A process optimization method for laser-arc hybrid welding weld shaping

Abstract

The application discloses a process optimization method for laser-arc hybrid welding weld forming, comprising the following steps: S1, obtaining a plurality of parameters of a hybrid welding experiment, wherein a penetration and a width are taken as experimental output parameters, and other parameters are taken as experimental input parameters; S2, analyzing the parameters through a Spearman correlation coefficient, and then obtaining key parameters influencing weld forming; S3, obtaining a range level of a single parameter variable value in the key parameters through a single variable method; S4, establishing a response surface mathematical model, and screening more parameter matrix schemes meeting weld forming conditions through the response surface mathematical model; and S5, taking the two input parameter variables, the penetration and the width, as optimization targets, and using a second-generation non-dominated sorting genetic algorithm to perform multi-objective optimization on the parameter matrix obtained in step 4, so as to obtain an optimized final solution of the optimization target. According to the application, compared with the existing method for improving weld forming based on process parameters, the problems of low efficiency and high experimental cost are solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of welding, in particular to a process optimization method for laser-arc hybrid welding weld forming. BACKGROUND

[0002] Laser-arc hybrid welding is a technology that combines two different physical properties of heat sources, laser heat source and arc heat source. This welding technology involves guiding and stabilizing the arc with laser, while the arc improves the absorption of laser by metal and enhances the droplet transfer and bridging ability, thereby achieving greater welding penetration, efficient and high-quality welding process. It has achieved significant welding efficiency in key components of shipbuilding, bridge, aviation and other industries, especially thick plate processing.

[0003] The energy coupling mechanism of laser and arc in hybrid welding process is complex, and involves multiple process parameters, including welding process parameters and welding condition parameters. Welding process parameters include laser power, welding speed, current and voltage, etc., and welding condition parameters include laser type and laser wavelength, welding angle, environmental factors, etc. Penetration and width are the key factors to judge the quality of weld forming, and different process parameters will directly affect the weld forming, for example, too low laser power cannot provide enough energy to fully melt the material, resulting in poor weld forming and lack of penetration; too high laser power will cause excessive melting and weld depression; too fast welding speed will cause the molten pool to cool faster, resulting in shallow penetration and insufficient weld width; too slow welding speed will increase the heat affected zone, causing weld overheating and grain growth, affecting the mechanical properties of the welded joint. Welding process is the core step of processing key components, and the quality of weld forming is the most intuitive indicator to evaluate the quality of welding, so the current development and research of hybrid welding mainly focuses on producing ideal weld shape without any visible defects.

[0004] The experimental process of hybrid welding process is complex, and there are many process parameters, and each parameter is not independent of each other. Many technical solutions explore different parameter combinations to obtain ideal weld quality through simulation or orthogonal experiment, which usually consumes a lot of time and economic cost. The method of using machine learning to fit the model of parameters is not suitable for hybrid welding, because the experimental data of hybrid welding is small, the experimental time is long, and the experimental cost is high, while the machine learning model usually needs a large amount of data for training. Therefore, how to obtain well-formed weld through process parameter optimization on the basis of improving efficiency and reducing cost is a problem to be solved. SUMMARY

[0005] In view of the deficiencies in the prior art, the purpose of the present application is to provide a process optimization method for laser-arc hybrid welding weld forming, in order to solve the problem of complex process parameters in laser-arc hybrid welding, high cost of welding experiment, and then leading to the overall low efficiency of exploring the influence of parameters on weld forming. In order to achieve the above-mentioned purposes and other advantages according to the present application, a process optimization method for laser-arc hybrid welding weld forming is provided, comprising:

[0006] S1, obtain a plurality of parameters of the composite welding experiment, the penetration and the width of the molten pool as the experimental output parameters, and the other parameters as the experimental input parameters;

[0007] S2, analyze the parameters by Spearman correlation coefficient, and then obtain the key parameters affecting the weld forming, the key parameters including laser power, defocusing amount, light wire spacing, current, welding speed;

[0008] S3, obtain the range level of the single parameter variable value in the key parameters by the single variable method;

[0009] S4, establish a response surface mathematical model, and screen out more parameter matrix schemes meeting the weld forming conditions by the response surface mathematical model;

[0010] S5, taking the two input parameter variables penetration and width of the molten pool as the optimization target, using the second generation non-dominated sorting genetic algorithm to multi-objective optimize the parameter matrix obtained in step 4, and obtaining the optimized final solution of the optimization target.

[0011] Preferably, the parameters in step S1 include laser power, welding speed, wire feeding speed, light wire spacing, defocusing amount, protective gas flow, arc voltage, arc current, groove spacing, laser wavelength, guiding mode, penetration and width of the molten pool.

[0012] Preferably, in step S2, the correlation coefficient of the input parameter and the output parameter is denoted as r, when the absolute value of the r is greater than or equal to 0.8, the input parameter and the output parameter are strongly correlated.

[0013] Preferably, when the absolute value of r is less than 0.8, the input parameter and the output parameter are weakly correlated, and the influence of the input parameter on the output parameter is ignored.

[0014] Compared with the prior art, the present application has the beneficial effects that: the correlation strengths of various parameters are analyzed by Spearman correlation analysis, and laser power, defocusing amount, optical fiber spacing, current and welding speed are selected as key parameters affecting weld forming by comparing various correlation coefficients. Through single factor experiment, no weld defects are taken as experimental targets, and the level value ranges of the five parameters are obtained respectively. Then, the functional relationship between the five key input parameters and the output parameters of penetration and width is obtained by response surface method, so as to construct a response surface and obtain a parameter matrix in the level range of the weld forming quality. Finally, the optimal solution of weld forming is obtained by multi-objective genetic algorithm, so that the optimized process parameters can meet the certain weld quality in welding processing. The present application has important significance for significantly improving the efficiency and reducing the economic cost in the processing of important parts in the fields of aerospace, ship and track. BRIEF DESCRIPTION OF DRAWINGS

[0015] Figure 1 A process optimization method flow chart for laser-arc hybrid welding weld forming according to the process optimization method for laser-arc hybrid welding weld forming of the present application;

[0016] Figure 2 A single factor experiment parameter level range flow chart for the process optimization method for laser-arc hybrid welding weld forming according to the process optimization method for laser-arc hybrid welding weld forming of the present application;

[0017] Figure 3 A response surface model residual normal probability distribution chart for the process optimization method for laser-arc hybrid welding weld forming according to the process optimization method for laser-arc hybrid welding weld forming of the present application;

[0018] Figure 4 A response surface chart of laser power parameter and optical fiber spacing parameter affecting penetration for the process optimization method for laser-arc hybrid welding weld forming according to the process optimization method for laser-arc hybrid welding weld forming of the present application;

[0019] Figure 5 A response surface chart of laser power parameter and defocusing amount parameter affecting penetration for the process optimization method for laser-arc hybrid welding weld forming according to the process optimization method for laser-arc hybrid welding weld forming of the present application;

[0020] Figure 6 A response surface chart of laser power parameter and current parameter affecting penetration for the process optimization method for laser-arc hybrid welding weld forming according to the process optimization method for laser-arc hybrid welding weld forming of the present application;

[0021] Figure 7 A response surface chart of laser parameter and welding speed affecting penetration for the process optimization method for laser-arc hybrid welding weld forming according to the process optimization method for laser-arc hybrid welding weld forming of the present application;

[0022] Figure 8Flow chart of the fast non-dominated genetic algorithm for the process optimization method for laser-arc hybrid welding weld formation according to the present application. DETAILED DESCRIPTION

[0023] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative labor fall within the protection scope of the present application.

[0024] Embodiment 1

[0025] The present application discloses an optimization method for laser-arc hybrid welding weld formation, and the optimization method is further illustrated by taking the optimization of process parameters of EH36 marine high-strength steel as an example. The optimization method flow is shown in Figure 1 and the specific steps include:

[0026] Step 1: Obtain all parameters of laser-arc hybrid welding experiments, in which the penetration and the width are taken as output parameters, and other parameters are taken as input parameters.

[0027] Step 2: Calculate the correlation of each parameter by using Spearman correlation coefficient, and analyze and evaluate the key parameters that have the greatest influence on the penetration and the width according to the correlation coefficient. The Spearman correlation coefficient evaluates the monotonic relationship between two variables without considering the linear relationship between the variables, and the correlation coefficient is denoted as r. If |r|≥0.8, the input parameter is strongly correlated with the output parameter; if |r|<0.8, the input parameter is weakly correlated with the output parameter, and the influence of the input parameter on the output parameter is ignored. Based on the existing composite welding experimental data, the Spearman analysis is performed, and the laser power, the defocusing amount, the light wire spacing, the current and the welding speed are taken as the key parameters that influence the penetration and the width. Table 1 shows the Spearman correlation coefficient analysis results of the commonly used parameters in the composite welding process.

[0028] Table 1. Spearman correlation coefficient of commonly used process parameters in composite welding

[0029]

[0030] Step 3: The influence of the five key parameters on the weld formation is studied by using the single variable method through the single factor experiment, and the specific flow is shown in Figure 2The purpose of this step is to obtain the upper and lower boundaries of the 5 key parameters for the formation of a defect-free weld. The experimental determination of the parameter level range that conforms to the formation of a defect-free weld is: laser power 14-15 kW, light wire spacing 4-5 mm, welding speed 2.0-2.2 m / min, current 400-420 A, and defocusing amount -4-0 mm.

[0031] Step 4: A response surface model of the 5 input parameters and 2 output parameters is established using the response surface method. The purpose of this step is to explore the influence of each parameter and the interaction between parameters on the weld appearance. Since the parameter range for the formation of a defect-free weld has been obtained in step 3 through single-factor experiments, this step only further refines and narrows the range to obtain an optimized interval, thereby obtaining the optimal weld appearance.

[0032] In the response surface method, the significance of the model and the significance of the lack of fit are determined by the P value. If the model is significant and the lack of fit is not significant, it means that the model can be used for subsequent optimization design. According to the experimental factor and response value statistical results, mathematical models based on the fusion width and the penetration depth are established.

[0033] y1 = -858.2 + 0.19*A - 2.09*B + 6.18*C + 0.67*D - 2.72*E - 2.47*A*B - 1.99*A*C + 1.24*A*D + 5.31*A*E - 4.97*B*C + 5.62*B*D - 0.2*B*E + 0.22*C*D + 0.1*C*E + 9.02*D*E - 1.29*A 2 - 0.63*B 2 - 0.75*C 2 - 1.55*D 2 - 0.99*E 2

[0034] y2 = 76.91 + 0.21*A - 3.21*B + 8.12*C - 0.31*D + 2.31*E - 0.18*A*B - 2.21*A*C + 3.21*A*D - 4.53*A*E + 3.21*B*C + 2.77*B*D + 0.41*B*E - 0.49*C*D + 0.24*C*E + 8.31*D*E - 2.03*A 2 + 0.52*B 2 + 0.67*C 2 - 2.71*D 2 - 0.83*E 2

[0035] Wherein y1 and y2 represent the penetration and the width of the weld, respectively, A, B, C, D, E represent the laser power, the defocusing amount, the distance between the light filaments, the current, and the welding speed, respectively. Figure 3 is the normal probability distribution diagram of the residual, which shows that the model is well adapted. Figure 4 、 Figure 5 、 Figure 6 and Figure 7 are the response surface diagrams of the laser power parameter and the distance between the light filaments, the defocusing amount, the current, and the welding speed on the penetration, respectively. The purpose of studying the response surface is to determine the two response indexes of the penetration and the width of the weld to obtain the parameter matrix of the preliminary optimized process parameters.

[0036] Example Two

[0037] Example Two is different from Example One in that Example One is to determine the factor level range without weld defects from the selection of the factors affecting the weld formation in the composite welding, which is a preparation for Example Two. In this embodiment, the second generation non-dominated genetic algorithm is used to perform the final optimization on the parameter matrix in Step 3 of Example One.

[0038] The second generation non-dominated genetic algorithm is a genetic algorithm used to solve multi-objective optimization problems, which can find a set of Pareto optimal solutions and maintain the diversity and uniformity of the distribution of the solution set when dealing with multi-objective optimization problems. The method of the present application is to optimize the weld formation in composite welding, which is usually related to the width and the penetration of the weld, and the flow of the algorithm is shown in Figure 8 , and the specific steps are as follows:

[0039] Step 1: Map the parameter matrix screened by the response surface method to the data space as the initial population.

[0040] Step 2: Perform non-dominated sorting on each individual in the population, wherein N(i) is used to represent the number of solution individuals dominated by individual i in the population, and S(i) is used to represent the set of solution individuals dominated by individual i. The calculation steps of the domination relationship are as follows:

[0041] Step 2.1: For each individual i in the population, traverse all other individuals j in the population.

[0042] Step 2.2: If individual j is not worse than individual i in all objectives and is better than individual i in at least one objective, individual i is dominated by individual j.

[0043] Step 2.3: Count N(i) and S(i). Select the individuals with N(i) = 0, which are not dominated by any other individual and are therefore non-dominated. Put all the non-dominated individuals into the first layer and set the Pareto level to 1.

[0044] Step 2.4: Re-scan the rest of the population for the first layer individual, check if it dominates each individual j in the rest of the population, if the first layer individual i dominates individual j, increase the domination count N(i) of individual j.

[0045] Step 2.5: After updating the domination count, find the individual with N(i) = 0, form the second layer, and set the Pareto rank to 2. In this way, until all individuals are assigned to the corresponding non-dominated layer and set the corresponding Pareto rank.

[0046] Step 2.6: In order to make the individuals more evenly distributed in each layer, introduce the crowding degree for each individual. The greater the value of the crowding degree, the less crowded the individual is in the solution space around it.

[0047] The calculation expression of the crowding degree is:

[0048]

[0049] Where i d represents the crowding degree of the ith individual, and respectively represent the jth objective function value of the i+1th point and the i-1th point, and respectively represent the maximum value and the minimum value of the jth objective function.

[0050] Step 3: According to the tournament selection method, select individuals from the layer with the same rank and the maximum crowding degree of Pareto rank 1 for crossover, mutation, and then generate the first generation of sub-population Q t .

[0051] Step 4: Merge the parent population P t and the child population Q t to get a population R t with a size of 2N, and then perform non-dominated sorting and crowding calculation on the individuals in the population R t . According to the non-dominated relationship and the crowding degree of the individuals, select appropriate individuals to form a new parent population P t+1 .

[0052] Step 5: Use the new parent population P t+1 to repeat the selection, crossover, and mutation steps until the termination iteration number is met. A set of Pareto optimal solution is obtained.

[0053] Repeat all the above steps, use the optimized process parameters as actual parameters for experimental verification, and excellent weld appearance can be obtained, and the welded joint has no porosity and incomplete fusion defects.

[0054] The number of devices and the scale of processing described herein are intended to be illustrative only.

[0055] While embodiments of the application have been disclosed in connection with the specified embodiments, as illustrated in the drawings, it should be understood that many modifications, enhancements, substitutions, changes, and equivalents will now occur to persons of ordinary skill in the art, and that such modifications, enhancements, substitutions, changes, and equivalents are also intended to be encompassed by the application, which should not be limited to the above described embodiments.

Claims

1. A process optimization method for laser-arc hybrid welding seam shaping, characterized in that, The method comprises the following steps: S1, obtaining a plurality of parameters of a composite welding experiment, wherein a penetration and a width are taken as output parameters, and other parameters are taken as input parameters; The parameters include laser power, welding speed, wire feeding speed, light-wire spacing, defocusing amount, protective gas flow, arc voltage, arc current, groove spacing, laser wavelength, guide mode, penetration, and width; S2, analyzing the parameters by using a Spearman correlation coefficient, and then obtaining key parameters that have the greatest influence on the penetration and the width, wherein the key parameters include laser power, defocusing amount, light-wire spacing, current, and welding speed, wherein the correlation coefficient is denoted as r, if an absolute value of r is greater than or equal to 0.8, the input parameter is strongly correlated with the output parameter, if the absolute value of r is less than 0.8, the input parameter is weakly correlated with the output parameter, and the influence of the input parameter on the output parameter is ignored; S3, obtaining a range of values of a single parameter variable value in the key parameters by using a single variable method, and taking no welding defects as an experimental target; S4, establishing a response surface mathematical model, obtaining a functional relationship between the key parameters and the penetration and the width, and screening a parameter matrix that meets a welding forming condition by using the response surface mathematical model; S5, taking the penetration and the width as optimization targets, performing multi-objective optimization on the parameter matrix obtained in step S4 by using a second-generation non-dominated sorting genetic algorithm, and obtaining an optimized final solution of the optimization targets; and wherein the second-generation non-dominated sorting genetic algorithm comprises the following steps: (1) mapping the parameter matrix screened based on the response surface method to a data space and initializing the parameter matrix as a primary population; (2) performing non-dominated sorting on each individual in the primary population and performing crowding degree calculation, selecting individuals by using a tournament method selection method after sorting, and performing crossover and mutation to obtain a first-generation sub-population; (3) performing non-dominated sorting on individuals in a population obtained by combining the first-generation sub-population and a parent population and performing crowding degree calculation, and selecting new individuals to form a new parent; (4) repeating steps (2) and (3) until a termination iteration number is met, and obtaining a set of Pareto optimal solutions.

2. A process optimization method for laser-arc hybrid welding seam formation according to claim 1, characterized in that, The calculation method of the crowding degree in step (2) is as follows: ， wherein, denotes the crowding distance of the i-th individual, and denotes the j-th objective function value of the i+1-th point and the i-1-th point, respectively, and denotes the maximum and minimum value of the j-th objective function, respectively.

Images