected zone width prediction model; step S133 (not shown), the device 1 updates the historical optimal welding process parameter information corresponding to each particle and the historical optimal welding process parameter information corresponding to the particle group based on the fitness information corresponding to each particle; step S134 (not shown), if the preset conditions are not met, the device 1 updates the particle group and repeats steps S132-S134; otherwise, based on the historical optimal welding process parameter information corresponding to the particle group, the corresponding target welding process parameter information is determined.

[0043] In some embodiments, each particle corresponds to a candidate welding process parameter information, and a candidate welding process parameter information corresponds to a value combination of welding process parameters. The candidate welding process parameter information includes but is not limited to candidate welding current information, candidate welding voltage information, candidate gas flow information, candidate welding speed information and / or candidate wire feeding speed information. The initialization of the particle population includes initializing the candidate welding process parameter information corresponding to each particle, for example, determining the parameter value randomly selected from the parameter range corresponding to the welding process parameter as the initial candidate welding process parameter information. In some embodiments, the initialization of the particle population also includes initializing the update speed corresponding to each particle. The update speed determines the iteration distance and direction of the corresponding candidate welding process parameter information when the particle population is updated. When initializing the update speed corresponding to each particle, random initialization can be performed to randomly determine the initial update speed corresponding to each particle within a preset speed range; normal distribution initialization can also be performed to generate the initial update speed corresponding to each particle using normal distribution; and the initial update speed corresponding to each particle can also be set based on existing setting experience.

[0044] In some embodiments, the device 1 determines the heat-affected zone width prediction information corresponding to the candidate welding process parameter information based on the candidate welding process parameter information corresponding to each particle, and uses the heat-affected zone width prediction model, and uses the heat-affected zone width prediction information as the fitness information corresponding to the particle. For each particle in the particle group, the fitness information corresponding to the particle is compared with the fitness information of the historical optimal welding process parameter information corresponding to the particle. If the fitness information corresponding to the particle is less than the fitness information of the historical optimal welding process parameter information corresponding to the particle, the candidate welding process parameter information currently corresponding to the particle is used as the historical optimal welding process parameter information corresponding to the particle; otherwise, the historical optimal welding process parameter information corresponding to the particle is not updated. Compare the fitness information corresponding to the particle with the fitness information of the historical optimal welding process parameter information corresponding to the particle group. If the fitness information corresponding to the particle is less than the fitness information of the historical optimal welding process parameter information corresponding to the particle group, the candidate welding process parameter information currently corresponding to the particle is used as the historical optimal welding process parameter information corresponding to the particle group; otherwise, the historical optimal welding process parameter information corresponding to the particle group is not updated. The historical optimal welding process parameter information corresponding to the particle group is determined by comparing all particles in the particle group, and the historical optimal welding process parameter information corresponding to the particle is determined by comparing the data obtained by the particle through previous iterations. In some embodiments, the device 1 updates the historical optimal welding process parameter information of the particle group through iteration of the particle group, and outputs the historical optimal welding process parameter of the particle group as the target welding process parameter information after the iteration is terminated when the preset conditions are met. The target welding process parameter information is the value combination that can achieve the best welding quality determined from the parameter range information.

[0045] In some embodiments, the updating of the particle group includes: device 1 updates the particle group based on the historical optimal welding process parameter information corresponding to each particle and the historical optimal welding process parameter information corresponding to the particle group. In some embodiments, the device 1 can update the update speed corresponding to each particle based on the historical optimal welding process parameter information corresponding to each particle and the historical optimal welding process parameter information corresponding to the particle group. Based on the update speed corresponding to each particle, the candidate welding process parameter information corresponding to each particle is updated, thereby completing the update of the particle group. For example, for particle i, its update speed v at the k+1 iteration is i (k+1)=ω(k)v i (k)+φ1c1(p i (k)-x i (k))+φ2c2(g i (k)-x i(k)), where ω(k) is the inertia weight factor, and its value is usually set to decrease with the increase of the number of iterations. The update of ω(k) can be set to linear decrease, nonlinear decrease or dynamic weight, etc.; c1 = rand(0, a1), c2 = rand(0, a2), where a1 and a2 are preset constants; φ1 and φ2 are preset constants; p i (k) is the historical optimal welding process parameter information corresponding to particle i in the kth iteration; g i (k) is the historical optimal welding process parameter information corresponding to the particle group in the kth iteration; x i (k) is the candidate welding process parameter information corresponding to particle i in the kth iteration. Based on the update speed v of particle i in the k+1th iteration i (k+1), the candidate welding process parameter information x corresponding to particle i at the k+1 iteration can be determined i (k+1)=x i (k)+v i (k+1). In some embodiments, for each updated candidate welding process parameter information corresponding to each particle, the device 1 will also determine whether it satisfies the corresponding constraint condition. If so, the particle is retained; otherwise, the particle is eliminated. For example, it is determined whether the candidate welding process parameter information is still within the corresponding parameter range. If so, the candidate welding process parameter information is retained; otherwise, the candidate welding process parameter information is deleted. The device 1 calculates and updates the historical optimal welding process parameter information corresponding to the corresponding particle or the historical optimal welding process parameter information corresponding to the particle group based on the retained candidate welding process parameter information.

[0046] In some embodiments, the preset condition includes at least one of the following: satisfying the corresponding iteration number threshold; the historical optimal welding process parameter information corresponding to the particle group satisfies the corresponding termination condition. In some embodiments, the device 1 determines the fitness difference between the historical optimal welding process parameter information corresponding to the particle group in the current iteration and the historical optimal welding process parameter information corresponding to the particle group in the previous iteration, and if the fitness difference is less than the threshold, it is recorded. The termination condition includes the number of records satisfying the threshold. Therefore, when facing the situation that the iteration number threshold has not been met, but the optimal target welding process parameter information has been found, the iteration can be terminated in advance, the result output efficiency is improved, and the waste of computing resources is avoided.

[0047] Figure 2A device structure diagram for constructing a welding process parameter optimization model according to an embodiment of the present application is shown, wherein the device 1 includes a first module 11 and a second module 12. The first module 11 constructs a heat-affected zone width prediction model based on training sample data and using a neural network model, wherein the training sample data includes first welding process parameter information and first heat-affected zone width information corresponding to the first welding process parameter information; the first module 12 constructs a welding process parameter optimization model based on the heat-affected zone width prediction model and in combination with a particle swarm algorithm. Here, Figure 2 The specific implementations corresponding to the illustrated one-one module 11 and one-two module 12 are respectively the same as or similar to the specific embodiments of the aforementioned step S11 and step S12, and therefore will not be described in detail and are included herein by reference.

[0048] In some embodiments, the device 1 further includes a three-module 13 (not shown). The three-module 13 determines target welding process parameter information based on the welding process parameters and the parameter range corresponding to the welding process parameters using the welding process parameter optimization model. Here, the specific implementation of the three-module 13 is the same or similar to the specific implementation of the aforementioned step S13, so it will not be repeated and is included here by reference.

[0049] In some embodiments, the one-three module 13 includes a one-three-one unit 131 (not shown), a one-three-two unit 132 (not shown), a one-three-three unit 133 (not shown) and a one-three-four unit 134 (not shown). The one-three-one unit 131 initializes a particle group based on the welding process parameter and the parameter range corresponding to the welding process parameter, wherein the particle group includes a plurality of particles, each of the plurality of particles corresponds to a candidate welding process parameter information; the one-three-two unit 132 determines the fitness information corresponding to each particle in the particle group based on the heat affected zone width prediction model; the one-three-three unit 133 updates the historical optimal welding process parameter information corresponding to each particle and the historical optimal welding process parameter information corresponding to the particle group based on the fitness information corresponding to each particle; if the one-three-four unit 134 does not meet the preset conditions, the particle group is updated and the schemes executed by the one-three-two unit 132, the one-three-three unit 133 and the one-three-four unit 134 are repeated; otherwise, the corresponding target welding process parameter information is determined based on the historical optimal welding process parameter information corresponding to the particle group. Here, the specific implementations of the 131 unit 131, the 132 unit 132, the 133 unit 133 and the 134 unit 134 are respectively the same as or similar to the specific implementations of the aforementioned step S131, step S132, step S133 and step S134, so they are not repeated here and are included herein by reference.

[0050] In some embodiments, the device 1 further includes a four-module 14 (not shown). The four-module 14 determines the parameter range corresponding to the welding process parameter. Here, the specific implementation of the four-module 14 is the same or similar to the specific implementation of the aforementioned step S14, so it is not repeated here and is included here by reference.

[0051] Figure 3 An exemplary system that can be used to implement the various embodiments described in this application is shown; Figure 3 In some embodiments shown, the system 300 can be used as any of the devices in the various described embodiments. In some embodiments, the system 300 may include one or more computer-readable media (e.g., system memory or NVM / storage device 320) with instructions and one or more processors (e.g., (one or more) processors 305) coupled to the one or more computer-readable media and configured to execute instructions to implement modules to perform the actions described in this application.

[0052] For one embodiment, system control module 310 may include any suitable interface controller to provide any suitable interface to at least one of processor(s) 305 and / or any suitable device or component in communication with system control module 310 .

[0053] The system control module 310 may include a memory controller module 330 to provide an interface to the system memory 315. The memory controller module 330 may be a hardware module, a software module, and / or a firmware module.

[0054] The system memory 315 may be used, for example, to load and store data and / or instructions for the system 300. For one embodiment, the system memory 315 may include any suitable volatile memory, such as a suitable DRAM. In some embodiments, the system memory 315 may include double data rate type four synchronous dynamic random access memory (DDR4 SDRAM).

[0055] For one embodiment, system control module 310 may include one or more input / output (I / O) controllers to provide interfaces to NVM / storage device 320 and communication interface(s) 325 .

[0056] For example, NVM / storage device 320 may be used to store data and / or instructions. NVM / storage device 320 may include any suitable non-volatile memory (e.g., flash memory) and / or may include any suitable non-volatile storage device(s) (e.g., one or more hard disk drives (HDDs), one or more compact disk (CD) drives, and / or one or more digital versatile disk (DVD) drives).

[0057] NVM / storage device 320 may include storage resources that are physically part of the device on which system 300 is installed, or it may be accessible to the device without being part of the device. For example, NVM / storage device 320 may be accessed over a network via communication interface(s) 325.

[0058] Communication interface(s) 325 may provide an interface for system 300 to communicate over one or more networks and / or with any other suitable devices. System 300 may wirelessly communicate with one or more components of a wireless network in accordance with any of one or more wireless network standards and / or protocols.

[0059] For one embodiment, at least one of the processor(s) 305 may be packaged together with the logic of one or more controllers of the system control module 310 (e.g., the memory controller module 330). For one embodiment, at least one of the processor(s) 305 may be packaged together with the logic of one or more controllers of the system control module 310 to form a system-in-package (SiP). For one embodiment, at least one of the processor(s) 305 may be integrated on the same die with the logic of one or more controllers of the system control module 310. For one embodiment, at least one of the processor(s) 305 may be integrated on the same die with the logic of one or more controllers of the system control module 310 to form a system on chip (SoC).

[0060] In various embodiments, the system 300 may be, but is not limited to: a server, a workstation, a desktop computing device, or a mobile computing device (e.g., a laptop computing device, a handheld computing device, a tablet computer, a netbook, etc.). In various embodiments, the system 300 may have more or fewer components and / or a different architecture. For example, in some embodiments, the system 300 includes one or more cameras, a keyboard, a liquid crystal display (LCD) screen (including a touch screen display), a non-volatile memory port, multiple antennas, a graphics chip, an application specific integrated circuit (ASIC), and a speaker.

[0061] In addition to the methods and devices described in the above embodiments, the present application also provides a computer-readable storage medium, which stores computer code. When the computer code is executed, the method described in any of the preceding items is executed.

[0062] The present application also provides a computer program product. When the computer program product is executed by a computer device, the method described in any of the preceding items is executed.

[0063] The present application also provides a computer device, the computer device comprising:

[0064] one or more processors;

[0065] a memory for storing one or more computer programs;

[0066] When the one or more computer programs are executed by the one or more processors, the one or more processors are caused to implement the method as described in any of the preceding items.

[0067] It should be noted that the present application can be implemented in software and / or a combination of software and hardware, for example, can be implemented using an application specific integrated circuit (ASIC), a general purpose computer or any other similar hardware device. In one embodiment, the software program of the present application can be executed by a processor to implement the steps or functions described above. Similarly, the software program of the present application (including relevant data structures) can be stored in a computer-readable recording medium, for example, a RAM memory, a magnetic or optical drive or a floppy disk and similar devices. In addition, some steps or functions of the present application can be implemented using hardware, for example, as a circuit that cooperates with a processor to perform each step or function.

[0068] In addition, a part of the present application may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present application through the operation of the computer. Those skilled in the art should understand that the existence of computer program instructions in computer-readable media includes but is not limited to source files, executable files, installation package files, etc., and accordingly, the way in which computer program instructions are executed by a computer includes but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to the computer.

[0069] Communication media include media by which communication signals containing, for example, computer readable instructions, data structures, program modules, or other data are transmitted from one system to another. Communication media may include guided transmission media such as cables and wires (e.g., fiber optic, coaxial, etc.) and wireless (unguided transmission) media that can propagate energy waves, such as acoustic, electromagnetic, RF, microwave, and infrared. Computer readable instructions, data structures, program modules, or other data may be embodied as a modulated data signal in, for example, a wireless medium such as a carrier wave or similar mechanism such as embodied as part of spread spectrum technology. The term "modulated data signal" refers to a signal whose one or more characteristics are changed or set in such a manner as to encode information in the signal. Modulation may be analog, digital, or a hybrid modulation technique.

[0070] By way of example and not limitation, computer-readable storage media may include volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules or other data. For example, computer-readable storage media include, but are not limited to, volatile memory, such as random access memory (RAM, DRAM, SRAM); and non-volatile memory, such as flash memory, various read-only memories (ROM, PROM, EPROM, EEPROM), magnetic and ferromagnetic / ferroelectric memories (MRAM, FeRAM); and magnetic and optical storage devices (hard disks, magnetic tapes, CDs, DVDs); or other media now known or later developed that can store computer-readable information / data for use by a computer system.

[0071] Here, according to an embodiment of the present application, a device is included, which includes a memory for storing computer program instructions and a processor for executing the program instructions, wherein, when the computer program instructions are executed by the processor, the device is triggered to run the methods and / or technical solutions based on the aforementioned multiple embodiments of the present application.

[0072] It is obvious to those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and that the present application can be implemented in other specific forms without departing from the spirit or basic features of the present application. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-restrictive, and the scope of the present application is limited by the attached claims rather than the above description, so it is intended to include all changes that fall within the meaning and scope of the equivalent elements of the claims in the present application. Any figure mark in the claims should not be regarded as limiting the claims involved. In addition, it is obvious that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the device claim can also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

Claims

1. A method for constructing a welding process parameter optimization model, in, The method comprises: Based on the training sample data, a heat-affected zone width prediction model is constructed using a neural network model, wherein the training sample data includes first welding process parameter information and first heat-affected zone width information corresponding to the first welding process parameter information; Based on the heat affected zone width prediction model and combined with the particle swarm algorithm, a welding process parameter optimization model is constructed; Determine a parameter range corresponding to a welding process parameter, wherein the determining the parameter range corresponding to the welding process parameter comprises: based on the original parameter range information corresponding to the welding process parameter, determine the parameter range information corresponding to the welding process parameter by using an orthogonal test method; based on the level number corresponding to the welding process parameter and the corresponding parameter range information, determine second welding process parameter information for the orthogonal test, wherein the level number is determined based on the sensitivity of the change in the width of the heat-affected zone relative to the change in the value of the welding process parameter; obtain second heat-affected zone width information determined by performing a corresponding welding test based on the second welding process parameter information; based on the second welding process parameter information and the corresponding second heat-affected zone width information, optimize the original parameter range information to determine the optimal parameter range information; based on the the second heat affected zone width information, determining second target welding process parameter information from the second welding process parameter information, wherein the heat affected zone width corresponding to the second target welding process parameter information is the smallest width in the second heat affected zone width information, performing parameter range optimization based on the second target welding process parameter information, determining parameter range information corresponding to the welding process parameter, determining a relationship between each parameter in the welding process parameter and the heat affected zone width according to the second welding process parameter information and the corresponding second heat affected zone width information, and according to the relationship between each parameter in the welding process parameter and the heat affected zone width, on the basis of the second target welding process parameter information, expanding each parameter in an optimization direction, determining an optimal parameter range information, and narrowing the parameter range used to determine the target welding process parameter information; Based on the welding process parameters and the parameter ranges corresponding to the welding process parameters, the target welding process parameter information is determined using the welding process parameter optimization model.

2. The method according to claim 1, in, Based on the training sample data, a neural network model is used to construct a heat-affected zone width prediction model, wherein the training sample data includes first welding process parameter information and first heat-affected zone width information corresponding to the first welding process parameter information further includes: Based on the test sample data, the heat affected zone width prediction model is updated.

3. The method according to claim 2, in, The updating of the heat affected zone width prediction model based on the test sample data includes: Determining corresponding error information based on the test sample data and the heat affected zone width prediction model; Based on the error information, the heat affected zone width prediction model is updated.

4. The method according to claim 1, in, The determining of target welding process parameter information based on the welding process parameter and the parameter range corresponding to the welding process parameter by using the welding process parameter optimization model comprises: Initializing a particle population based on the welding process parameter and a parameter range corresponding to the welding process parameter, wherein the particle population includes a plurality of particles, and each particle in the plurality of particles corresponds to a type of candidate welding process parameter information; i. determining fitness information corresponding to each particle in the particle population based on the heat affected zone width prediction model; j. Based on the fitness information corresponding to each particle, updating the historical optimal welding process parameter information corresponding to each particle and the historical optimal welding process parameter information corresponding to the particle group; k If the preset condition is not met, update the particle group and repeat step ik; otherwise, determine the corresponding target welding process parameter information based on the historical optimal welding process parameter information corresponding to the particle group.

5. The method according to claim 4, in, The updating of the particle population comprises: Based on the historical optimal welding process parameter information corresponding to each particle and the historical optimal welding process parameter information corresponding to the particle group, the particle group is updated.

6. A computer device for constructing a welding process parameter optimization model, comprising a memory, a processor and a computer program stored in the memory, It is characterized in that The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 5.

7. A computer-readable storage medium having a computer program / instructions stored thereon, It is characterized in that When the computer program / instructions are executed by a processor, the steps of the method as claimed in any one of claims 1 to 5 are implemented.

Images