Friction stir welding real-time temperature field monitoring method and system and electronic equipment

Abstract

The invention discloses a friction stir welding real-time temperature field monitoring method and system and electronic equipment, and relates to the technical field of welding, the method comprises the steps that temperature field data of a friction stir welding area are acquired, a heat distribution characteristic value is calculated according to the temperature field data, and the temperature field data are acquired through an infrared temperature measurement system; comparing and analyzing the heat distribution characteristic value with a preset temperature window to generate a temperature field deviation index; triggering a parameter adjustment instruction according to the temperature field deviation index, wherein the parameter adjustment instruction comprises a shaft shoulder pressing amount correction value and a main shaft rotating speed compensation value; the radiation temperature of a black identification area on the periphery of the stirring head is collected in real time, the radiation temperature is dynamically matched with a reference temperature model, when the temperature deviation exceeds a preset deviation threshold value, multi-parameter cooperative control is started, and the reference temperature model is built based on obtained welding parameter information of friction stir welding; according to the method, the temperature monitoring and regulating effect on friction stir welding under the complex working condition is improved.

Description

Technical Field

[0001] The present application relates to the field of welding technology, and in particular to a method, system and electronic equipment for real-time temperature field monitoring of friction stir welding. Background Art

[0002] As a solid-state joining technology, friction stir welding (FSW) relies heavily on heat input uniformity for weld quality. Studies have shown that the axial gradient of the welding temperature field must be controlled within ±15°C, and the circumferential temperature difference must not exceed 20°C. Otherwise, problems such as microstructural inhomogeneity and decreased mechanical properties can result.

[0003] Existing monitoring of welding temperature fields mostly uses thermocouples or infrared spot thermometers for local temperature collection, which cannot reflect the overall temperature distribution characteristics of the weld area. For example, although US6733010B2 introduces infrared temperature measurement technology, it only monitors the surface temperature of the shaft shoulder and ignores the temperature gradient changes in the heat-affected zone. When welding dissimilar metals or composite materials, the existing fixed temperature window (such as the fixed temperature window of aluminum-magnesium alloy (450-520℃)) and the temperature fixed threshold welding strategy are prone to cause temperature overshoot, and the temperature fluctuation can reach ±35℃ when welding copper and aluminum dissimilar materials. It is difficult to ensure the stability of the temperature window under complex working conditions. Therefore, there is a defect in the temperature monitoring and control effect of stir friction welding, and there is room for improvement. Summary of the Invention

[0004] In order to improve the temperature monitoring and control effect of stir friction welding under complex working conditions, the present application provides a real-time temperature field monitoring method, system and electronic equipment for stir friction welding.

[0005] In the first aspect, the invention objectives of this application are achieved by adopting the following technical solutions: A real-time temperature field monitoring method for friction stir welding, comprising: Acquiring temperature field data of the friction stir welding area, and calculating a heat distribution characteristic value based on the temperature field data, wherein the temperature field data is collected by an infrared temperature measurement system; Comparing and analyzing the heat distribution characteristic value with a preset temperature window to generate a temperature field deviation index; triggering a parameter adjustment instruction according to the temperature field deviation index, wherein the parameter adjustment instruction includes a shoulder pressure correction value and a spindle speed compensation value; The radiation temperature of the black marked area around the stirring head is collected in real time, and the radiation temperature is dynamically matched with the reference temperature model. When the temperature deviation exceeds the preset deviation threshold, multi-parameter collaborative control is initiated, where the reference temperature model is constructed based on the acquired welding parameter information of stir friction welding.

[0006] By adopting the above technical solution, the welding parameter information of stir friction welding includes parameter information such as welding speed, spindle speed and welding pressure; the black marked area is an artificial heat radiation source formed by applying a high-absorptivity coating to enhance the contrast of the temperature signal; this application uses an infrared temperature measurement system to collect temperature field data in real time, breaking through the limitations of traditional single-point thermocouple monitoring and realizing global perception of the temperature distribution in the welding area; this application forms a closed-loop linkage mechanism with the temperature deviation index, the shoulder pressure, and the spindle speed to realize multi-parameter coupling control, solves the process conflict problem easily caused by single parameter adjustment, and realizes precise regulation of welding heat input; through dynamic matching of the reference temperature model, it can automatically identify material property differences and working condition fluctuations, and trigger a collaborative control strategy through a preset deviation threshold, significantly improving process robustness; this application uses multi-dimensional temperature feature analysis to provide early warning of temperature abnormal areas, which is beneficial to avoid defects such as coarse grains and flash caused by local overheating, improve the welding effect of stir friction welding, and thus help improve the temperature monitoring and regulation effect of stir friction welding under complex working conditions.

[0007] In a preferred example of the present application, the step of obtaining temperature field data of the friction stir welding area includes: The infrared temperature camera installed on the main shaft bracket of the friction stir welding machine is used to perform a grid temperature scan on the working area of the stirring head to obtain an infrared thermal image; Performing grayscale processing on the infrared thermal image to extract temperature gradient distribution characteristics; Based on the temperature gradient distribution characteristics and combined with the blackbody radiation theory, a temperature-grayscale conversion model is established to convert the red thermal image into temperature field matrix data to obtain the temperature field data of the welding area.

[0008] By adopting the above technical solution, the spatial resolution is improved, and the grid scanning improves the spatial sampling density of the temperature field space compared to the traditional single-point infrared temperature measurement, which can capture local hot spots in the welding area (such as overheating of the edge of the stirring head); the temperature-grayscale conversion model established based on the blackbody radiation theory, combined with the grayscale nonlinear correction, is conducive to eliminating the deviation of the infrared camera response curve and reducing the temperature measurement error. This application overcomes the problems of slow response and susceptibility to environmental interference of traditional temperature measurement methods, and improves the accuracy and stability of temperature field data acquisition.

[0009] In a preferred example of the present application, the step of generating the temperature field deviation index includes: Calculate the similarity between the real-time temperature field matrix and the standard temperature field in the material process database to obtain the similarity difference; Calculate the axial temperature gradient offset and circumferential temperature fluctuation coefficient; The temperature gradient offset, the circumferential temperature fluctuation coefficient and the real-time temperature extreme value are combined to generate a temperature field deviation index including a spatial distribution dimension.

[0010] By adopting the above technical solution, through the joint judgment of axial temperature gradient offset and circumferential temperature fluctuation coefficient, material overheating or cold welding defects can be detected 10 to 15 seconds earlier than the traditional single-point temperature threshold alarm; the temperature field similarity difference (such as SSIM<0.85) is directly related to the mismatch degree between welding speed and pressure, guiding the direction of parameter adjustment to improve the traceability accuracy of process parameters; this application combines the axial temperature gradient offset and the circumferential temperature fluctuation coefficient to comprehensively generate the temperature field deviation index in the spatial dimension, realizing a comprehensive evaluation of the temperature distribution state during the welding process. Compared with the single temperature threshold judgment method, this method can identify potential welding abnormality trends earlier.

[0011] In a preferred example of the present application, the welding parameter information includes welding speed, spindle speed and welding pressure; the reference temperature model construction method includes: Collect temperature field data under different welding parameter combinations and establish welding speed v and rotation speed , multiple regression model of pressure F and temperature field characteristic parameters: , where a, b, c, and d are weight coefficients. is the error term; Genetic algorithm is used to optimize the model parameters a, b, c, and d so that the root mean square error between the predicted temperature field and the measured temperature field is less than the preset temperature threshold; The optimized reference temperature model is embedded in the dynamic temperature compensation unit and denoised using the Kalman filter algorithm; When a sudden change in the welding parameters of friction stir welding is identified, the adaptive learning module is activated and the LSTM neural network is used to predict the temperature field change trend within a specified time period in the future.

[0012] By adopting the above technical solution, a multivariate regression baseline temperature model is constructed based on welding parameters (such as welding speed, rotation speed, and pressure), and a genetic algorithm is used to optimize the model parameters. Combined with Kalman filter denoising and LSTM neural network prediction, the accuracy and dynamic adaptability of temperature field modeling are significantly improved. This application not only improves the response capability to sudden changes in the welding process, but also enhances the robustness and intelligence level of the system under different process conditions.

[0013] In a preferred example of the present application, the triggering of the parameter adjustment instruction according to the temperature field deviation index specifically includes: Establish a welding parameter sensitivity matrix based on the rotation speed sensitivity coefficient, the pressing amount sensitivity coefficient and the welding speed sensitivity coefficient; generating a parameter adjustment vector based on the welding parameter sensitivity matrix and the temperature field deviation index, wherein the parameter adjustment vector includes a rotation speed compensation value, a downward pressure correction value, and a welding speed correction value; Parameter adjustment constraints are set based on the parameter adjustment vector, and a hierarchical adjustment instruction set is generated according to the parameter adjustment constraints.

[0014] By adopting the above technical solution, by establishing a welding parameter sensitivity matrix, combining the temperature field deviation index to generate a parameter adjustment vector, and introducing a hierarchical adjustment instruction set, refined and scientific control of welding parameter adjustment is achieved.

[0015] In a preferred example of the present application, setting parameter adjustment constraints based on the parameter adjustment vector and generating a hierarchical adjustment instruction set according to the parameter adjustment constraints include: The parameter adjustment constraints include: when ∈[-10rpm, +10rpm], perform fast adjustment; when ∈[-0.05mm, +0.05mm] when performing precision adjustment; When Δv∈[-5m / min, +5m / min], segmented adjustment is performed; Generate hierarchical adjustment instruction set { , , },in The spindle speed adjustment amount; is the correction value of the shoulder pressure; Δv is the correction value of the welding speed; For a single adjustment instruction, For gradual adjustment instructions, It is a compound adjustment instruction.

[0016] By adopting the above technical solution, clear parameter adjustment constraints are set, and the variation ranges of the spindle speed, shoulder pressure and welding speed are matched with different types of adjustment instructions (fast adjustment, precise adjustment, and segmented adjustment), thereby constructing a graded adjustment instruction set. This application can select the most appropriate control strategy according to the degree of temperature deviation under different working conditions, thereby avoiding the occurrence of over-adjustment or under-adjustment.

[0017] In a preferred embodiment of the present application, the method further includes: When the temperature gradient offset G of the infrared thermal image is equal to the axial strain collected by the strain sensor Satisfy G× When the temperature is >1.5℃ / %, the fuse mechanism is triggered and a safety instruction is generated forcibly. ; According to the noise covariance matrix Q output by the Kalman filter, the sensitivity matrix is modified 、 , Δv weight coefficient: When the speed noise component of Q is greater than the preset speed noise threshold, The weight coefficient of Q is increased by 30%; when the pressure noise component of Q is greater than the preset pressure noise threshold, The weight coefficient of Δv is reduced by 20%; when the welding speed noise component of Q is greater than the preset speed noise threshold, the weight coefficient of Δv is increased by 5%; or, The execution logic of the hierarchical adjustment instruction set includes: When the fast adjustment instructions are met at the same time and fine adjustment instructions When the trigger condition is and generates compensation instructions through the PID fuzzy controller , so that the correction value of the shoulder pressure satisfy: ,in For quick adjustment instructions Correction value of shoulder pressure; For precise adjustment of instructions Correction value of shoulder pressure; ∈[0.3, 0.7] is the weight factor dynamically assigned to the fuzzy rules.

[0018] By adopting the above technical solution, a fusing mechanism and a dynamic weight correction mechanism are introduced on the basis of hierarchical control, which further improves the safety and adaptability of the system. When the product of the temperature gradient offset and the axial strain exceeds the set threshold, a mandatory safety instruction is triggered, which can effectively prevent welding defects caused by abnormal temperature rise. At the same time, the sensitivity coefficient weight is dynamically adjusted based on the noise covariance matrix output by the Kalman filter, which enhances the robustness of the control system to measurement noise.

[0019] In the second aspect, the invention objective of this application is achieved by adopting the following technical solutions: A real-time temperature field monitoring system for friction stir welding is used to implement the real-time temperature field monitoring method for friction stir welding as described above, and the system comprises: Infrared temperature measurement module, used to collect temperature field data of the welding area during welding; a data processing module, configured to calculate a heat distribution characteristic value based on the temperature field data, and compare and analyze the heat distribution characteristic value with a preset temperature window to generate a temperature field deviation index; a control module, configured to generate a parameter adjustment instruction according to the temperature field deviation index, wherein the parameter adjustment instruction includes a shoulder pressure correction value and a spindle speed compensation value; Radiation temperature acquisition unit, used to collect the radiation temperature of the black marked area around the stirring head in real time; a dynamic matching module, configured to dynamically match the radiation temperature with a reference temperature model, wherein the reference temperature model is constructed based on welding parameter information of friction stir welding; The multi-parameter collaborative controller is used to start parameter collaborative control when the temperature deviation exceeds a preset deviation threshold to adjust the process parameters during the welding process.

[0020] In a third aspect, the invention objective of this application is achieved by adopting the following technical solutions: An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned method for real-time temperature field monitoring of stir friction welding are implemented.

[0021] Fourthly, the invention objectives of this application are achieved by adopting the following technical solutions: A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned method for real-time temperature field monitoring of stir friction welding.

[0022] In summary, this application includes at least one of the following beneficial technical effects: 1. This application proposes a complete real-time temperature field monitoring system architecture for friction stir welding, covering infrared temperature measurement, data processing, deviation analysis, parameter adjustment, radiation temperature acquisition, dynamic model matching, and multi-parameter collaborative control. It achieves high-precision sensing and closed-loop control of the temperature field during welding, with excellent real-time performance, stability, and intelligence, and is applicable to a variety of welding materials and process parameter scenarios. 2. By setting an infrared temperature camera on the friction stir welding spindle bracket to perform grid scanning of the welding area, and combining grayscale processing with blackbody radiation theory to establish a temperature-grayscale conversion model, high-precision and real-time acquisition of the temperature field in the welding area can be achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 This is a flow chart of a method for real-time temperature field monitoring of friction stir welding in one embodiment of the present application; Figure 2 It is a schematic diagram of a device in one embodiment of the present application. DETAILED DESCRIPTION

[0024] The present application is further described in detail below with reference to the accompanying drawings.

[0025] In one embodiment, if Figure 1As shown, the present application discloses a real-time temperature field monitoring method for friction stir welding, which specifically includes the following steps: S1: Obtain temperature field data of the friction stir welding area and calculate the thermal distribution characteristic value based on the temperature field data, wherein the temperature field data is collected by an infrared temperature measurement system.

[0026] The infrared temperature measurement system is deployed as follows: An infrared thermal imager (such as the FLIR A655sc, with a temperature range of 300-1200°C and a frame rate of ≥200Hz) is mounted on the spindle support of the friction stir welding machine. The lens axis maintains a ±5° angle with the axis of rotation of the stir head. A three-dimensional motion platform controls the camera to perform grid scans along the welding direction (X-axis) and depth (Y-axis). The scan interval is set to 1mm x 1mm, covering the stir head working area (diameter ≤200mm). The welding current and voltage signals are simultaneously collected (sampling rate ≥1kHz).

[0027] Specifically, the infrared thermal image is corrected for non-uniformity, using a piecewise linear correction method to eliminate the nonlinear error of the detector response curve; dynamic background subtraction is implemented: the ambient thermal radiation interference is filtered out by a sliding average method (window length 5 frames), retaining the characteristic temperature signal of the stirring head area. The thermal distribution feature extraction includes gradient calculation and hot spot positioning. The gradient calculation refers to the use of the Sobel operator to calculate the axial (X direction) and circumferential (θ direction) gradients of the temperature field matrix to generate the gradient amplitude map G(x, y) = ,in is the temperature gradient offset on the X-axis of the temperature field matrix; is the temperature gradient offset on the Y axis of the temperature field matrix. The hot spot in the contact area between the stirring head and the workpiece is extracted by the Otsu adaptive threshold segmentation method, and its centroid coordinates are calculated ( , ) and equivalent diameter .

[0028] Furthermore, the temperature field data of the friction stir welding area is obtained, including: S11: The infrared temperature camera installed on the main spindle bracket of the friction stir welding is used to perform a grid temperature scan on the working area of the stirring head to obtain an infrared thermal image.

[0029] In this embodiment, grid scanning involves dividing the weld area into a regularly arranged array of discrete points (e.g., 1mm x 1mm) and collecting temperature data point by point. Infrared thermal images are two-dimensional grayscale images that reflect the temperature distribution in the weld area, with grayscale values positively correlated with temperature. The thermal imager's trigger mode is set to "external trigger," synchronizing with the welding power supply signal to avoid motion blur. Each frame of the infrared thermal image is labeled with a timestamp and spatial coordinates to facilitate subsequent data fusion.

[0030] S12: grayscale processing is performed on the infrared thermal image to extract temperature gradient distribution characteristics.

[0031] In this embodiment, grayscale processing refers to mapping the original pixel values of the infrared thermal image (such as a 14-bit digital signal) into 0-255 grayscale levels to enhance contrast; the temperature gradient refers to the rate of change of the temperature field in space, reflecting the direction and rate of heat transfer.

[0032] Specifically, the infrared thermal image after grayscale processing is detected based on the cv2 image processing toolkit: the Sobel algorithm is used to detect the light and dark changes in the left and right directions of the image (that is, the horizontal edges) to obtain the horizontal gradient; similarly, the light and dark changes in the up and down directions of the image (that is, the vertical edges) are detected to obtain the vertical gradient. Based on the image change gradients in the horizontal and vertical directions, the square root is used to calculate the total "edge strength" at each point, which is synthesized into the total edge strength of each pixel to form a gradient map.

[0033] S13: Based on the temperature gradient distribution characteristics and the blackbody radiation theory, a temperature-grayscale conversion model is established to convert the red thermal image into temperature field matrix data to obtain the temperature field data of the welding area.

[0034] In this embodiment, the blackbody radiation theory refers to the quantitative relationship between the radiation energy and temperature of an ideal object (Planck's law); the temperature-grayscale conversion model refers to a mathematical model that maps the grayscale value of an infrared thermal image to a real temperature value.

[0035] Specifically, a constant temperature blackbody furnace (temperature range 300-1200°C, accuracy ±1°C) was used as a standard source to collect grayscale images at different temperatures.

[0036] The model construction of the temperature-grayscale conversion model includes: The relationship between radiation brightness L and temperature T is derived based on Planck's law: ,in, is the material emissivity (0.3-0.4 for aluminum alloy); is the Stefan-Boltzmann constant; and the linear relationship between the gray value G1 and the radiance L is fitted by the least squares method: G1=a1×L+b1, a1 and b1 are weight coefficients, combined with the emissivity correction to obtain the temperature calculation formula: Insert a standard temperature block (such as a copper block with a known melting point of 1085°C) every 10 minutes of welding to dynamically correct parameters a1 and b1.

[0037] S2: Compare and analyze the heat distribution characteristic value with the preset temperature window to generate a temperature field deviation index.

[0038] In this embodiment, a standard temperature field library based on typical materials and fixed process parameters is first constructed: The method for constructing a standard temperature field library includes: selecting typical materials (such as 2219 aluminum alloy and 316L stainless steel) to make standardized specimens, collecting temperature field data under fixed process parameters (v=300mm / min, ω=1500rpm, F=5kN), and then simulating the temperature field distribution through finite element simulation (ANSYS Workbench). Combined with the measured data calibration, a standard temperature field library containing material thermal conductivity λ, specific heat capacity, and heat capacity is established. Three-dimensional standard temperature field database.

[0039] Specifically, the structural similarity index (SSIM) is used to quantify the real-time temperature field. (x, y) and standard temperature field The spatial matching degree of (x, y) and the multi-scale similarity are calculated as: Where N is the number of scale layers (usually 3-5 layers); is the mean; is the spatial average temperature of the real-time temperature field; is the spatial average temperature of the standard temperature field; is the covariance between the real-time temperature field and the standard temperature field; is the variance; is the covariance; 、 is a constant term, usually ranging from 0.01 to 0.03; Multi-scale SSIM (MS-SSIM) combines the similarity weights of different spatial frequencies, and outputs the similarity difference ,like If it is greater than 0.2, the temperature field is judged to be abnormal.

[0040] Furthermore, step S2 includes: S21: Calculate the similarity between the real-time temperature field matrix and the standard temperature field in the material process database to obtain a similarity difference.

[0041] S22: Calculate the axial temperature gradient offset and the circumferential temperature fluctuation coefficient.

[0042] S23: The temperature gradient offset, circumferential temperature fluctuation coefficient and real-time temperature extreme value are integrated to generate a temperature field deviation index including the spatial distribution dimension.

[0043] When calculating the gradient offset, the axial gradient is calculated by calculating the temperature gradient amplitude along the welding direction (X axis): The calculation of the circumferential gradient is along the direction of rotation of the stirring head ( Axis) to calculate the temperature gradient amplitude: , the offset quantification formula is: axial temperature gradient offset in, is the real-time temperature field axial gradient amplitude matrix; is the axial gradient amplitude matrix of the standard temperature field; circumferential temperature fluctuation coefficient ,in is the real-time temperature field circumferential gradient amplitude matrix; is the circumferential gradient amplitude matrix of the standard temperature field; A is the area of the region of interest.

[0044] Calculate the spatial standard deviation based on the spatial mean temperature: , where M and N1 should represent the number of rows and columns of the temperature field matrix, that is, the resolution of the image. For example, if the temperature field is divided into a grid with M rows and N1 columns, then the position of each pixel can be expressed as To represent, where x ranges from 1 to M, and y ranges from 1 to N1; is the average temperature of the space.

[0045] Calculate the energy proportion of the 10-50Hz frequency band: in, It is the fast Fourier transform result of the temperature field data. The temperature field deviation index is obtained by weighted fusion calculation based on the corresponding weight coefficients (specific values can be defined by yourself) associated with the axial temperature gradient offset, circumferential temperature fluctuation coefficient, spatial standard deviation and the energy proportion of the 10-50Hz frequency band.

[0046] S3: triggering a parameter adjustment instruction according to the temperature field deviation index, wherein the parameter adjustment instruction includes a shoulder pressure correction value and a spindle speed compensation value.

[0047] In this embodiment, step S3 includes: S31: Establishing a welding parameter sensitivity matrix based on the rotation speed sensitivity coefficient, the downward pressure sensitivity coefficient and the welding speed sensitivity coefficient.

[0048] In this embodiment, the speed sensitivity coefficient refers to the unit speed change ( ) caused by the temperature field deviation index change; the pressure sensitivity coefficient refers to the unit pressure change ( ) caused by the temperature field deviation index change; the welding speed sensitivity coefficient refers to the temperature field deviation index change caused by the unit welding speed change (Δv).

[0049] Specifically, an orthogonal experiment (such as L9(3^4)) was designed, with a fixed pressure of F=5kN, combined variables v=[200, 400, 600]mm / min, ω=[1000, 1500, 2000]rpm, and the temperature field deviation index BI was recorded.

[0050] Partial least squares regression (PLSR) was used to build the sensitivity model: ,in, 、 is the weight coefficient; is a cross term; is the error term; extract the principal component contribution rate and determine the weight coefficient: Speed sensitivity: =0.38, pressure sensitivity: =0.45, welding speed sensitivity: =0.22.

[0051] Then construct a 3×3 diagonal sensitivity matrix S: S= .

[0052] S32: Generate a parameter adjustment vector based on the welding parameter sensitivity matrix and the temperature field deviation index, where the parameter adjustment vector includes a rotation speed compensation value, a downward pressure correction value, and a welding speed correction value.

[0053] Specifically, the normalized index BI is normalized to obtain , calculate the adjustment amount by matrix multiplication:

[0054] , where Δv is the adjustment amount of welding speed, unit: m / min (meters per minute); The adjustment amount of the shoulder pressure, unit: mm (millimeter); The adjustment amount of the spindle speed, unit: rpm (revolutions per minute).

[0055] S33: Setting parameter adjustment constraints based on the parameter adjustment vector, and generating a hierarchical adjustment instruction set according to the parameter adjustment constraints.

[0056] Specifically, the hierarchical adjustment instruction set generates hierarchical single adjustment instructions ( ), gradual adjustment instructions ( ), compound adjustment instructions ( ), the definition of constraints during graded adjustment includes: The rapid adjustment range is ±10 rpm, the gradual adjustment range is ±3 rpm, and the compound adjustment range is ±5 rpm +±3m / min. The range of rapid adjustment is ±0.1 mm, the range of gradual adjustment is ±0.2 mm, and the range of compound adjustment is ±0.05 mm + ±2 m / min. The range of Δv is ±5 m / min in the rapid adjustment range, ±1 m / min in the gradual adjustment range, and the range of compound adjustment is ±3 m / min + ±2 rpm.

[0057] Furthermore, parameter adjustment constraints are set based on the parameter adjustment vector, and a hierarchical adjustment instruction set is generated according to the parameter adjustment constraints, including: S331: Parameter adjustment constraints include: when ∈[-10rpm, +10rpm], perform fast adjustment; when ∈[-0.05mm, +0.05mm] when performing precision adjustment; When Δv∈[-5m / min, +5m / min], segmented adjustment is performed; Generate hierarchical adjustment instruction set { , , },in For a single adjustment instruction, For gradual adjustment instructions, It is a compound adjustment instruction.

[0058] Furthermore, the execution logic of the hierarchical adjustment instruction set includes: When the fast adjustment instructions are met at the same time and fine adjustment instructions When the trigger condition is and generates compensation instructions through the PID fuzzy controller , so that the correction value of the shoulder pressure satisfy: ,in For quick adjustment instructions Correction value of shoulder pressure; For precise adjustment of instructions Correction value of shoulder pressure; ∈[0.3, 0.7] is the weight factor dynamically assigned to the fuzzy rules.

[0059] S4: The radiation temperature of the black marked area around the stirring head is collected in real time, and the radiation temperature is dynamically matched with the reference temperature model. When the temperature deviation exceeds the preset deviation threshold, multi-parameter collaborative control is initiated, where the reference temperature model is constructed based on the obtained welding parameter information of stir friction welding.

[0060] In this embodiment, the welding parameter information includes welding speed, spindle speed and welding pressure.

[0061] Specifically, step S4 includes: S41: Collect temperature field data under different welding parameter combinations, establish welding speed v, rotation speed , multiple regression model of pressure F and temperature field characteristic parameters: , where a, b, c, and d are weight coefficients. is the error term.

[0062] In this embodiment, the welding speed refers to the moving speed of the weld per unit time (unit: mm / min); the rotation speed refers to the angular velocity of the stirring head (unit: rpm); the welding pressure refers to the axial force corresponding to the pressure of the shoulder (unit: kN); the temperature field characteristic parameters include the spatial average temperature, the axial gradient amplitude, the circumferential fluctuation coefficient, and the error term Obey the normal distribution N(0, ).

[0063] S42: Optimizing the model parameters a, b, c, and d using a genetic algorithm so that the root mean square error between the predicted temperature field and the measured temperature field is less than a preset temperature threshold.

[0064] In this embodiment, the genetic algorithm optimization includes crossover and mutation operations based on a fitness function, where the fitness function is the inverse of the root mean square error (RMSE), that is: ,in, To predict the temperature field; The measured temperature field is represented by the root mean square error (RMSE), which measures the difference between the predicted and measured temperature fields. The inverse of the RMSE is taken when converting it to a fitness function. The goal is to achieve a lower RMSE (more accurate model predictions) and a higher fitness value. The mutation operation is simulated binary crossover (SBX), with a crossover probability of Pc = 0.9. Polynomial mutation is used, with a mutation probability of Pm = 0.1.

[0065] S43: Embed the optimized reference temperature model into the dynamic temperature compensation unit and perform denoising through the Kalman filter algorithm.

[0066] Specifically, the dynamic temperature compensation unit adjusts the baseline model output according to the real-time welding parameters. Contains temperature field prediction value, control input Including welding speed v, rotation speed , pressure F, observation value is the measured temperature field data, where the recursive state estimation algorithm formula of the Kalman filter is: , ,in = Indicates the state of the Kth step; For the previous step ( k −1) state estimate; is the system noise; H is the observation matrix (mapping the state vector to the observation value); the state transfer matrix A= , which represents the evolution of the system state over time. The temperature term is attenuated (90% retained from the previous step, plus the current input effect), and other parameters remain unchanged. Control input gain matrix: B = , which represents the control input The degree of influence on each state variable.

[0067] S44: When a sudden change in the welding parameters of friction stir welding is identified, the adaptive learning module is activated and the LSTM neural network is used to predict the temperature field change trend within a specified time period in the future.

[0068] In this embodiment, the STM network is a long short-term memory neural network suitable for time series prediction; the training data is the historical welding parameters and temperature field data, sampled at a time step of Δt = 1 second Specifically, the input layer of the STM network includes 3 nodes (v, ω, F), the LSTM layer: 64 hidden units, the forgetting factor γ = 0.8, and the output layer 1 node (predicted temperature field ), the loss function uses the mean square error (MSE), and the optimizer uses the Adam optimizer (learning rate 0.001).

[0069] In one embodiment, a method for real-time temperature field monitoring of friction stir welding further includes: S10: When the temperature gradient offset G of the infrared thermal image is equal to the axial strain collected by the strain sensor Satisfy G× When the temperature is >1.5℃ / %, the fuse mechanism is triggered and a safety instruction is generated forcibly. .

[0070] In this embodiment, the temperature gradient offset G refers to the absolute difference between the real-time temperature field gradient amplitude and the standard temperature field gradient amplitude, reflecting the abnormal thermal distribution morphology; the axial strain It refers to the plastic deformation of the stirring head in the axial direction (welding direction), which is collected by a strain sensor (such as HBM C16A).

[0071] Specifically, the temperature gradient offset G is related to the axial strain collected by the strain sensor. Satisfy G× When the temperature is >1.5℃ / %, it is determined that there is a risk of thermal coupling failure (such as the stirring head is stuck or the material is over-softened), and the safety instruction is forcibly triggered. .

[0072] Specifically, safety instructions The execution mechanism includes: immediately interrupting the welding current (cutting off the heat source); controlling the shaft shoulder to rise at a speed of 60mm / s for 200ms to avoid material adhesion; triggering the sound and light alarm and recording the process parameters at the time of the fault.

[0073] S20: According to the noise covariance matrix Q output by the Kalman filter, correct the sensitivity matrix 、 , Δv weight coefficient: When the speed noise component of Q is greater than the preset speed noise threshold, The weight coefficient of Q is increased by 30%; when the pressure noise component of Q is greater than the preset pressure noise threshold, The weight coefficient is reduced by 20%.

[0074] In this embodiment, the noise covariance matrix ,in 、 、 are the noise components of welding speed, rotation speed and pressure respectively. is the temperature observation noise, and the noise covariance matrix Q is output in real time through the Kalman filter state estimator.

[0075] For example, the weight coefficient base value is: initial sensitivity matrix (corresponding to Δv, , , T noise weight).

[0076] Dynamic adjustment example: like =0.0006>0.0005, The weight is adjusted to 0.4×1.3=0.52.

[0077] Constraints include the need to normalize the sum of the adjusted weights. This application combines temperature gradient offset (thermal field) with axial strain (force field) to overcome the limitations of single parameter threshold alarms.

[0078] It should be understood that the serial numbers of the steps in the above embodiments do not imply the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0079] In one embodiment, a real-time temperature field monitoring system for friction stir welding is provided. The real-time temperature field monitoring system for friction stir welding corresponds to a real-time temperature field monitoring method for friction stir welding in the above embodiment.

[0080] A real-time temperature field monitoring system for friction stir welding includes an infrared temperature measurement module, a data processing module, a control module, a radiation temperature acquisition unit, a dynamic matching module, and a multi-parameter collaborative controller. The detailed description of each functional module is as follows: Infrared temperature measurement module, used to collect temperature field data of the welding area during welding; The data processing module is used to calculate the heat distribution characteristic value based on the temperature field data, and compare and analyze the heat distribution characteristic value with the preset temperature window to generate the temperature field deviation index; A control module is used to generate a parameter adjustment instruction according to the temperature field deviation index, the parameter adjustment instruction including a shoulder pressure correction value and a spindle speed compensation value; Radiation temperature acquisition unit, used to collect the radiation temperature of the black marked area around the stirring head in real time; A dynamic matching module is used to dynamically match the radiation temperature with a reference temperature model, which is constructed based on the welding parameter information of the friction stir welding; The multi-parameter collaborative controller is used to start parameter collaborative control when the temperature deviation exceeds a preset deviation threshold to adjust the process parameters during the welding process.

[0081] For the specific definition of a real-time temperature field monitoring system for stir friction welding, please refer to the definition of a real-time temperature field monitoring method for stir friction welding mentioned above, which will not be repeated here; the various modules in the above-mentioned real-time temperature field monitoring system for stir friction welding can be implemented in whole or in part through software, hardware and their combination; the above-mentioned modules can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the corresponding operations of the above modules.

[0082] In one embodiment, an electronic device is provided. The electronic device may be a server, and its internal structure diagram may be as follows: Figure 2 As shown. The electronic device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the electronic device is used to store temperature field data, the radiation temperature of the black mark area, etc. The network interface of the electronic device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a real-time temperature field monitoring method for stir friction welding is realized.

[0083] In one embodiment, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the following steps are implemented: S1: Acquire temperature field data of the friction stir welding area and calculate thermal distribution characteristic values based on the temperature field data, wherein the temperature field data is collected by an infrared temperature measurement system; S2: Compare and analyze the heat distribution characteristic value with the preset temperature window to generate the temperature field deviation index; S3: triggering a parameter adjustment instruction according to the temperature field deviation index, wherein the parameter adjustment instruction includes a shoulder pressure correction value and a spindle speed compensation value; S4: The radiation temperature of the black marked area around the stirring head is collected in real time, and the radiation temperature is dynamically matched with the reference temperature model. When the temperature deviation exceeds the preset deviation threshold, multi-parameter collaborative control is initiated, where the reference temperature model is constructed based on the obtained welding parameter information of stir friction welding.

[0084] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented: S1: Acquire temperature field data of the friction stir welding area and calculate thermal distribution characteristic values based on the temperature field data, wherein the temperature field data is collected by an infrared temperature measurement system; S2: Compare and analyze the heat distribution characteristic value with the preset temperature window to generate the temperature field deviation index; S3: triggering a parameter adjustment instruction according to the temperature field deviation index, wherein the parameter adjustment instruction includes a shoulder pressure correction value and a spindle speed compensation value; S4: The radiation temperature of the black marked area around the stirring head is collected in real time, and the radiation temperature is dynamically matched with the reference temperature model. When the temperature deviation exceeds the preset deviation threshold, multi-parameter collaborative control is initiated, where the reference temperature model is constructed based on the obtained welding parameter information of stir friction welding.

[0085] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0086] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0087] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, it should be understood by those skilled in the art that the technical solutions described in the aforementioned embodiments may still be modified, or some of the features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. A real-time temperature field monitoring method for friction stir welding, characterized in that: include: Acquiring temperature field data of the friction stir welding area, and calculating a heat distribution characteristic value based on the temperature field data, wherein the temperature field data is collected by an infrared temperature measurement system; Comparing and analyzing the heat distribution characteristic value with a preset temperature window to generate a temperature field deviation index; triggering a parameter adjustment instruction according to the temperature field deviation index, wherein the parameter adjustment instruction includes a shoulder pressure correction value and a spindle speed compensation value; The radiation temperature of the black marked area around the stirring head is collected in real time, and the radiation temperature is dynamically matched with the reference temperature model. When the temperature deviation exceeds the preset deviation threshold, multi-parameter collaborative control is initiated, where the reference temperature model is constructed based on the acquired welding parameter information of stir friction welding.

2. A method for real-time temperature field monitoring of friction stir welding according to claim 1, characterized in that: The method of obtaining temperature field data of the friction stir welding area includes: The infrared temperature camera installed on the main shaft bracket of the friction stir welding machine is used to perform a grid temperature scan on the working area of the stirring head to obtain an infrared thermal image; Performing grayscale processing on the infrared thermal image to extract temperature gradient distribution characteristics; Based on the temperature gradient distribution characteristics and combined with the blackbody radiation theory, a temperature-grayscale conversion model is established to convert the red thermal image into temperature field matrix data to obtain the temperature field data of the welding area.

3. The method for real-time temperature field monitoring of friction stir welding according to claim 1, characterized in that: The step of generating the temperature field deviation index comprises: Calculate the similarity between the real-time temperature field matrix and the standard temperature field in the material process database to obtain the similarity difference; Calculate the axial temperature gradient offset and circumferential temperature fluctuation coefficient; The temperature gradient offset, the circumferential temperature fluctuation coefficient and the real-time temperature extreme value are combined to generate a temperature field deviation index including a spatial distribution dimension.

4. The method for real-time temperature field monitoring of friction stir welding according to claim 1, wherein: The welding parameter information includes welding speed, spindle speed and welding pressure; the reference temperature model construction method includes: Collect temperature field data under different welding parameter combinations and establish welding speed v and rotation speed , multiple regression model of pressure F and temperature field characteristic parameters: , where a, b, c, and d are weight coefficients. is the error term; Genetic algorithm is used to optimize the model parameters a, b, c, and d so that the root mean square error between the predicted temperature field and the measured temperature field is less than the preset temperature threshold; The optimized reference temperature model is embedded in the dynamic temperature compensation unit and denoised using the Kalman filter algorithm; When a sudden change in the welding parameters of friction stir welding is identified, the adaptive learning module is activated and the LSTM neural network is used to predict the temperature field change trend within a specified time period in the future.

5. The method for real-time temperature field monitoring of friction stir welding according to claim 1, characterized in that: The triggering of the parameter adjustment instruction according to the temperature field deviation index specifically includes: Establish a welding parameter sensitivity matrix based on the rotation speed sensitivity coefficient, the pressing amount sensitivity coefficient and the welding speed sensitivity coefficient; generating a parameter adjustment vector based on the welding parameter sensitivity matrix and the temperature field deviation index, wherein the parameter adjustment vector includes a rotation speed compensation value, a downward pressure correction value, and a welding speed correction value; Parameter adjustment constraints are set based on the parameter adjustment vector, and a hierarchical adjustment instruction set is generated according to the parameter adjustment constraints.

6. The method for real-time temperature field monitoring of friction stir welding according to claim 5, characterized in that: The step of setting parameter adjustment constraints based on the parameter adjustment vector and generating a hierarchical adjustment instruction set according to the parameter adjustment constraints includes: The parameter adjustment constraints include: when ∈[-10rpm, +10rpm], perform fast adjustment; when ∈[-0.05mm, +0.05mm] when performing precision adjustment; When Δv∈[-5m / min, +5m / min], segmented adjustment is performed; Generate hierarchical adjustment instruction set { , , },in The spindle speed adjustment amount; is the correction value of the shoulder pressure; Δv is the correction value of the welding speed; For a single adjustment instruction, For gradual adjustment instructions, It is a compound adjustment instruction.

7. A method for real-time temperature field monitoring of friction stir welding according to claim 6, characterized in that: The method further comprises: When the temperature gradient offset G of the infrared thermal image is equal to the axial strain collected by the strain sensor Satisfy G× When the temperature is >1.5℃ / %, the fuse mechanism is triggered and a safety instruction is generated forcibly. ; According to the noise covariance matrix Q output by the Kalman filter, the sensitivity matrix is modified 、 , Δv weight coefficient: When the speed noise component of Q is greater than the preset speed noise threshold, The weight coefficient of Q is increased by 30%; when the pressure noise component of Q is greater than the preset pressure noise threshold, The weight coefficient of Δv is reduced by 20%; when the welding speed noise component of Q is greater than the preset speed noise threshold, the weight coefficient of Δv is increased by 5%; or, The execution logic of the hierarchical adjustment instruction set includes: When the fast adjustment instructions are met at the same time and fine adjustment instructions When the trigger condition is and generates compensation instructions through the PID fuzzy controller , so that the correction value of the shoulder pressure satisfy: ,in For quick adjustment instructions Correction value of shoulder pressure; For precise adjustment of instructions Correction value of shoulder pressure; ∈[0.3, 0.7] is the weight factor dynamically assigned to the fuzzy rules.

8. A real-time temperature field monitoring system for friction stir welding, characterized in that: A method for monitoring the real-time temperature field of friction stir welding according to any one of claims 1 to 7, the system comprising: Infrared temperature measurement module, used to collect temperature field data of the welding area during welding; a data processing module, configured to calculate a heat distribution characteristic value based on the temperature field data, and compare and analyze the heat distribution characteristic value with a preset temperature window to generate a temperature field deviation index; a control module, configured to generate a parameter adjustment instruction according to the temperature field deviation index, wherein the parameter adjustment instruction includes a shoulder pressure correction value and a spindle speed compensation value; Radiation temperature acquisition unit, used to collect the radiation temperature of the black marked area around the stirring head in real time; a dynamic matching module, configured to dynamically match the radiation temperature with a reference temperature model, wherein the reference temperature model is constructed based on welding parameter information of friction stir welding; The multi-parameter collaborative controller is used to start parameter collaborative control when the temperature deviation exceeds a preset deviation threshold to adjust the process parameters during the welding process.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the method for real-time temperature field monitoring of friction stir welding as claimed in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for real-time temperature field monitoring of friction stir welding as claimed in any one of claims 1 to 7 are implemented.

Images