Laser arc hybrid welding interface temperature regulation and control method and system with external magnetic field

Abstract

The invention discloses a laser-arc hybrid welding interface temperature regulation and control method and system with an external magnetic field. The method comprises the steps that current welding parameters of a welding sample are obtained; an interface temperature distribution feature neural network prediction model is adopted to process the welding parameters, and current temperature distribution features of the welding interface are obtained through prediction; based on the current temperature distribution characteristics of the welding interface and the standard temperature distribution characteristics of the welding interface, the deviation value of the current temperature distribution characteristics of the welding interface is determined; based on the deviation value, determining the adjustment amount of the magnetic field intensity of the induction coil through a fuzzy rule; and based on the adjustment amount of the magnetic field intensity of the induction coil, the magnetic field intensity of the induction coil is adjusted so as to adjust the current temperature of the welding interface.

Description

Technical Field

[0001] The present application relates to the field of welding processing technology, and in particular to a method and system for controlling the interface temperature of laser arc hybrid welding with an external magnetic field. Background Art

[0002] With the rapid development of the fourth generation of new reactors, titanium alloys with higher radiation resistance, corrosion resistance and high temperature creep performance will quickly replace low alloy stainless steel as a new structural material for thick-walled reactor pressure vessels, meeting the comprehensive performance requirements of thick-walled reactor pressure vessels for high temperature strength, radiation resistance and fatigue resistance. Titanium alloys and original stainless steel materials form a new structural system, and titanium steel dissimilar metal welding is very necessary.

[0003] The multi-field coupling technology based on the applied magnetic field, laser and arc can significantly enhance the controllability and stability of the welding heat source. Therefore, the laser arc hybrid welding with an applied magnetic field can be applied to the welding of dissimilar metals, such as the welding of titanium and steel dissimilar metals. The quality of titanium and steel dissimilar metal welding joints is mainly limited by the control of the welding interface temperature. Therefore, it is very necessary to invent a laser arc hybrid welding interface temperature control method with an applied magnetic field to complete the real-time control of the welding interface temperature of dissimilar metals. Summary of the invention

[0004] In view of this, an embodiment of the present application provides a method and system for controlling the interface temperature of laser arc hybrid welding with an external magnetic field.

[0005] According to the first aspect of the present application, an embodiment of the present application provides a method for controlling the interface temperature of laser arc hybrid welding with an external magnetic field, comprising: Obtain the current welding parameters of the welding sample; the welding parameters include welding current, welding voltage, laser power, welding sample surface temperature, arc deflection angle and arc width; The interface temperature distribution characteristics neural network prediction model is used to process the welding parameters and predict the current temperature distribution characteristics of the welding interface. Determine the deviation of the current temperature distribution characteristics of the welding interface based on the current temperature distribution characteristics of the welding interface and the standard temperature distribution characteristics of the welding interface; Based on the deviation, the adjustment amount of the magnetic field strength of the induction coil is determined by fuzzy rules; Based on the adjustment amount of the magnetic field strength of the induction coil, the magnetic field strength of the induction coil is adjusted to adjust the current temperature of the welding interface.

[0006] Optionally, the steps of constructing the interface temperature distribution characteristic neural network prediction model include: Obtaining training welding parameters of the pre-experimental welding sample during the welding pre-experiment; wherein the material and thickness of the pre-experimental welding sample are the same as the material and thickness of the welding sample; the welding pre-experiment is a single-factor variable experiment, and during the single-factor variable experiment, the training welding voltage, training welding current, training laser power, training transverse magnetic field intensity, and training longitudinal magnetic field intensity are changed respectively; the training welding parameters include training welding voltage, training welding current, training laser power, training arc width, training arc deflection angle, internal temperature of the pre-experimental welding sample, and surface temperature of the pre-experimental welding sample; Based on the internal temperature of the pre-experimental welding sample, the laser arc hybrid welding model of the welding sample is fitted to obtain the welding simulation model; Perform two-dimensional slicing on the welding simulation model to obtain the corresponding interface distribution cloud map; perform feature extraction on the interface distribution cloud map to obtain the corresponding training interface temperature distribution features; The training welding voltage, training welding current, training laser power, training arc width, training arc deflection angle, and surface temperature of the pre-experimental welding specimens are used as training samples, and the training interface temperature distribution characteristics are used as labels to train the neural network and obtain the interface temperature distribution characteristics neural network prediction model.

[0007] Optionally, the steps of constructing the standard temperature distribution characteristics of the welding interface include: Obtain the compound analysis results of the pre-experimental welding samples after the single factor variable experiment, the compound analysis results include the average intermetallic compound thickness and the brittle intermetallic compound content; The training interface temperature distribution characteristics of the pre-experimental welding specimens whose compound analysis results meet the requirements are selected as the standard temperature distribution characteristics of the welding interface.

[0008] Optionally, the deviation includes an average temperature difference and a difference change rate, an X-direction temperature gradient component difference and a difference change rate, and a Y-direction temperature gradient component difference and a difference change rate; Based on the deviation, the adjustment amount of the magnetic field strength of the induction coil is determined by fuzzy rules, including: Through the interface temperature distribution fuzzy controller, the average temperature difference and the difference change rate, the temperature gradient X-direction component difference and the difference change rate, the temperature gradient Y-direction component difference and the difference change rate are processed based on fuzzy rules to obtain the fuzzy value of the induction coil transverse magnetic field intensity adjustment amount and the fuzzy value of the induction coil longitudinal magnetic field intensity adjustment amount; The fuzzy value of the induction coil transverse magnetic field strength adjustment amount and the fuzzy value of the induction coil transverse magnetic field strength adjustment amount are defuzzified to obtain the induction coil transverse magnetic field strength adjustment amount ΔH1 and the induction coil transverse magnetic field strength adjustment amount ΔH2.

[0009] Optionally, adjusting the magnetic field strength of the induction coil based on the adjustment amount of the magnetic field strength of the induction coil includes: Determining the current adjustment amount of the induction coil based on the adjustment amount of the magnetic field strength of the induction coil; Based on the current adjustment amount of the induction coil, the current amount of the induction coil is adjusted to adjust the magnetic field strength of the induction coil.

[0010] Optionally, obtaining the arc deflection angle and arc width includes: Acquire arc images; Based on the arc image, the arc deflection angle and arc width are determined.

[0011] Optionally, based on the arc image, determining the arc deflection angle and the arc width includes: Identify the arc in the arc image and obtain the target area corresponding to the arc; Extract the edge of the target area to obtain the arc contour; Based on the arc profile, the arc deflection angle and arc width are determined.

[0012] Optionally, obtaining the surface temperature of the welding specimen includes: The temperature of a point on the surface of the welding sample that is perpendicular to the weld direction and 4 mm to 11 mm away from the welding groove is obtained to obtain the surface temperature of the welding sample.

[0013] Optionally, the material of the welding specimen is titanium steel dissimilar material.

[0014] According to the second aspect of the present application, the embodiment of the present application provides a laser arc hybrid welding interface temperature control system with an external magnetic field, comprising: Welding process monitoring subsystem and computer control subsystem; The welding process monitoring subsystem includes a welding parameter monitoring module, an arc monitoring module and a temperature monitoring module; the welding parameter monitoring module is used to collect the current welding current, welding voltage and laser power of the welding sample; the arc monitoring module is used to collect the current arc image of the welding sample; the temperature monitoring module is used to monitor the current surface temperature of the welding sample; The computer control subsystem includes an image feature processing module, an interface temperature distribution feature prediction module and an interface temperature control module; the image feature processing module is used to determine the arc deflection angle and arc width based on the arc image; the interface temperature distribution feature prediction module is used to process the welding parameters using the interface temperature distribution feature neural network prediction model to predict the current temperature distribution characteristics of the welding interface; the welding parameters include welding current, welding voltage, laser power, welding sample surface temperature, arc deflection angle and arc width; the interface temperature control module is used to determine the deviation of the current temperature distribution characteristics of the welding interface based on the current temperature distribution characteristics of the welding interface and the standard temperature distribution characteristics of the welding interface; based on the deviation, the adjustment amount of the magnetic field strength of the induction coil is determined by fuzzy rules; based on the adjustment amount of the magnetic field strength of the induction coil, the magnetic field strength of the induction coil is adjusted to adjust the current temperature of the welding interface.

[0015] The embodiment of the present application provides a method and system for controlling the interface temperature of laser arc hybrid welding with an external magnetic field. Since the magnetic field can act on the charged particles of the arc plasma to dynamically change the shape and position of the arc, the shape change can control the intensity of the heat source effect, and the position change can affect the transmission direction of the heat source effect, thereby obtaining the current welding parameters of the welding sample; the welding parameters include welding current, welding voltage, laser power, welding sample surface temperature, arc deflection angle and arc width; the interface temperature distribution feature neural network prediction model is used to process the welding parameters to predict the current temperature distribution characteristics of the welding interface; based on the current temperature distribution characteristics of the welding interface and the standard temperature distribution characteristics of the welding interface, the deviation of the current temperature distribution characteristics of the welding interface is determined; based on the deviation, the adjustment amount of the magnetic field strength of the induction coil is determined by fuzzy rules; based on the adjustment amount of the magnetic field strength of the induction coil, the magnetic field strength of the induction coil is adjusted to adjust the current temperature of the welding interface; in this way, by controlling the magnetic field strength of the induction coil in real time, the shape and position of the arc can be changed, the input position and intensity of the heat source can be controlled, the temperature of the welding interface can be controlled in real time, and high-quality welding of dissimilar metals can be completed.

[0016] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A schematic diagram of a process for controlling the interface temperature of laser arc hybrid welding with an external magnetic field in an embodiment of the present application; Figure 2 This is a schematic diagram of the arrangement of thermocouples in the preliminary experiment in the embodiment of the present application; Figure 3 This is a schematic diagram of the structure of a laser arc hybrid welding interface temperature control system with an external magnetic field in an embodiment of the present application. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0019] The present application embodiment provides a method for controlling the interface temperature of laser arc hybrid welding with an external magnetic field, such as Figure 1 As shown, including: S101, obtaining current welding parameters of the welding sample; the welding parameters include welding current, welding voltage, laser power, surface temperature of the welding sample, arc deflection angle and arc width.

[0020] In this embodiment, laser arc hybrid welding with an external magnetic field is used to weld the welding sample. When laser arc hybrid welding with an external magnetic field is used to weld the welding sample, the device used may include an arc welder, a laser, a welding robot, an induction coil for generating a magnetic field, and a current controller for controlling the current of the induction coil; an arc monitoring module, such as a camera, may be included to collect arc images in real time during the welding process, so as to obtain the arc deflection angle and arc width; a temperature monitoring module, such as an infrared temperature sensor, may be included to monitor the surface temperature distribution of the welding sample in real time; a welding parameter monitoring module may be included to collect the welding current and welding voltage of the arc welder and the laser power of the laser in real time during the welding process.

[0021] In this embodiment, the welding specimen includes but is not limited to dissimilar metals, and the dissimilar metals include but are not limited to titanium alloy and stainless steel.

[0022] In some embodiments, obtaining the surface temperature of the welding sample includes: obtaining the temperature of a point on the surface of the welding sample that is perpendicular to the direction of the weld and 4 mm to 11 mm away from the welding groove, and obtaining the surface temperature of the welding sample. In a specific implementation, the temperature of a point on the surface of the welding sample that is perpendicular to the direction of the weld and 5 mm and 10 mm away from the welding groove can be obtained as the surface temperature of the welding sample.

[0023] S102, using the interface temperature distribution characteristic neural network prediction model to process the welding parameters and predict the current temperature distribution characteristics of the welding interface.

[0024] In this embodiment, the current temperature distribution characteristics of the welding interface can characterize the temperature characteristics corresponding to multiple different regions of the welding interface. The current temperature distribution characteristics of the welding interface can include the current average temperature of multiple regions of the welding interface, the temperature gradient X-direction component and the temperature gradient Y-direction component.

[0025] In some embodiments, the steps of constructing the interface temperature distribution characteristic neural network prediction model include: The training welding parameters of the pre-experimental welding sample during the welding pre-experiment are obtained; wherein the material and thickness of the pre-experimental welding sample are the same as those of the welding sample; the welding pre-experiment is a single-factor variable experiment, and the training welding voltage, training welding current, training laser power, training transverse magnetic field intensity, and training longitudinal magnetic field intensity are changed respectively during the single-factor variable experiment; the training welding parameters include training welding voltage, training welding current, training laser power, training arc width, training arc deflection angle, internal temperature of the pre-experimental welding sample, and surface temperature of the pre-experimental welding sample; based on the internal temperature of the pre-experimental welding sample, the laser arc composite welding model of the welding sample is fitted to obtain a welding simulation model; the welding simulation model is two-dimensionally sliced ​​to obtain a corresponding interface distribution cloud map; and the interface distribution cloud map is feature extracted to obtain the corresponding training interface temperature distribution characteristics; the training welding voltage, training welding current, training laser power, training arc width, training arc deflection angle, and surface temperature of the pre-experimental welding sample are used as training samples, and the training interface temperature distribution characteristics are used as labels to train the neural network to obtain an interface temperature distribution characteristic neural network prediction model.

[0026] In specific implementation, the method for establishing the interface temperature distribution characteristic neural network prediction model is as follows: S11, preparing pre-experimental welding samples: preparing multiple pre-experimental welding samples with the same material and thickness as the welding samples to be welded, and embedding thermocouples in the pre-experimental welding samples that can collect the interface temperature distribution of the pre-experimental welding samples; The arrangement of the thermocouples in this example is as follows: three thermocouples are embedded in the butt plate at 5 mm from the welding groove and parallel to the groove direction at equal intervals, and at the same time, the corresponding thermocouples are embedded at equal intervals of 10 mm along the welding direction, such as Figure 2 As shown, Figure 2 4 groups of thermocouples 1-4 are respectively embedded in Ti and Fe at equal intervals of 10 mm along the welding direction, and each group of thermocouples includes 3 thermocouples.

[0027] S12, single factor variable welding pre-experiment: a laser arc hybrid welding test with a single factor variable external magnetic field is conducted on the pre-experiment welding samples. The welding voltage, welding current, laser power, transverse magnetic field intensity H1, and longitudinal magnetic field intensity H2 of the arc welder are changed during the welding process for different pre-experiment welding samples. During the welding process, the welding current, welding voltage, laser power, and arc image of the arc welder are collected in real time to obtain the corresponding training welding current, training welding voltage, training laser power, and training arc image. The internal temperature of the pre-experiment welding sample is collected by a thermocouple, and the surface temperature distribution of the pre-experiment welding sample is collected by an infrared temperature sensor. Then, the training arc width and training arc deflection angle are obtained by processing the training arc image.

[0028] During the welding pre-experiment in this example, the real-time collection frequency of the arc welding machine's welding current, welding voltage, laser power, and arc image is 100Hz, the collection frequency of the thermocouple collecting the internal temperature of the pre-experiment welding sample is 10KHz, and the collection frequency of the infrared temperature sensor collecting the surface temperature distribution of the pre-experiment welding sample is 100Hz.

[0029] S13. Extracting the training interface temperature distribution characteristics: firstly, establish a laser arc hybrid welding model of the pre-experimental welding sample, and correct the laser arc hybrid welding model of the pre-experimental welding sample through the temperature change value collected by the thermocouple to fit the welding simulation model, and perform two-dimensional slicing on the fitted welding simulation model to obtain the interface temperature distribution cloud map, and divide the interface temperature distribution cloud map into different areas; then perform feature extraction on the interface temperature distribution cloud map, the specific method is: fit the temperature back-labeling formula through the temperature value in the temperature scale output by the cloud map and the red intensity value R, green intensity value G, and blue intensity value B of the corresponding point pixel, and then calculate the temperature value of each pixel point in the interface temperature distribution cloud map through the temperature back-labeling formula, calculate the regional average temperature e, the temperature gradient X-direction component tx, and the temperature gradient Y-direction component ty in each divided area, and obtain the corresponding training interface temperature distribution characteristics.

[0030] It should be noted here that: in actual welding, the role of the magnetic field is to change the arc shape and position, thereby changing the heat distribution of the welding heat source. Therefore, in the simulation model established in this application, the welding heat source model is selected to replace the thermal effect of the arc and laser on the material during the welding process. Furthermore, the welding heat source model is modified to replace the influence of the change of the heat distribution of the welding heat source under different magnetic fields on the temperature distribution of the welding interface.

[0031] S14. Training of neural network prediction model for interface temperature distribution characteristics: Taking the training welding voltage, training welding current, training laser power, training arc width, training arc deflection angle of the pre-experimental arc welding machine and the surface temperature distribution of the pre-experimental welding sample as input, and the training interface temperature distribution characteristics of the pre-experimental welding sample as output, the neural network prediction model for interface temperature distribution characteristics is obtained through neural network training.

[0032] The method for establishing the neural network prediction model of interface temperature distribution characteristics in this example is as follows: 1) Sample set preparation: The arc image acquisition frequency is 100 Hz, the welding current, welding voltage, and laser power value acquisition frequency is 100 Hz, and the pre-experimental welding sample surface temperature acquisition frequency is 100 Hz. According to the three groups of arc width, arc deflection angle, welding voltage, welding current, laser power within n×0.03s and the surface temperature of the pre-experimental welding sample and the welding interface temperature distribution characteristics of the n×0.03s, a sample is formed. n is a positive integer. All samples are combined into a sample set.

[0033] 2) Sample set division: Normalize the eigenvalue data in the sample set to make the values ​​of different types of features consistent, eliminate the quantitative differences between different eigenvalue data, and divide the sample set into training set and test set according to a certain ratio.

[0034] 3) Topology structure design optimization of neural network prediction model for interface temperature distribution characteristics: Using 10-fold cross validation, the sample set is divided into 10 parts, 9 samples are randomly selected as training sets, and the remaining 1 sample is used as a test set. The selection range of the number of hidden layers and the number of nodes is set, and the number of hidden layers and the number of nodes are selected through a grid search algorithm. The optimal number of hidden layers and the number of nodes are determined according to the prediction accuracy of the test set.

[0035] 4) Hyperparameter optimization of the neural network prediction model of interface temperature distribution characteristics: The training set, test set, optimal number of hidden layers and number of nodes divided in the previous step are used as the prerequisites for this step, and the parameter selection range of weights, thresholds and learning rates is set. The hyperparameters of model training are selected by improving the sparrow algorithm, and the optimal weights, thresholds and learning rates are determined according to the prediction accuracy of the test set. 5) Establishment of the neural network prediction model of interface temperature distribution characteristics: Use the selected number of hidden layers, number of nodes, weights, thresholds and learning rates to train the entire training set to obtain the neural network prediction model of interface temperature distribution characteristics, use the sample test set to test the trained neural network prediction model of interface temperature distribution characteristics, and generate the neural network prediction model of interface temperature distribution characteristics after the test.

[0036] S103, determining a deviation of the current temperature distribution characteristics of the welding interface based on the current temperature distribution characteristics of the welding interface and the standard temperature distribution characteristics of the welding interface.

[0037] In this embodiment, the standard temperature distribution characteristics of the welding interface represent the temperature distribution characteristics of the welding interface under standard temperature conditions.

[0038] In this embodiment, the standard temperature distribution characteristics of the welding interface may include the standard average temperature of multiple regions of the welding interface, the standard temperature gradient X-direction component, and the standard temperature gradient Y-direction component.

[0039] In some embodiments, the current temperature distribution characteristics of the welding interface and the standard temperature distribution characteristics of the welding interface can be compared to obtain a deviation, which may include an average temperature difference and a difference change rate, a temperature gradient X-component difference and a difference change rate, and a temperature gradient Y-component difference and a difference change rate.

[0040] In specific implementation, the area with the largest average temperature difference in the current temperature distribution characteristics of the welding interface and the standard temperature distribution characteristics of the welding interface can be selected as the comparison area; based on the average temperature, the temperature gradient X-direction component and the temperature gradient Y-direction component corresponding to the comparison area, the deviation of the comparison area is calculated, and the deviation includes the average temperature difference and the difference change rate Δec of the comparison area, the temperature gradient X-direction component difference and the difference change rate Δtxc, and the temperature gradient Y-direction component difference and the difference change rate Δtyc. Among them, the difference change rate Δec = (Δe1-Δe2) / Δt, the difference change rate Δtxc = (Δtx1-Δtx2) / Δt, the difference change rate Δtyc = (Δty1-Δty2) / Δt, Δe2, Δtxc2, Δty2 are the last average temperature difference, the last X-direction component difference and the last Y-direction component difference respectively, Δe1, Δtxc1, Δty1 are the current average temperature difference, the current X-direction component difference and the current Y-direction component difference respectively, and Δt is the interval time.

[0041] S104, based on the deviation, determining the adjustment amount of the magnetic field strength of the induction coil by using a fuzzy rule. In this embodiment, the adjustment amount of the magnetic field strength of the induction coil includes a first adjustment amount corresponding to the transverse magnetic field strength of the induction coil and a second adjustment amount corresponding to the longitudinal magnetic field strength of the induction coil.

[0042] In this embodiment, since the magnetic field can act on the charged particles of the arc plasma to dynamically change the shape and position of the arc, the shape change can regulate the intensity of the heat source action, and the position change can affect the transmission direction of the heat source action, so that the magnetic field strength is related to the current temperature distribution characteristics of the welding interface. Therefore, based on the deviation amount of the current temperature distribution characteristics of the welding interface, the adjustment amount of the magnetic field strength of the induction coil can be determined through fuzzy rules.

[0043] S105, adjusting the magnetic field strength of the induction coil based on the adjustment amount of the magnetic field strength of the induction coil to adjust the current temperature of the welding interface.

[0044] In some embodiments, adjusting the magnetic field strength of the induction coil based on the adjustment amount of the magnetic field strength of the induction coil includes: Based on the adjustment amount of the magnetic field strength of the induction coil, the current adjustment amount of the induction coil is determined; based on the current adjustment amount of the induction coil, the current amount of the induction coil is adjusted to adjust the magnetic field strength of the induction coil.

[0045] In this embodiment, the current adjustment amount of the induction coil includes a first current adjustment amount corresponding to the transverse magnetic field of the induction coil and a second current adjustment amount corresponding to the longitudinal magnetic field of the induction coil.

[0046] In this embodiment, the magnetic field strength of the induction coil is related to the current of the induction coil. Therefore, the current adjustment amount of the induction coil is determined based on the adjustment amount of the magnetic field strength of the induction coil, so that the transverse magnetic field strength can be adjusted by the current when the induction coil generates a transverse magnetic field, and the longitudinal magnetic field strength can be adjusted by the current when the induction coil generates a longitudinal magnetic field.

[0047] In this embodiment, the current adjustment amount of the induction coil can be obtained through the magnetic field strength formula.

[0048] In this embodiment, the current adjustment amount of the induction coil may be sent to a current controller of the induction coil current, so that the current controller adjusts the current of the induction coil based on the current adjustment amount.

[0049] In this embodiment, based on the current adjustment amount of the induction coil, the current of the induction coil is adjusted, so that the transverse magnetic field strength and the longitudinal magnetic field strength of the induction coil can be adjusted, so that the shape and position of the arc can be changed, so as to adjust the current temperature of the welding interface to the standard temperature in real time.

[0050] In this embodiment, the entire welding process repeats the above steps S101-S105 until the welding is completed, thereby achieving real-time control of the welding interface temperature.

[0051] The interface temperature control method of laser arc hybrid welding with an external magnetic field provided in the embodiment of the present application is that the magnetic field can act on the charged particles of the arc plasma to dynamically change the shape and position of the arc, the shape change can control the intensity of the heat source effect, and the position change can affect the transmission direction of the heat source effect, thereby obtaining the current welding parameters of the welding sample; the welding parameters include welding current, welding voltage, laser power, welding sample surface temperature, arc deflection angle and arc width; the interface temperature distribution feature neural network prediction model is used to process the welding parameters to predict the current temperature distribution characteristics of the welding interface; based on the current temperature distribution characteristics of the welding interface and the standard temperature distribution characteristics of the welding interface, the deviation of the current temperature distribution characteristics of the welding interface is determined; based on the deviation, the adjustment amount of the magnetic field strength of the induction coil is determined by fuzzy rules; based on the adjustment amount of the magnetic field strength of the induction coil, the magnetic field strength of the induction coil is adjusted to adjust the current temperature of the welding interface; in this way, by real-time control of the magnetic field strength of the induction coil, the shape and position of the arc can be changed, the input position and intensity of the heat source can be controlled, the temperature of the welding interface can be controlled in real time, and high-quality welding of dissimilar metals can be completed.

[0052] In some embodiments, in step S101, obtaining the arc deflection angle and the arc width includes: Acquire an arc image; and determine the arc deflection angle and arc width based on the arc image.

[0053] In this embodiment, the arc deflection angle and arc width can be determined by analyzing the arc image.

[0054] In some embodiments, determining the arc deflection angle and the arc width based on the arc image includes: Identify the arc in the arc image and obtain the target area corresponding to the arc; extract the edge of the target area to obtain the arc contour; based on the arc contour, determine the arc deflection angle and arc width.

[0055] In specific implementation, the arc in the arc image can be identified, and the region of interest in the arc image can be extracted to obtain the target region corresponding to the arc. Then, the target region is binarized, and then the arc contour is extracted from the binarized target region, and then the feature value of the arc contour is extracted to obtain the arc deflection angle and arc width.

[0056] In this embodiment, the arc deflection angle and arc width can be determined quickly and accurately by extracting the arc profile.

[0057] In an optional embodiment, in step S103, the step of constructing the standard temperature distribution characteristics of the welding interface includes: The compound analysis results of the pre-experimental welding samples after the single-factor variable experiment are obtained, and the compound analysis results include the average intermetallic compound thickness and the brittle intermetallic compound content; the training interface temperature distribution characteristics of the pre-experimental welding samples whose compound analysis results meet the requirements are selected as the standard temperature distribution characteristics of the welding interface.

[0058] In this embodiment, the standard temperature distribution characteristics of the welding interface can be determined by the single-factor variable welding pre-experiment of the above embodiment. The specific implementation process can be: sampling and analyzing the pre-experimental welding samples obtained from different pre-experiments, and selecting the interface temperature distribution characteristics corresponding to the pre-experimental welding sample with the thinnest average intermetallic compound layer thickness and the lowest brittle intermetallic compound content as the interface standard temperature distribution characteristics; wherein the average intermetallic compound layer thickness can be measured by an optical microscope, and the brittle intermetallic compound content can be analyzed by X-ray diffractometer technology.

[0059] In some embodiments, the deviation includes an average temperature difference and a difference change rate, an X-component difference of the temperature gradient and a difference change rate, and a Y-component difference of the temperature gradient and a difference change rate.

[0060] Step S104, based on the deviation, determining the adjustment amount of the magnetic field strength of the induction coil by using a fuzzy rule, includes: Through the interface temperature distribution fuzzy controller, the average temperature difference and the difference change rate, the temperature gradient X-direction component difference and the difference change rate, the temperature gradient Y-direction component difference and the difference change rate are processed based on fuzzy rules to obtain the fuzzy value of the induction coil transverse magnetic field intensity adjustment amount and the fuzzy value of the induction coil longitudinal magnetic field intensity adjustment amount; The fuzzy value of the induction coil transverse magnetic field strength adjustment amount and the fuzzy value of the induction coil transverse magnetic field strength adjustment amount are defuzzified to obtain the induction coil transverse magnetic field strength adjustment amount ΔH1 and the induction coil transverse magnetic field strength adjustment amount ΔH2.

[0061] In this embodiment, the fuzzy rule may be: when the difference is less than the first threshold and the rate of change of the difference is less than the second threshold, ΔH1 and ΔH2 take smaller values; when the difference is less than the first threshold and the rate of change of the difference is greater than the third threshold, ΔH1 takes a larger value and ΔH2 takes a smaller value; when the difference is greater than the first threshold and less than the fourth threshold; and the rate of change of the difference is greater than the second threshold and less than the fifth threshold, ΔH1 and ΔH2 take moderate values; when the difference is greater than the fourth threshold and the rate of change of the difference is less than the second threshold, ΔH1 takes a smaller value and ΔH2 takes a larger value; when the difference is greater than the fourth threshold and the rate of change of the difference is greater than the fifth threshold, ΔH1 and ΔH2 take larger values.

[0062] In this embodiment, the deviation amount can be transmitted as an input to the interface temperature distribution fuzzy controller to obtain a fuzzy value through fuzzy rules; then the fuzzy value is defuzzified to obtain the adjustment amounts ΔH1 and ΔH2 of the transverse magnetic field intensity H1 and the longitudinal magnetic field intensity H2.

[0063] The specific method of establishing the interface temperature distribution fuzzy controller in this example is as follows: S31. Establish fuzzy subsets and domains of input and output quantities respectively: calculate the change in the temperature distribution characteristics of the welding interface caused by the change in magnetic field intensity and the change in the standard temperature distribution characteristics of the welding interface through preliminary tests in the early stage, set the minimum values ​​of the average temperature difference and the difference change rate, the temperature gradient X-direction component difference and the difference change rate, and the temperature gradient Y-direction component difference and the difference change rate to Δemin, Δecmin, Δtxmin, Δtxcmin, Δtymin, Δtycmin, set the maximum values ​​of the average temperature difference and the difference change rate, the temperature gradient X-direction component difference and the difference change rate, and the temperature gradient Y-direction component difference and the difference change rate to Δemax, Δecmax, Δtxmax, Δtxcmax, Δtymax, Δtycmax; set the domain of the average temperature difference Δe to {Δemin, Δemin / 2, Δemin / 3, 0,Δemax / 3, Δemax / 2, Δemax}, the domain of the average temperature difference change rate Δec is {Δecmin, Δecmin / 2, Δecmin / 3, 0, Δecmax / 3, Δecmax / 2, Δecmax}, the domain of the temperature gradient X-component difference Δtx is {Δtxmin, Δtxmin / 2, Δtxmin / 3, 0, Δtxmax / 3, Δtxmax / 2, Δtxmax}, the domain of the temperature gradient X-component difference change rate Δtxc is {Δtxcmin, Δtxcmin / 2, Δtxcmin / 3, 0, Δtxcmax / 3, Δtxcmax / 2,Δtxcmax}, the domain of the temperature gradient Y-component difference Δty is {Δtymin, Δtxmin / 2, Δtymin / 3, 0,Δtymax / 3, Δtymax / 2, The domain of the temperature gradient Y-component difference change rate Δtyc is {Δtycmin, Δtxmin / 2, Δtycmin / 3, 0, Δtycmax / 3, Δtycmax / 2, Δtycmax}, and the corresponding fuzzy subsets of the input quantities are established respectively. Set eH1 and eH2 as the difference between the maximum and minimum values ​​of the transverse magnetic field intensity and the longitudinal magnetic field intensity in the preliminary experiment, set the domain of the transverse magnetic field intensity adjustment ΔH1 to {-eH1, -eH1 / 2, -eH1 / 3, 0, eH1 / 3, eH1 / 2, eH1}, and the domain of the longitudinal magnetic field intensity adjustment ΔH2 to {-eH2, -eH2 / 2, -eH2 / 3, 0, eH2 / 3, eH2 / 2, eH2}, and establish the corresponding fuzzy subsets of the output quantities {NB, NM, NS, Z0, PS, PM, PB} respectively; S32, setting fuzzy rule standards and establishing a fuzzy rule base: establishing fuzzy rules for average temperature, temperature gradient X-direction component and temperature gradient Y-direction component respectively according to the following standards: 1) When the deviation and the rate of change of deviation are small, ΔH1 and ΔH2 take smaller values; 2) When the deviation is small and the deviation change rate is large, ΔH1 takes a larger value and ΔH2 takes a smaller value; 3) When the deviation and the rate of change of deviation are of medium size, ΔH1 and ΔH2 take moderate values; 4) When the deviation is large and the deviation change rate is small, ΔH1 takes a smaller value and ΔH2 takes a larger value; 5) When the deviation and the rate of change of deviation are large, ΔH1 and ΔH2 take larger values; The above-mentioned smaller refers to a smaller negative deviation or a smaller positive deviation, and larger refers to a larger negative deviation or a larger positive deviation.

[0064] The established fuzzy control rule table is shown in the following table:

[0065] In the above, NB is the abbreviation of Negative Big, representing a larger negative deviation, NM is the abbreviation of Negative Middle, representing a medium negative deviation, NS is the abbreviation of Negative Small, representing a smaller negative deviation, Z0 represents no deviation, PS, PM, and PB are the abbreviations of Positive Small, Positive Middle, and Positive Big, representing small, medium, and large positive deviations, respectively.

[0066] S33. Select the membership function of the fuzzification process of input and output and the defuzzification method of the output: use the triangular membership function to determine the membership of the elements in the domain of input and output to the fuzzy variables, and use the weighted average method to achieve the defuzzification of the output.

[0067] The present application also provides a laser arc hybrid welding interface temperature control system with an external magnetic field, such as Figure 3 As shown, including: Welding process monitoring subsystem 31 and computer control subsystem 32.

[0068] The welding process monitoring subsystem 31 includes a welding parameter monitoring module 311, an arc monitoring module 312 and a temperature monitoring module 313; the welding parameter monitoring module 311 is used to collect the current welding parameters of the welding sample, and the welding parameters include welding current, welding voltage, laser power and current of the induction coil; the arc monitoring module 312 is used to collect the current arc image of the welding sample; the temperature monitoring module 313 is used to monitor the current surface temperature of the welding sample.

[0069] The computer control subsystem 32 includes an image feature processing module 321, an interface temperature distribution feature prediction module 322 and an interface temperature control module 323; the image feature processing module 321 is used to determine the arc deflection angle and arc width based on the arc image; the interface temperature distribution feature prediction module 322 is used to process the welding parameters using the interface temperature distribution feature neural network prediction model to predict the current temperature distribution characteristics of the welding interface; the welding parameters include welding current, welding voltage, laser power, welding sample surface temperature, arc deflection angle and arc width; the interface temperature control module 323 is used to determine the deviation of the current temperature distribution characteristics of the welding interface based on the current temperature distribution characteristics of the welding interface and the standard temperature distribution characteristics of the welding interface; based on the deviation, determine the adjustment amount of the magnetic field strength of the induction coil through fuzzy rules; based on the adjustment amount of the magnetic field strength of the induction coil, adjust the magnetic field strength of the induction coil to adjust the current temperature of the welding interface.

[0070] The laser arc hybrid welding interface temperature control system with an external magnetic field provided in the embodiment of the present application has a magnetic field that can act on the charged particles of the arc plasma to dynamically change the shape and position of the arc. The shape change can regulate the intensity of the heat source action, and the position change can affect the transmission direction of the heat source action, thereby obtaining the current welding parameters of the welding sample; the welding parameters include welding current, welding voltage, laser power, surface temperature of the welding sample, arc deflection angle and arc width; the interface temperature distribution feature neural network prediction model is used to process the welding parameters to predict the current temperature distribution characteristics of the welding interface; based on the current temperature distribution characteristics of the welding interface The invention discloses a method for adjusting the magnetic field strength of the induction coil by using a fuzzy rule based on the deviation of the standard temperature distribution characteristics of the welding interface and the current temperature distribution characteristics of the welding interface; the method comprises the following steps: determining the adjustment amount of the magnetic field strength of the induction coil, the first adjustment amount corresponding to the transverse magnetic field strength of the induction coil, and the second adjustment amount corresponding to the longitudinal magnetic field strength of the induction coil; and adjusting the magnetic field strength of the induction coil based on the adjustment amount of the magnetic field strength of the induction coil to adjust the current temperature of the welding interface; in this way, the shape and position of the arc can be changed, the input position and strength of the heat source can be controlled, the temperature of the welding interface can be adjusted in real time, and high-quality welding of dissimilar metals can be completed.

[0071] In an optional embodiment, the image feature processing module is used to identify the arc in the arc image and obtain the target area corresponding to the arc; perform edge extraction on the target area to obtain the arc contour; and determine the arc deflection angle and arc width based on the arc contour.

[0072] The program code for implementing the method of the present application can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, implements the functions / operations specified in the flow chart and / or block diagram. The program code can be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0073] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0074] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0075] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0076] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this application can be executed in parallel, sequentially or in different orders, as long as the expected results of the technical solution disclosed in this application can be achieved, and this document is not limited here.

[0077] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0078] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for controlling the interface temperature of laser arc hybrid welding with an external magnetic field, characterized in that: include: Obtaining current welding parameters of the welding sample; the welding parameters include welding current, welding voltage, laser power, surface temperature of the welding sample, arc deflection angle and arc width; The welding parameters are processed by using a neural network prediction model for interface temperature distribution characteristics to predict the current temperature distribution characteristics of the welding interface; Determining a deviation of the current temperature distribution characteristics of the welding interface based on the current temperature distribution characteristics of the welding interface and the standard temperature distribution characteristics of the welding interface; Based on the deviation, determining the adjustment amount of the magnetic field strength of the induction coil by using a fuzzy rule; Based on the adjustment amount of the magnetic field strength of the induction coil, the magnetic field strength of the induction coil is adjusted to adjust the current temperature of the welding interface.

2. The method according to claim 1, characterized in that The steps of constructing the interface temperature distribution characteristic neural network prediction model include: Obtaining training welding parameters of the pre-experimental welding sample during the welding pre-experiment; wherein the material and thickness of the pre-experimental welding sample are the same as the material and thickness of the welding sample; the welding pre-experiment is a single-factor variable experiment, and during the single-factor variable experiment, the training welding voltage, training welding current, training laser power, training transverse magnetic field intensity, and training longitudinal magnetic field intensity are changed respectively; the training welding parameters include training welding voltage, training welding current, training laser power, training arc width, training arc deflection angle, internal temperature of the pre-experimental welding sample, and surface temperature of the pre-experimental welding sample; Based on the internal temperature of the pre-experimental welding sample, a laser arc hybrid welding model of the welding sample is fitted to obtain a welding simulation model; Performing two-dimensional slicing processing on the welding simulation model to obtain a corresponding interface distribution cloud map; and performing feature extraction on the interface distribution cloud map to obtain a corresponding training interface temperature distribution feature; The training welding voltage, training welding current, training laser power, training arc width, training arc deflection angle, and surface temperature of the pre-experimental welding sample are used as training samples, and the training interface temperature distribution characteristics are used as labels to train the neural network and obtain the interface temperature distribution characteristics neural network prediction model.

3. The method according to claim 2, characterized in that The steps of constructing the standard temperature distribution characteristics of the welding interface include: Obtaining compound analysis results of the pre-experimental welding specimens after the single factor variable experiment, wherein the compound analysis results include average intermetallic compound thickness and brittle intermetallic compound content; The training interface temperature distribution characteristics of the pre-experimental welding sample whose compound analysis results meet the requirements are selected as the standard temperature distribution characteristics of the welding interface.

4. The method according to claim 1, characterized in that: The deviation includes the average temperature difference and the difference change rate, the temperature gradient X-direction component difference and the difference change rate, the temperature gradient Y-direction component difference and the difference change rate; Based on the deviation, the adjustment amount of the magnetic field strength of the induction coil is determined by fuzzy rules, including: The average temperature difference and the difference change rate, the temperature gradient X-direction component difference and the difference change rate, the temperature gradient Y-direction component difference and the difference change rate are processed based on fuzzy rules through the interface temperature distribution fuzzy controller to obtain the fuzzy value of the induction coil transverse magnetic field intensity adjustment amount and the fuzzy value of the induction coil longitudinal magnetic field intensity adjustment amount; The fuzzy value of the induction coil transverse magnetic field strength adjustment amount and the fuzzy value of the induction coil transverse magnetic field strength adjustment amount are defuzzified to obtain the induction coil transverse magnetic field strength adjustment amount ΔH1 and the induction coil transverse magnetic field strength adjustment amount ΔH2.

5. The method according to claim 1, characterized in that Adjusting the magnetic field strength of the induction coil based on the adjustment amount of the magnetic field strength of the induction coil includes: Determining an adjustment amount of a current of the induction coil based on an adjustment amount of the magnetic field strength of the induction coil; Based on the current adjustment amount of the induction coil, the current amount of the induction coil is adjusted to adjust the magnetic field strength of the induction coil.

6. The method according to claim 1, characterized in that Get arc deflection angle and arc width, including: Acquire arc images; Based on the arc image, the arc deflection angle and arc width are determined.

7. The method according to claim 6, characterized in that Determining the arc deflection angle and the arc width based on the arc image includes: Identify the arc in the arc image and obtain a target area corresponding to the arc; Performing edge extraction on the target area to obtain an arc contour; Based on the arc profile, an arc deflection angle and an arc width are determined.

8. The method according to claim 1, characterized in that: Obtain the surface temperature of the welding specimen, including: The temperature of a point on the surface of the welding sample that is perpendicular to the weld direction and 4 mm to 11 mm away from the welding groove is obtained to obtain the surface temperature of the welding sample.

9. The method according to claim 1, characterized in that: The material of the welding specimen is titanium steel dissimilar material.

10. A laser arc hybrid welding interface temperature control system with an external magnetic field, characterized in that: include: Welding process monitoring subsystem and computer control subsystem; The welding process monitoring subsystem includes a welding parameter monitoring module, an arc monitoring module and a temperature monitoring module; The welding parameter monitoring module is used to collect the current welding current, welding voltage and laser power of the welding sample; the arc monitoring module is used to collect the current arc image of the welding sample; the temperature monitoring module is used to monitor the current surface temperature of the welding sample; The computer control subsystem includes an image feature processing module, an interface temperature distribution feature prediction module and an interface temperature control module; the image feature processing module is used to determine the arc deflection angle and arc width based on the arc image; the interface temperature distribution feature prediction module is used to process the welding parameters using the interface temperature distribution feature neural network prediction model to predict the current temperature distribution characteristics of the welding interface; the welding parameters include the welding current, welding voltage, laser power, welding sample surface temperature, arc deflection angle and arc width; the interface temperature control module is used to determine the deviation of the current temperature distribution characteristics of the welding interface based on the current temperature distribution characteristics of the welding interface and the standard temperature distribution characteristics of the welding interface; based on the deviation, the adjustment amount of the magnetic field strength of the induction coil is determined by fuzzy rules; based on the adjustment amount of the magnetic field strength of the induction coil, the magnetic field strength of the induction coil is adjusted to adjust the current temperature of the welding interface.

Images