Double-beam composite laser welding device

Abstract

The invention discloses a double-beam composite laser welding device. The double-beam composite laser welding device comprises a hardware body and a double-beam composite control system. The hardware body is composed of a supporting assembly, a bearing assembly, a three-axis moving mechanism, an angle adjusting mechanism and a double-compound welding head, and three-dimensional position adjustment and double-beam relative angle and posture adjustment and control can be achieved. The control system comprises a data acquisition module, a data analysis module and a control execution module, light beam parameters, postures, workpiece states and environment data are acquired through multiple sensors, optimal control parameters are generated through preprocessing, feature extraction and fusion algorithms, and all mechanisms are driven to act accurately. The device solves the problems that an existing device is low in angle adjustment efficiency, poor in double-beam collaboration and the like, angle adjustment precision, beam collaborative optimization and control intelligence are achieved, the welding quality and efficiency are effectively improved, and the device is suitable for the high-precision welding requirement of the high-end manufacturing industry.

Description

Technical Field

[0001] This invention relates to the field of laser welding technology, and in particular to a dual-beam composite laser welding device. Background Technology

[0002] In high-end manufacturing sectors such as automobile manufacturing, aerospace component processing, and electronic component packaging, laser welding, with its core advantages of small heat-affected zone, high welding strength, and superior welding efficiency, has gradually replaced traditional arc welding and resistance welding as a key process. With the increasing demand for complex workpiece structures, single-beam laser welding is prone to problems such as insufficient penetration and thermal deformation due to concentrated energy. Dual-beam composite laser welding technology, by synergistically applying two lasers with different characteristics to the welding area, has become an important direction for solving these problems, and its application and optimization have become core needs for industry development.

[0003] However, existing dual-beam composite laser welding devices suffer from key technical bottlenecks: First, angle adjustment relies on manual disassembly and reassembly of the beam components, requiring frequent adjustments for complex workpieces, which is time-consuming and severely impacts production efficiency; second, the manual knob adjustment lacks precision, resulting in significant relative angle deviations between the two beams, leading to uneven energy distribution and defects such as localized overheating or incomplete fusion in the welding area, making it difficult to meet high-precision welding requirements. Therefore, there is an urgent need to develop a technical solution that enables rapid and precise angle adjustment and ensures optimized synergy between the two beams. Summary of the Invention

[0004] This invention provides a dual-beam composite laser welding device that solves the problems of low laser absorption rate, unstable molten pool and easy generation of porosity and spatter when welding high reflective materials, as well as insufficient precision in the coordinated adjustment of dual beam angle and energy ratio.

[0005] To solve the above-mentioned technical problems, the present invention provides a dual-beam composite laser welding device, comprising: a hardware main body and a dual-beam composite control system; the hardware main body includes:

[0006] Support components are used to provide overall support for the device;

[0007] A support component is fixed to the top of a support component. The support component is a support plate with a storage area on its surface for placing workpieces. A welding storage plate is provided in the storage area.

[0008] The three-axis moving mechanism is installed on one side of the supporting component and is used to achieve position adjustment in three-dimensional space.

[0009] An angle adjustment mechanism, mounted on the actuator of the three-axis moving mechanism, is used to adjust the relative angle and spatial attitude of the two beams;

[0010] The double composite welding head includes a first composite welding head and a second composite welding head, which are respectively assembled at corresponding positions of the angle adjustment mechanism;

[0011] The dual-beam composite control system includes:

[0012] The data acquisition module is used to collect dual-beam parameter data, spatial attitude data, workpiece welding status data, and environmental parameter data.

[0013] The data analysis module includes a data preprocessing unit, a feature extraction unit, a state assessment unit, and a dual-beam composite fusion unit. The data preprocessing unit standardizes the collected data. The feature extraction unit extracts key features from the standardized data. The state assessment unit judges the welding state based on the key features. The dual-beam composite fusion unit establishes a mapping relationship between key features and welding effect through a preset fusion algorithm and calculates the optimal control parameters.

[0014] The control execution module is used to receive optimal control parameters and drive the three-axis moving mechanism, angle adjustment mechanism and double composite welding head to perform corresponding actions.

[0015] Preferably, the support assembly includes a base plate and a support structure. The support structure is a support foot installed at the bottom of the base plate, and the support column is fixed to the upper end of the base plate. The top of the support assembly is fixed to the support assembly through the support column.

[0016] Preferably, the three-axis moving mechanism includes an X-axis moving unit, a Y-axis moving unit, and a Z-axis moving unit. The X-axis moving unit is mounted on the support assembly, the Y-axis moving unit is assembled on the actuating end of the X-axis moving unit, the Z-axis moving unit is assembled on the actuating end of the Y-axis moving unit, and the angle adjustment mechanism is assembled on the actuating end of the Z-axis moving unit.

[0017] The X-axis moving unit includes a positioning cylinder, a linear motor, and a moving seat. The positioning cylinder is fixed to one side of the upper end of the support plate, the linear motor is installed on the support plate inside the positioning cylinder, and the moving seat is slidably installed on the linear motor.

[0018] The Y-axis moving unit includes a first moving block, a first servo motor, a second moving block, and a first bolt. The first moving block is fixedly installed on the upper end of the moving base. The first bolt is rotatably installed on the inner side of the first moving block. The first servo motor is installed on one end of the first moving block, and its output end passes through the first moving block and is coaxially fixed to one end of the first bolt. The second moving block is threadedly connected and sleeved on the first bolt.

[0019] The Z-axis moving unit includes a second servo motor, a lifting seat, and a second bolt. The second bolt is rotatably installed in the lifting groove of the second moving block. The second servo motor is installed on the top of the second moving block, and its output end passes through the second moving block and is coaxially fixed to the top of the second bolt. The lifting seat is threadedly connected to the second bolt.

[0020] Preferably, the angle adjustment mechanism includes a positioning frame, a driving component, a transmission component, and a fixing component. The positioning frame is fixed to the lifting seat of the Z-axis moving unit. The first composite welding head is installed on one side of the positioning frame. The transmission component is rotatably connected to the positioning frame. The fixing component is hinged to one end of the transmission component. The second composite welding head is assembled inside the fixing component.

[0021] The driving component includes a first driving component and a second driving component. The first driving component is a fourth servo motor, which is installed inside the positioning frame. Its output end is connected to the transmission component via a snap-fit ​​plate, driving the fixing component to coarsely adjust the angle of the second composite welding head. The second driving component is a third servo motor, which is installed on the transmission component. Its output end is fixedly connected to the fixing component, driving the second composite welding head to finely adjust the angle. The transmission component is a connecting plate, which is symmetrically rotated and installed on the lifting seats at both ends of the first composite welding head. The fixing component is a fixing cylinder, which is hinged between the other ends of the connecting plate. The second composite welding head is assembled inside the fixing cylinder.

[0022] Preferably, the data acquisition module includes a laser parameter sensor, an attitude sensor, a status sensor, and an environmental sensor; the laser parameter sensor is mounted on the second composite welding head inside the first composite welding head and the fixed cylinder, the attitude sensor is mounted on the connecting plate of the angle adjustment mechanism and the fixed cylinder, the status sensor is mounted on the side of the placement area of ​​the support component, and the environmental sensor is installed on the support component.

[0023] Preferably, the standardization processing of the data preprocessing unit includes data denoising, outlier removal, and data normalization transformation.

[0024] Preferably, the key features extracted by the feature extraction unit include beam parameter features, attitude features, workpiece state features, and environmental features.

[0025] Preferably, the fusion algorithm of the dual-beam composite fusion unit includes a weight allocation model and an effect prediction model. The weight allocation model is used to assign weight coefficients to each key feature quantity, and the effect prediction model is used to predict the welding effect and select the optimal control parameters based on the weighted feature quantities.

[0026] Preferably, the control execution module includes a motion control unit, a beam parameter control unit, and an angle adjustment control unit; the motion control unit is electrically connected to the linear motor, the first servo motor, and the second servo motor of the three-axis moving mechanism; the beam parameter control unit is electrically connected to the first composite welding head and the second composite welding head; and the angle adjustment control unit is electrically connected to the third servo motor and the fourth servo motor of the angle adjustment mechanism.

[0027] Compared with related technologies, the dual-beam composite laser welding device provided by the present invention has the following beneficial effects:

[0028] 1. This solution employs a dual-servo motor drive design for the angle adjustment mechanism. A fourth servo motor performs coarse angle adjustment, while a third servo motor handles precise fine-tuning. Combined with real-time attitude data feedback from an attitude sensor, the relative angle adjustment of the two beams can be quickly completed without manual intervention. This design avoids the time wasted on frequent disassembly and ensures angle adjustment accuracy through closed-loop control, solving the problem of uneven energy distribution caused by angle deviation. This significantly improves the continuity and efficiency of welding operations and adapts to the diverse angle requirements of complex workpieces.

[0029] 2. This solution acquires beam parameters, attitude, workpiece status, and environmental data through multiple sensors. After data preprocessing and feature extraction, the dual-beam composite fusion unit calculates the optimal control parameters using a weighted allocation model and an effect prediction model. The control execution module precisely regulates the dual-beam power distribution, relative angle, and movement speed to achieve dynamic coordination of energy and attitude, effectively suppressing defects such as local overheating and incomplete fusion, improving the weld formation qualification rate and strength compliance rate, and ensuring the consistency of welding quality.

[0030] 3. The dual-beam composite control system constructed in this scheme achieves intelligent management and control throughout the entire process. The data acquisition module captures multi-dimensional data in real time, the status assessment unit dynamically judges the welding status, and the fusion algorithm automatically optimizes control parameters based on the mapping relationship between key feature quantities and welding effects. This system can adapt to environmental changes, workpiece differences, and beam parameter fluctuations, reducing reliance on manual experience and lowering the difficulty of operation. At the same time, through a real-time feedback calibration mechanism, it ensures stable output of welding effects under different working conditions, expanding the application scope of the device.

[0031] In summary, this solution, through precise mechanical structure design and the synergy of a dual-beam composite control system, specifically addresses the core pain points of existing dual-beam laser welding devices, such as inefficient angle adjustment, poor dual-beam coordination, and unstable welding quality. It achieves precise angle adjustment, optimized beam coordination, and intelligent control, improving production efficiency and ensuring welding quality stability while enhancing the device's adaptability to various scenarios and ease of operation, thus providing a reliable solution for the high-precision welding needs of high-end manufacturing industries. Attached Figure Description

[0032] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0033] Figure 1 This is a schematic diagram of the overall three-dimensional structure proposed in this invention;

[0034] Figure 2 This is a schematic diagram of the partial overall three-dimensional structure proposed in this invention;

[0035] Figure 3 This is a schematic diagram of the overall three-dimensional structure of the other side proposed in this invention;

[0036] Figure 4 This is a schematic diagram of the overall three-dimensional structure proposed in this invention from a bottom-view perspective;

[0037] Figure 5 This is a schematic diagram of the side cross-sectional structure proposed in this invention;

[0038] Figure 6 This is a block diagram illustrating the core module principle of the present invention.

[0039] The numbers in the diagram are: 1. Support column; 2. Base plate; 3. Support plate; 4. Welded storage plate; 5. Positioning cylinder; 6. Linear motor; 7. Moving seat; 8. First moving block; 9. First servo motor; 10. Second moving block; 11. Second servo motor; 12. Lifting seat; 13. First composite welding head; 14. Third servo motor; 15. Fourth servo motor; 16. Connecting plate; 17. Fixing cylinder; 18. First bolt; 19. Second bolt. Detailed Implementation

[0040] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0041] The terminology used in this disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The singular forms “group,” “class,” and “the” as used in this disclosure and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0042] It should be understood that although the terms first, second, third, etc., may be used in this disclosure to describe various information, such information should not be limited to these terms. These terms are used only to distinguish information of the same type from one another. For example, without departing from the scope of this disclosure, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0043] Please refer to the following: Figures 1-6 A dual-beam composite laser welding device includes a hardware main body and a dual-beam composite control system; the hardware main body includes:

[0044] Support components are used to provide overall support for the device;

[0045] The support component is fixed to the top of the support component. The support component is a support plate 3, and its surface is provided with a storage area for placing workpieces. A welding storage plate 4 is provided in the storage area.

[0046] The three-axis moving mechanism is installed on one side of the supporting component and is used to achieve position adjustment in three-dimensional space.

[0047] An angle adjustment mechanism, mounted on the actuator of the three-axis moving mechanism, is used to adjust the relative angle and spatial attitude of the two beams;

[0048] The dual composite welding head includes a first composite welding head 13 and a second composite welding head, which are respectively assembled at corresponding positions of the angle adjustment mechanism for outputting dual-beam lasers;

[0049] The dual-beam compound control system proposed in this invention includes:

[0050] The data acquisition module is electrically connected to the main hardware unit and is used to acquire dual-beam parameter data, spatial attitude data, workpiece welding status data, and environmental parameter data.

[0051] The dual-beam parameter data acquisition involves simultaneously acquiring the core parameters of both laser beams using laser parameter sensors mounted on the inner sides of the first composite welding head 13 and the second composite welding head of the fixed cylinder 17. These parameters include laser power. Laser wavelength λ, pulse width τ, pulse repetition frequency fp, beam quality factor sampling frequency Among them, the acquisition accuracy of each acquisition parameter satisfies: power error Wavelength error Pulse parameter error , Beam quality factor error The laser powers of the first and second composite welding heads are respectively , ;

[0052] The sensor outputs a 4-20mA analog signal or an RS485 digital signal. The data acquisition module converts the analog signal into a 16-bit digital signal using an analog-to-digital converter (ADC). The conversion formula is as follows: Where D is the digital signal value, The sensor input voltage, , The ADC reference voltage is used, and the converted data is stored in the cache unit;

[0053] Spatial attitude data acquisition: The spatial attitude parameters of the dual composite welding heads are acquired by a six-axis attitude sensor (gyroscope + accelerometer) mounted on the angle adjustment mechanism connecting plate 16 and the fixed cylinder 17. The acquired parameters include the pitch angle of the first composite welding head 13. Roll angle The pitch angle of the second composite welding head Roll angle The relative angle between the two beams Spatial coordinates of lifting platform 12 angular change rate Its sensor sampling frequency Angle measurement accuracy , Coordinate measurement accuracy , , Attitude data is preprocessed using the sensor's built-in Kalman filter algorithm. The filtering formula is as follows: ,in Let A be the optimal estimate at time k, and B be the state transition matrix and the control matrix. To control the input, For Kalman gain, This is the observation value at time k;

[0054] Workpiece welding status data acquisition: A combination sensor (infrared thermometer + high-speed vision camera) mounted on the side of the support component's placement area collects welding area status parameters, including the molten pool temperature. molten pool area Molten pool depth weld width Scope of the heat-affected zone Unfused area Number of pores Crack length Infrared thermometer measurement range Temperature measurement accuracy High-speed visual camera frame rate resolution Pixels are used to extract the molten pool contour using an image grayscale thresholding algorithm. The contour extraction formula is as follows: ,in For binary masking, The grayscale value of the image pixels. A preset grayscale threshold is set (which can be calculated using the maximum inter-class variance method), and then the pixel coordinate transformation formula is used. Calculate the area of ​​the molten pool, where The pixel area coefficient. This represents the number of pixels in the molten pool region.

[0055] Environmental parameter data acquisition: Welding environmental parameters are collected using environmental sensors installed on the support components. These parameters include ambient temperature. Ambient humidity Ambient air pressure Measurement range: , , Measurement accuracy: , , sampling frequency The data is transmitted to the data acquisition module via the I2C bus;

[0056] The data analysis module, electrically connected to the data acquisition module, includes a data preprocessing unit, a feature extraction unit, a state assessment unit, and a dual-beam composite fusion unit.

[0057] The data preprocessing unit performs standardization processing on the collected data, which includes data denoising, outlier removal, and data normalization transformation. The specific processing is as follows:

[0058] Data denoising: A 4-wavelet transform denoising algorithm is used, with the following steps:

[0059] Wavelet decomposition: for the original data sequence , Perform a 3-level wavelet decomposition on the data (within the specified length) to obtain approximate coefficients. (Low-frequency components) and detail coefficients (High-frequency noise component), decomposition formula is as follows ;

[0060] Thresholding: A soft thresholding function is used to process the detail coefficients. The calculation formula is ,in The standard deviation of noise. The median function is used; the soft thresholding formula is... ( (Number of detail coefficient layers);

[0061] Inverse wavelet transform: Based on processed approximation coefficients With detail coefficient The inverse transformation formula for reconstructing data is: ,in This is the db4 wavelet inverse transform operator. This is the denoised data sequence;

[0062] Outlier removal: A combined algorithm of the 3σ criterion and the Grubbs criterion is used, with the following steps: Calculate the denoised data sequence. mean with standard deviation The formula is , ; 3σ preliminary screening: if data points satisfy These are marked as suspected outliers; Grubbs Validation: Calculate the Grubbs statistic for suspected outliers. ,like , The mean is determined by the Grubbs' threshold value, identified as an outlier by querying the Grubbs' distribution table, and then removed. Iterative correction: After removing outliers, the mean is recalculated. with standard deviation Repeat steps 2-3 until no outliers are found, resulting in a sequence of data without outliers. ;

[0063] Data normalization transformation: The corresponding normalization algorithm is adopted according to the data characteristics: Non-positive and non-negative characteristic data (power, temperature, area, etc.): Linear normalization is used to map to the [0,1] interval, the formula is as follows: ,in The minimum value in the sequence. The maximum value of the sequence; positive and negative characteristic data (wavelength offset, angle deviation, etc.): normalized using standard deviation, formula is: ,in The mean of a data sequence without outliers. The standard deviation of the data sequence without outliers is given. After normalization, the mean of the data is 0 and the standard deviation is 1.

[0064] The feature extraction unit extracts key features from standardized data, specifically:

[0065] Defined as the degree of fluctuation in laser power per unit time, it is calculated using the coefficient of variation method, and the formula is: ,in, The standard deviation of the power series. Let M be the mean of the power sequence, and M be the number of sampling points per unit time. As a characteristic of power stability;

[0066] Defined as the difference between the real-time wavelength and the standard wavelength, the formula is: ,in For normalized real-time wavelength data, The standard wavelength of the laser; As a characteristic of wavelength offset;

[0067] Identify the pulse repetition frequency of the first and second composite welding joints Pulse width of the two welded joints Calculate the pulse frequency ratio respectively Ratio of pulse width The formula is , ; compare the pulse frequency Ratio of pulse width As a characteristic of pulse coordination;

[0068] Identifying the beam quality factor of two laser beams Calculate the mean beam quality factor respectively With fluctuation range The formula is , ;in , ; Average beam quality factor With fluctuation range As a characteristic of beam quality;

[0069] Power stability characteristics Wavelength offset characteristics Pulse coordination characteristics and beam quality characteristics are denoted as beam parameter characteristics;

[0070] Identify the pitch angle of the two welded joints Calculate the real-time relative angles respectively With the rate of change of the included angle The formula is , ;in The difference in angle between adjacent sampling times. The sampling interval is the real-time relative angle. With the rate of change of the included angle As a relative angular feature;

[0071] Identify the spatial coordinates of the lifting seat 12 Calculate coordinate deviation Spatial deviation The formula is , , , ;in For the real-time coordinates of the lifting platform, For the target coordinates; adjust the coordinate deviation. Spatial deviation As a feature of positional accuracy;

[0072] Defined as the fluctuation range of the roll angle per unit time, the formula is: ,in This represents the maximum roll angle of the two welded joints per unit time. The minimum roll angle of the two welded joints per unit time; the fluctuation range of the roll angle. As a characteristic of attitude stability;

[0073] The relative angle features, position accuracy features, and attitude stability features are denoted as attitude features;

[0074] Identify the molten pool temperature sequence in the welding area With the length of the molten pool Calculate the peak temperature Average temperature Temperature gradient The formula is , , ; Peak temperature Average temperature Temperature gradient As a characteristic of the molten pool temperature;

[0075] Identify the sequence of molten pool area, depth, and weld width in the welding area. Calculate the average area of ​​the molten pool Mean depth of molten pool Average weld width With area change rate The formula is , , , ; Average the area of ​​the molten pool Mean depth of molten pool Average weld width With area change rate This is denoted as the geometric feature of the molten pool;

[0076] Identify the total area of ​​the welding zone ,volume Calculate the proportion of unfused area based on the length of each crack. Pore ​​number density With crack length The formula is ;in, The length of the i-th crack is represented by the formula for calculating its volume. , For workpiece thickness; the proportion of unfused area. Pore ​​number density With crack length As a defect feature;

[0077] The molten pool temperature characteristics, molten pool geometric characteristics, and defect characteristics are recorded as workpiece state characteristics;

[0078] Define the range of change in ambient temperature per unit time. The formula is ,in , These represent the maximum and minimum ambient temperatures per unit time, respectively; the range of change... This is denoted as a temperature fluctuation characteristic;

[0079] Set standard welding environment humidity Identify the current welding environment humidity Calculate humidity deviation With humidity change rate The formula is , ; humidity deviation With humidity change rate This is recorded as a characteristic affected by humidity;

[0080] Identify the standard deviation of the ambient air pressure sequence per unit time. With the mean of the air pressure series Define the fluctuation coefficient of ambient air pressure per unit time. The formula is ; to increase the volatility coefficient As a characteristic of air pressure stability;

[0081] Temperature fluctuation characteristics, humidity influence characteristics, and air pressure stability characteristics are denoted as environmental characteristics.

[0082] The condition assessment unit determines the welding condition based on key characteristic quantities. The specific steps are as follows:

[0083] A three-tiered indicator system is established, with the first-level indicator being the overall welding condition (S), and the second-level indicators including beam coordination condition. Posture adaptation state Workpiece forming state Environmental adaptation status Secondary indicator weights satisfy Third-level indicator weights satisfy (m represents the number of tertiary indicators under the i-th secondary indicator);

[0084] The weights at each level are determined using the Analytic Hierarchy Process (AHP). The steps are as follows:

[0085] Construct a 4×4 judgment matrix for the secondary indicators. For each secondary indicator, construct an m×m judgment matrix for the tertiary indicators. ,in To represent the importance of the i-th indicator relative to the j-th indicator, a 1-9 scale is used (1 = equally important, 3 = slightly important, 5 = significantly important, 7 = strongly important, 9 = extremely important, with 2, 4, 6, and 8 being intermediate values), and the following conditions are met: ;

[0086] Then perform a consistency check and calculate the largest eigenvalue of the judgment matrix. Consistency indicators (n is the order of the judgment matrix), random consistency ratio (RI is the average random consistency index, which can be found in the AHP standard table.) If CR < 0.1, the matrix is ​​considered to be consistent; otherwise, the matrix is ​​adjusted until CR < 0.1.

[0087] After normalizing the judgment matrix, the weight formula is as follows: , where k 1 is the row index of the judgment matrix, representing the k 1-th element whose weight is to be calculated;

[0088] The evaluation is performed using a fuzzy comprehensive evaluation algorithm, specifically including:

[0089] Establish evaluation levels: The evaluation level set V={A,B,C,D} corresponds to "Excellent, Good, Satisfactory, Unsatisfactory";

[0090] Constructing a fuzzy evaluation matrix: For the i-th secondary indicator, establish a fuzzy evaluation matrix for the tertiary indicators. ,in Let be the membership degree of the j-th tertiary indicator to the k2-th evaluation level;

[0091] Membership degree calculation: Using the triangular membership function, taking the third-level index x as an example:

[0092] Excellent (A):

[0093] Good (B):

[0094] Pass (C):

[0095] Unacceptable (D): ;

[0096] in The threshold for evaluating the indicator can be specifically calibrated through process experiments;

[0097] Secondary indicator evaluation: ,get ;in This is fuzzy matrix multiplication;

[0098] Evaluation of primary indicators: ,get ;

[0099] State determination: The maximum membership principle is used; if... Then the welding condition corresponds to the k2th evaluation level;

[0100] The dual-beam composite fusion unit establishes a mapping relationship between key feature quantities and welding effects through a preset fusion algorithm, and calculates the optimal control parameters. The specific steps are as follows:

[0101] Constructing the decision matrix: Let the number of key features be m and the number of samples be n, construct the decision matrix. ,in The normalized value of the j-th sample for the i-th feature;

[0102] Calculating objective weights using the entropy weight method ,include:

[0103] Calculate the proportion of characteristic quantities: ,like ,but Avoid logarithmic inconsistencies;

[0104] Calculate the entropy value of the feature: ,in Entropy coefficient

[0105] Calculate the coefficient of difference: This indicates that the smaller the entropy value, the larger the difference coefficient, and the higher the feature importance;

[0106] Objective weight normalization: ,satisfy ;

[0107] Then use AHP to calculate subjective weights. The above steps of the Analytic Hierarchy Process (AHP) determine the weights for each level, resulting in subjective weights. ,satisfy ;

[0108] An improved BP neural network combined with particle swarm optimization (PSO) algorithm is used to construct an effect prediction model. The specific steps are as follows:

[0109] Model input / output design:

[0110] Input layer: weighted feature vectors ,in The real-time normalized value of the i-th feature is the number of input layer nodes. ;

[0111] Output layer: Welding effect vector ,in To ensure the weld strength meets the standard, To improve the weld formation qualification rate, The welding defect rate is represented by the number of nodes in the output layer. ;

[0112] Hidden layer design: Number of hidden layer nodes (c=5 is an empirical constant), the activation function is the Sigmoid function. ;

[0113] BP neural network training:

[0114] Sample set construction: data collection The feature data and corresponding welding effect data under different parameter combinations are divided into training set and test set according to a preset ratio;

[0115] Initialization: Randomly initialize the input layer and hidden layer weights. Hidden layer-output layer weights Hidden layer threshold Output layer threshold The initial learning rate η = 0.05;

[0116] Forward propagation includes:

[0117] Hidden layer output: ;

[0118] Output layer predictions: ;

[0119] Error calculation: Mean square error is used. ,in The target value for the output layer;

[0120] Backpropagation: Parameters are updated using gradient descent.

[0121] ;

[0122] ;

[0123] Iteration terminates: when Or stop training when the preset number of iterations is reached;

[0124] PSO screening for optimal control parameters:

[0125] Control parameter space: ,in Energy distribution ratio ( ), The relative angle between the two beams ( ), Let z be the movement speed, and z be the height along the Z-axis.

[0126] Optimize the objective function: ,in , , The target weight;

[0127] PSO Iterative Solution: Initialize the particle swarm positions and velocities, and iteratively update the particle positions using the fitness function J until convergence is achieved to obtain the optimal control parameters. ;

[0128] The fusion algorithm process is as follows: Data acquisition → Preprocessing → Feature extraction → Combined weight calculation → Weighted feature input to BP model → Welding effect prediction → PSO optimization objective function → Output of optimal control parameters;

[0129] The control execution module, electrically connected to both the data analysis module and the main hardware unit, receives optimal control parameters and drives the three-axis movement mechanism, angle adjustment mechanism, and dual composite welding head to perform corresponding actions. Specifically, it includes:

[0130] The motion control unit is used to electrically connect to the linear motor 6, the first servo motor 9, and the second servo motor 11, and to receive optimal control parameters. To achieve precise three-dimensional position control:

[0131] Position command conversion: Converts the target position into a motor pulse command, using the following formula: ;in , , For pulse equivalents on each axis, , , Current position;

[0132] Speed ​​control: Employs a trapezoidal acceleration / deceleration algorithm, including:

[0133] Acceleration phase: ,in The initial velocity, For acceleration, To speed up the process, To increase distance;

[0134] Uniform speed phase: ,in For uniform motion;

[0135] Deceleration phase: ;

[0136] PID closed-loop control: corrects position deviation, the formula is as follows ,in To control the output, This is the proportionality coefficient. The integral coefficient is... These are the differential coefficients. For real-time position deviation, The attitude sensor provides feedback on the position;

[0137] The beam parameter control unit is electrically connected to the first composite welding head 13 and the second composite welding head, receives the optimal control parameter k*, and realizes energy distribution and parameter adjustment.

[0138] Power distribution calculation: ,in This represents the total welding power (process setting value). These are the target power values ​​for the two welding joints, respectively.

[0139] Parameter Coordination: Wavelength adjustment is achieved by controlling the temperature of the laser generator resonant cavity.

[0140] To achieve this, the formula is: ,in As the reference wavelength, For temperature coefficient, The reference temperature is used; pulse parameter adjustment is achieved by controlling the drive power supply pulse signal, pulse width... The repetition frequency f is directly proportional to the high-level time of the drive signal, and inversely proportional to the signal period.

[0141] Feedback calibration: Real-time acquisition of laser parameter sensors ,like Then, it is corrected through proportional control: Continue until the deviation meets the requirements;

[0142] The angle adjustment control unit is electrically connected to the third servo motor 14 and the fourth servo motor 15 to receive optimal control parameters. To achieve precise angle adjustment:

[0143] Angle breakdown: ,in For the fourth servo motor 15, coarse angle adjustment ( ), For the third servo motor 14, fine-tune the angle ( );

[0144] Coarse adjustment control: number of pulse commands ,in Angle pulse equivalent, closed-loop control deviation ;

[0145] Fine-tuning control: PID control is used to fine-tune the deviation. ;

[0146] Collaborative verification: Attitude sensor acquires actual relative angles ,like If the adjustment is complete, then repeat the fine-tuning steps; otherwise, repeat the steps.

[0147] In this application, the support component includes a base plate 2 and a support structure. The support structure is a support foot installed at the bottom of the base plate 2. The support column 1 is fixed to the upper end of the base plate 2. The top of the support component is fixed to the support component through the support column 1.

[0148] In this application, the three-axis moving mechanism includes an X-axis moving unit, a Y-axis moving unit, and a Z-axis moving unit. The X-axis moving unit is mounted on the support assembly, the Y-axis moving unit is assembled on the actuator end of the X-axis moving unit, the Z-axis moving unit is assembled on the actuator end of the Y-axis moving unit, and the angle adjustment mechanism is assembled on the actuator end of the Z-axis moving unit.

[0149] The X-axis moving unit includes a positioning cylinder 5, a linear motor 6, and a moving seat 7. The positioning cylinder 5 is fixed to one side of the upper end of the support plate 3. The linear motor 6 is installed on the support plate 3 inside the positioning cylinder 5. The moving seat 7 is slidably installed on the linear motor 6.

[0150] The Y-axis moving unit includes a first moving block 8, a first servo motor 9, a second moving block 10, and a first bolt 18. The first moving block 8 is fixedly installed on the upper end of the moving base 7. The first bolt 18 is rotatably installed on the inner side of the first moving block 8. The first servo motor 9 is installed on one end of the first moving block 8, and its output end passes through the first moving block 8 and is coaxially fixed to one end of the first bolt 18. The second moving block 10 is threadedly sleeved on the first bolt 18.

[0151] The Z-axis moving unit includes a second servo motor 11, a lifting seat 12, and a second bolt 19. The second bolt 19 is rotatably installed in the lifting groove of the second moving block 10. The second servo motor 11 is installed on the top of the second moving block 10, and its output end passes through the second moving block 10 and is coaxially fixed to the top of the second bolt 19. The lifting seat 12 is threadedly sleeved on the second bolt 19.

[0152] In this application, the angle adjustment mechanism includes a positioning frame, a driving component, a transmission component, and a fixing component. The positioning frame is fixedly connected to the lifting seat 12 of the Z-axis moving unit. The first composite welding head 13 is installed on one side of the positioning frame. The transmission component is rotatably connected to the positioning frame. The fixing component is hinged to one end of the transmission component. The second composite welding head is assembled inside the fixing component.

[0153] The driving components include a first driving component and a second driving component. The first driving component is a fourth servo motor 15, which is installed inside the positioning frame. Its output end is connected to the transmission component through a snap-fit ​​plate, driving the fixing component to coarsely adjust the angle of the second composite welding head. The second driving component is a third servo motor 14, which is installed on the transmission component. Its output end is fixedly connected to the fixing component, driving the second composite welding head to finely adjust the angle. The transmission component is a connecting plate 16, which is symmetrically rotated and installed on the lifting seats 12 at both ends of the first composite welding head 13. The fixing component is a fixing cylinder 17, which is hinged between the other ends of the connecting plate 16. The second composite welding head is assembled inside the fixing cylinder 17.

[0154] In this application, the data acquisition module includes a laser parameter sensor, an attitude sensor, a status sensor, and an environmental sensor; the laser parameter sensor is mounted on the second composite welding head inside the first composite welding head 13 and the fixed cylinder 17, the attitude sensor is mounted on the connecting plate 16 of the angle adjustment mechanism and the fixed cylinder 17, the status sensor is mounted on the side of the placement area of ​​the support component, and the environmental sensor is installed on the support component.

[0155] In this application, the standardization processing of the data preprocessing unit includes data denoising, outlier removal, and data normalization transformation.

[0156] In this application, the key features extracted by the feature extraction unit include beam parameter features, attitude features, workpiece state features, and environmental features.

[0157] In this application, the fusion algorithm of the dual-beam composite fusion unit includes a weight allocation model and an effect prediction model. The weight allocation model is used to assign weight coefficients to each key feature quantity, and the effect prediction model is used to predict the welding effect and select the optimal control parameters based on the weighted feature quantities.

[0158] In this application, the control execution module includes a motion control unit, a beam parameter control unit, and an angle adjustment control unit; the motion control unit is electrically connected to the linear motor 6, the first servo motor 9, and the second servo motor 11 of the three-axis moving mechanism; the beam parameter control unit is electrically connected to the first composite welding head 13 and the second composite welding head; and the angle adjustment control unit is electrically connected to the third servo motor 14 and the fourth servo motor 15 of the angle adjustment mechanism.

[0159] Other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of the invention are indicated by the following claims.

[0160] It should be understood that the present invention is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A dual-beam hybrid laser welding apparatus, characterized by comprising: Including hardware body and double light beam composite control system;The hardware body includes: Supporting assembly for providing overall support for the device; Support assembly fixedly connected to the top end of the supporting assembly, the support assembly is a support plate (3), the surface of the support plate (3) is provided with a placing area for placing a workpiece, and a welding placing plate (4) is arranged in the placing area; Three-axis moving mechanism installed on one side of the support assembly for realizing position adjustment in three-dimensional space; Angle adjusting mechanism assembled at the execution end of the three-axis moving mechanism for adjusting the relative angle and space posture of the double light beams; Double composite welding head including a first composite welding head (13) and a second composite welding head, which are respectively assembled at corresponding positions of the angle adjusting mechanism; The double light beam composite control system includes: Data acquisition module for acquiring double light beam parameter data, space posture data, workpiece welding state data and environmental parameter data; Data analysis module including data preprocessing unit, feature extraction unit, state evaluation unit and double light beam composite fusion unit;The data preprocessing unit standardizes the collected data;The feature extraction unit extracts key feature quantities from the standardized data;The state evaluation unit judges the welding state based on the key feature quantities;The double light beam composite fusion unit establishes the mapping relationship between the key feature quantities and the welding effect through a preset fusion algorithm, and calculates the optimal control parameters; Control execution module for receiving optimal control parameters, driving three-axis moving mechanism, angle adjusting mechanism and double composite welding head to execute corresponding actions.

2. The dual-beam hybrid laser welding apparatus of claim 1, wherein, The supporting assembly includes a bottom plate (2) and a support structure, the support structure is a support leg installed at the bottom of the bottom plate (2), a support column (1) is fixedly connected to the upper end of the bottom plate (2), and the top end of the supporting assembly is fixedly connected with the support assembly through the support column (1).

3. The dual beam hybrid laser welding apparatus of claim 1, wherein, The three-axis moving mechanism includes an X-axis moving unit, a Y-axis moving unit and a Z-axis moving unit, the X-axis moving unit is installed on the support assembly, the Y-axis moving unit is assembled at the execution end of the X-axis moving unit, the Z-axis moving unit is assembled at the execution end of the Y-axis moving unit, and the angle adjusting mechanism is assembled at the execution end of the Z-axis moving unit; The X-axis moving unit includes a positioning cylinder (5), a linear motor (6) and a moving seat (7), the positioning cylinder (5) is fixedly connected to one side of the upper end of the support plate (3), the linear motor (6) is installed on the support plate (3) in the positioning cylinder (5), and the moving seat (7) is slidingly installed on the linear motor (6); The Y-axis moving unit includes a first moving block (8), a first servo motor (9), a second moving block (10) and a first bolt (18), the first moving block (8) is fixedly installed on the upper end of the moving seat (7), the first bolt (18) is rotatably installed on the inner side of the first moving block (8), the first servo motor (9) is installed on one end of the first moving block (8), the output end of the first servo motor (9) is coaxially fixedly connected with one end of the first bolt (18) penetrating through the first moving block (8), and the second moving block (10) is threadedly connected and sleeved on the first bolt (18). The Z-axis moving unit comprises a second servo motor (11), a lifting seat (12) and a second screw (19), the second screw (19) is rotatably installed in a lifting groove of the second moving block (10), the second servo motor (11) is installed at the top end of the second moving block (10), the output end of the second servo motor (11) penetrates the second moving block (10) and is coaxially fixed to the top end of the second screw (19), and the lifting seat (12) is threadedly connected to the second screw (19).

4. The dual beam hybrid laser welding apparatus of claim 1, wherein, The angle adjusting mechanism comprises a positioning frame, a driving component, a transmission component and a fixing component, the positioning frame is fixed to the lifting seat (12) of the Z-axis moving unit, the first composite welding head (13) is installed on one side of the positioning frame, the transmission component is rotatably connected to the positioning frame, the fixing component is hingedly connected to one end of the transmission component, and the second composite welding head is assembled on the inner side of the fixing component. The driving component comprises a first driving component and a second driving component, the first driving component is a fourth servo motor (15) installed on the inner side of the positioning frame, the output end of the fourth servo motor (15) is clamped to the transmission component through a clamping plate, the fourth servo motor (15) drives the fixing component to drive the second composite welding head to perform angle coarse adjustment, and the second driving component is a third servo motor (14) installed on the transmission component, the output end of the third servo motor (14) is fixed to the fixing component, and the third servo motor (14) drives the second composite welding head to perform angle fine adjustment.

5. The dual beam hybrid laser welding apparatus of claim 1, wherein, The data acquisition module comprises a laser parameter sensor, a posture sensor, a state sensor and an environment sensor, the laser parameter sensor is assembled on the second composite welding head on the inner side of the first composite welding head (13) and the fixing cylinder (17), the posture sensor is assembled on the connecting plate (16) and the fixing cylinder (17) of the angle adjusting mechanism, the state sensor is assembled on the side of the storage area of the supporting assembly, and the environment sensor is installed on the supporting assembly.

6. The dual beam hybrid laser welding apparatus of claim 1, wherein, The standardization processing of the data preprocessing unit comprises data denoising, abnormal value elimination and data normalization conversion.

7. The dual beam hybrid laser welding apparatus of claim 1, wherein, The key feature quantity extracted by the feature extraction unit comprises a light beam parameter feature, a posture feature, a workpiece state feature and an environment feature.

8. The dual beam hybrid laser welding apparatus of claim 1, wherein, The fusion algorithm of the double-beam composite fusion unit comprises a weight distribution model and an effect prediction model, the weight distribution model is used for distributing weight coefficients to the key feature quantities, and the effect prediction model is used for predicting the welding effect based on the weighted feature quantities and screening the optimal control parameters.

9. The dual beam hybrid laser welding apparatus of claim 1, wherein, The control execution module comprises a motion control unit, a light beam parameter control unit and an angle adjusting control unit, the motion control unit is electrically connected with the linear motor (6), the first servo motor (9) and the second servo motor (11) of the three-axis moving mechanism, the light beam parameter control unit is electrically connected with the first composite welding head (13) and the second composite welding head, and the angle adjusting control unit is electrically connected with the third servo motor (14) and the fourth servo motor (15) of the angle adjusting mechanism.

Images