Method for efficiently cutting vacuum brazing soldering lug

Abstract

The invention relates to the technical field of material processing control, and discloses a method for efficiently cutting a vacuum brazing soldering lug. The method comprises the following steps: firstly, receiving material parameters and target geometrical shape data of a to-be-cut soldering lug, and generating and optimizing an initial cutting track based on a preset algorithm; in combination with real-time temperature field monitoring data, thermal stress distribution is calculated through a finite element analysis method, and the cutting speed and laser power parameters are dynamically adjusted; and then the cutting precision and the equipment energy consumption are synchronously optimized through a multi-objective optimization algorithm, and final cutting parameters are output to a vacuum brazing control system. In addition, signals are collected in real time during cutting to recognize abnormity, and algorithm weights are calibrated by comparing geometric parameters after cutting. The cutting precision and efficiency can be effectively improved, equipment energy consumption is reduced, cutting abnormity is treated in time, self-optimization of the cutting process is achieved, and the method is suitable for the production field with the high requirement for vacuum brazing piece cutting.

Description

Technical Field

[0001] The invention relates to the technical field of material processing control, in particular to a method for efficiently cutting a vacuum brazing sheet. Background Art

[0002] In modern manufacturing, the cutting process for vacuum brazing sheets plays a vital role in numerous fields, such as aerospace and electronic equipment manufacturing. With the rapid development of related industries, the requirements for cutting precision, efficiency, and quality of vacuum brazing sheets are becoming increasingly stringent, and traditional cutting methods are gradually exposing many difficult-to-overcome problems.

[0003] Early manual cutting methods relied entirely on the worker's experience and skill. Not only was cutting efficiency extremely low, but also precision was difficult to guarantee due to the instability of manual operation. With the increasing demand for mass production, manual cutting could no longer keep up with the pace of large-scale production, resulting in high production costs and inconsistent product quality, making it difficult to adapt to the development needs of modern industry.

[0004] The advent of mechanical cutting technology has improved cutting efficiency to a certain extent, but its limitations are also very obvious when dealing with materials such as vacuum brazing pads, which require extremely high precision. The mechanical cutting process generates large mechanical stresses, which can easily cause the pads to deform and affect the subsequent welding quality. Moreover, mechanical cutting tools will wear during the cutting process. This not only requires frequent tool replacement, increasing production costs and downtime, but also causes a gradual decline in cutting accuracy due to tool wear, making it difficult to consistently produce high-precision products.

[0005] The rise of laser cutting technology has brought new ideas to the cutting of vacuum brazing pads. However, existing laser cutting methods still have many problems in practical applications. On the one hand, there is a lack of effective algorithms for cutting path planning, and most methods use relatively simple path planning methods without fully considering the geometric shape and material properties of the pads. This results in the cutting path being suboptimal, which not only wastes cutting time, but also increases equipment energy consumption and reduces production efficiency. On the other hand, during the cutting process, due to the inability to monitor and control thermal stress in real time, the pads are prone to defects such as cracks and delamination due to concentrated thermal stress. The parameter settings of laser power and cutting speed often rely on experience and lack scientific dynamic adjustment methods. It is difficult to accurately control according to the real-time status of the pads, which seriously affects the cutting quality and yield of the pads.

[0006] Furthermore, existing cutting processes also have shortcomings in terms of quality inspection and exception handling. After cutting, there is a lack of efficient and accurate inspection methods to comprehensively evaluate the quality of the solder pads, making it impossible to promptly detect minor defects and shape errors. Once cutting anomalies occur, there is no comprehensive response mechanism, often resulting in the scrapping of entire batches of products and huge economic losses. In summary, existing vacuum brazing pad cutting technology has many problems in terms of accuracy, efficiency, quality control, and exception handling. An innovative cutting method is urgently needed to address these challenges and meet the ever-evolving needs of modern manufacturing. Summary of the Invention

[0007] The object of the present invention is to provide a method for efficiently cutting vacuum brazing sheets to solve the problems raised in the above background technology.

[0008] To achieve the above object, the present invention provides the following technical solution: a method for efficiently cutting vacuum brazing sheets, the method comprising: Receiving material parameters and target geometry data of the welding piece to be cut, wherein the material parameters include melting point, thermal conductivity and thickness distribution; Based on a preset cutting path generation algorithm, an initial cutting trajectory is generated according to the target geometric shape data, and the trajectory is segmented and optimized; Combined with real-time temperature field monitoring data, the thermal stress distribution during the soldering process is calculated using finite element analysis; According to the thermal stress distribution, the cutting speed and laser power parameters are dynamically adjusted to generate adaptive control instructions; Based on a multi-objective optimization algorithm, cutting accuracy and equipment energy consumption are simultaneously optimized, and the final cutting parameters are output to the vacuum brazing control system.

[0009] Preferably, the steps of constructing the cutting path generation algorithm include: Collect historical cutting trajectory data and cutting quality scores to build a training data set; Performing path optimization on the training data set by using a genetic algorithm to generate a set of candidate trajectories; Using a Bayesian optimization algorithm to select the optimal segmentation points in the candidate trajectory set; The segment point coordinates are combined with the cutting head kinematic model to generate the smooth initial cutting trajectory.

[0010] Preferably, the execution of the finite element analysis method includes: Establish a three-dimensional heat conduction model of the solder joint, divide the mesh nodes and set boundary conditions; Calculate the temperature gradient and thermal expansion coefficient of each node based on real-time temperature field data; Combined with the material elastic modulus, the thermal stress tensor equation is solved and the thermal stress distribution diagram is output; Wherein, the thermal stress tensor equation is: Where, Represents the stress component of the solder joint in the (i, j) direction in the three-dimensional coordinate system, is the elastic modulus, represents the strain component of the solder joint in the (i, j) direction, is the coefficient of thermal expansion, is the temperature change, is the Kronecker function.

[0011] Preferably, the dynamic adjustment of cutting speed and laser power parameters includes: Based on the thermal stress distribution map, stress concentration areas are identified and marked as high-risk areas; Assign a deceleration factor to the high-risk area and optimize the laser power attenuation curve based on the gradient descent method; The optimized parameters are input into the pulse width modulation module to generate the adaptive control instructions.

[0012] Preferably, the execution of the multi-objective optimization algorithm includes: Define the cutting accuracy objective function and energy consumption constraint function, and construct the Pareto frontier model; The cutting speed, power and path parameters are jointly optimized using a non-dominated sorting genetic algorithm; In each iteration, the elite retention strategy is adopted to update the candidate solution set until the convergence condition is met.

[0013] Preferably, the screening step of the Bayesian optimization algorithm includes: Construct a response surface model of cutting quality and segmentation point location; Calculate the expected improvement value of each candidate trajectory through Gaussian process regression; The segmentation point with the largest expected improvement value is selected as the optimal segmentation point.

[0014] Preferably, the method further comprises: Real-time collection of acoustic emission signals and vibration spectrum data during the cutting process; Extract signal features through wavelet transform and identify abnormal cutting events; If an anomaly is detected, the emergency stop protocol is triggered and the cutting path is replanned.

[0015] Preferably, the setting of the energy consumption constraint function includes: Establish the energy consumption relationship model between laser power and cutting speed; Calculate the dynamic energy consumption threshold based on the equipment's rated power and heat dissipation efficiency; The dynamic energy consumption threshold is used as a hard constraint condition of the Pareto frontier model.

[0016] Preferably, the execution of the emergency shutdown protocol includes: Select local pause or global shutdown mode according to the abnormal event level; In local pause mode, redundant paths are used to bypass abnormal areas; In global stop mode, reset cutting parameters and start the self-test procedure.

[0017] Preferably, the method further comprises: After cutting is completed, the actual geometric parameters of the welding piece are obtained through an optical scanner; Compare the actual geometric parameters with the target geometric shape data and calculate the shape error matrix; According to the shape error matrix, the segment optimization weights in the cutting path generation algorithm are reversely calibrated.

[0018] Compared with the prior art, the present invention has the following beneficial effects: In terms of cutting accuracy, by receiving the material parameters and target geometry data of the solder piece to be cut, generating an initial cutting trajectory based on a preset algorithm and performing segmented optimization, the system can accurately plan the cutting path to closely match the target shape of the solder piece. Furthermore, after cutting, the optical scanner obtains the actual geometric parameters of the solder piece, compares them with the target data to calculate the shape error matrix, and reversely calibrates the segmented optimization weights in the cutting path generation algorithm, forming a closed-loop feedback optimization mechanism. This greatly improves cutting accuracy and effectively reduces the product rejection rate due to insufficient cutting accuracy. For high-precision applications in electronics, aerospace, and other fields, it can significantly improve product quality and performance stability.

[0019] To control thermal stress, finite element analysis is used to calculate the thermal stress distribution during solder cutting, combined with real-time temperature field monitoring data. Cutting speed and laser power parameters are dynamically adjusted based on the thermal stress distribution. For example, areas of stress concentration are identified and marked as high-risk areas, where speed reduction factors are assigned and the laser power attenuation curve is optimized. This precisely controls heat input during the cutting process, effectively reducing thermal stress and preventing defects such as cracks and deformation in the solder due to excessive thermal stress. This significantly improves solder yield, ensures product quality, and reduces production costs.

[0020] Regarding equipment energy consumption, a multi-objective optimization algorithm is used to simultaneously optimize cutting accuracy and equipment energy consumption. A cutting accuracy objective function and an energy consumption constraint function are defined, a Pareto frontier model is constructed, and a non-dominated sorting genetic algorithm is used to jointly optimize cutting speed, power, and path parameters. This ensures that equipment energy consumption is rationally configured while ensuring cutting accuracy. Dynamic energy consumption thresholds are calculated based on the equipment's rated power and heat dissipation efficiency and used as constraints, effectively avoiding energy waste, reducing the company's production and operating costs, and improving energy efficiency, all in line with the concept of sustainable development.

[0021] The adaptability and stability of the cutting process have also been enhanced. Acoustic emission signals and vibration spectrum data are collected in real time during the cutting process, and wavelet transforms are used to extract signal features and identify cutting anomalies. Once an anomaly is detected, an emergency shutdown protocol is quickly triggered and the cutting path is replanned, ensuring a safe and reliable cutting process. Furthermore, this method can flexibly adjust cutting parameters and path planning based on the material parameters (melting point, thermal conductivity, thickness distribution, etc.) and target geometry data of the different solder pads. This method is highly versatile and adaptable, capable of adapting to the cutting needs of solder pads of various complex shapes and materials.

[0022] Cutting efficiency has also been significantly improved. A pre-set cutting path generation algorithm builds a training dataset by collecting historical cutting trajectory data and cutting quality scores. It then utilizes genetic algorithms and Bayesian optimization algorithms to generate a smooth initial cutting trajectory, reducing ineffective motion and energy loss during the cutting process. During the cutting process, cutting parameters are adjusted in real time based on thermal stress distribution, avoiding interruptions and rework caused by improper parameters. This improves cutting efficiency overall, shortens production cycles, and enhances the company's market competitiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 This is a working principle diagram of the high-efficiency cutting vacuum brazing welding sheet of the present invention; Figure 2 Flowchart for dynamically adjusting cutting parameters; Figure 3 Flowchart for the execution of multi-objective optimization algorithm; Figure 4 FIG. 4 is a flowchart of the execution of the emergency shutdown protocol. DETAILED DESCRIPTION

[0024] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0025] See also Figure 1-Figure 4 The present invention provides a method for efficiently cutting vacuum brazing sheets, aiming to effectively manage urban waste recycling and improve resource utilization efficiency. The specific implementation steps are as follows: Receive the material parameters and target geometry data of the solder piece to be cut. Material parameters include key information such as melting point, thermal conductivity, and thickness distribution, which are crucial for planning and controlling the subsequent cutting process. The target geometry data specifies the desired final shape of the solder piece.

[0026] Based on the preset cutting path generation algorithm, the initial cutting trajectory is generated according to the target geometry data. Subsequently, the generated trajectory is segmented and optimized to improve cutting efficiency and quality.

[0027] Finite element analysis is used to calculate the thermal stress distribution during the solder cutting process, combined with real-time temperature field monitoring data. This precise calculation of the thermal stress distribution allows for early identification of potential stress issues during the cutting process, providing a basis for subsequent adjustment of cutting parameters.

[0028] Based on the calculated thermal stress distribution, the cutting speed and laser power parameters are dynamically adjusted, and adaptive control instructions are generated. This step ensures that the cutting parameters are adjusted in real time according to the actual conditions of the solder joint during the cutting process, reducing the impact of thermal stress on the solder joint quality.

[0029] Based on a multi-objective optimization algorithm, cutting accuracy and equipment energy consumption are simultaneously optimized. The optimized final cutting parameters are output to the vacuum brazing control system, thus achieving efficient and accurate cutting of vacuum brazing welds.

[0030] The implementation of the present invention will be further described below with reference to Examples 1 to 6.

[0031] Example 1: The cutting path generation algorithm plays a key role in generating the initial cutting trajectory. The steps to build the algorithm are as follows: Historical cutting trajectory data and cut quality scores are collected to construct a training dataset. The historical cutting trajectory data contains information about the cutting head's motion path during previous cutting processes, while the cut quality score reflects the quality of the welds cut along the corresponding cutting trajectory. This data provides a rich sample for subsequent path optimization.

[0032] A genetic algorithm is used to optimize the paths in the training dataset and generate a set of candidate trajectories. A genetic algorithm is an optimization algorithm that simulates the natural evolutionary process. It iteratively optimizes individuals (i.e., cutting trajectories) by selecting, crossover, and mutation operations. This allows it to select the best candidate trajectories from a large number of possible trajectories and form the candidate trajectory set.

[0033] The Bayesian optimization algorithm is used to screen the optimal segmentation points in the candidate trajectory set. Specifically, a response surface model of cutting quality and segmentation point position is first constructed. Assuming that the cutting quality is , the segmentation point position is , the response surface model can be expressed as ,in It is a complex functional relationship obtained by fitting historical data. Through this model, a quantitative relationship between the segmentation point position and the cutting quality can be established.

[0034] The expected improvement value of each candidate trajectory is calculated by Gaussian process regression. Gaussian process regression is a probability-based regression method that can predict the improvement of cutting quality at different segmentation point positions while taking into account uncertainty. The calculation formula is: ,in It is the maximum cutting quality currently known. This formula means calculating the possible improvement of cutting quality compared to the current optimal value at different segmentation point positions.

[0035] The segmentation point with the greatest expected improvement is selected as the optimal segmentation point. Combining the coordinates of these optimal segmentation points with the cutting head kinematic model generates a smooth initial cutting trajectory. The cutting head kinematic model describes the motion of the cutting head in space. By substituting the segmentation point coordinates into this model, the cutting head's motion path during the actual cutting process can be determined, ensuring a smooth cutting trajectory, avoiding sudden changes during the cutting process, and improving cutting quality.

[0036] Example 2: When calculating the thermal stress distribution during the solder joint cutting process, the finite element analysis method is performed as follows: Establish a three-dimensional heat conduction model of the soldering pad. In this model, the soldering pad needs to be meshed and discretized into numerous mesh nodes, each with corresponding coordinate information. At the same time, boundary conditions are set, including the heat exchange between the soldering pad and the external environment, such as the heat convection coefficient and the ambient temperature. Assume that the heat convection coefficient is , the ambient temperature is , the solder surface temperature is , then the boundary condition of heat convection can be expressed as ,in is the thermal conductivity of the solder material, represents the derivative of temperature along the normal direction of the solder surface. This formula describes the transfer of heat between the solder surface and the external environment through thermal convection.

[0037] According to the real-time temperature field data, the temperature gradient and thermal expansion coefficient of each node are calculated. The temperature gradient represents the rate of change of temperature in space. Assuming that the temperature gradient in a certain direction is , which can be calculated from the temperature difference and distance between adjacent nodes. Thermal expansion coefficient It is an inherent property of the material. Different materials have different thermal expansion coefficients, which reflects the expansion or contraction characteristics of the material when the temperature changes.

[0038] Bonding material elastic modulus , solve the thermal stress tensor equation and output the thermal stress distribution diagram. The thermal stress tensor equation is: In this equation, It represents the stress component of the solder joint in the (i, j) direction in the three-dimensional coordinate system, which reflects the magnitude of the stress on the solder joint in this direction; is the elastic modulus, which reflects the material's ability to resist elastic deformation; It represents the strain component of the solder joint in the (i, j) direction, reflecting the degree of deformation of the solder joint in this direction; is the coefficient of thermal expansion; is the temperature change, that is, the difference between the current temperature and the initial temperature; is the Kronecker function, when hour, ,when hour, By solving this equation, the thermal stress distribution of the solder joint in various positions and directions can be obtained, providing an important basis for subsequent adjustment of cutting parameters.

[0039] Example 3: When dynamically adjusting the cutting speed and laser power parameters, the specific operations are as follows: Based on the thermal stress distribution diagram, stress concentration areas are identified and marked as high-risk zones. The thermal stress distribution diagram visually displays the stress distribution at different locations on the solder joint during the cutting process. By observing the thermal stress distribution diagram, areas with significantly higher stress values ​​than other areas are identified. These areas are stress concentration areas and are marked as high-risk areas. Improper cutting parameters in these areas can easily lead to quality problems such as cracks and deformation in the solder joint.

[0040] Assign a deceleration factor to the high-risk area. The deceleration factor is a coefficient less than 1. Assume that the deceleration factor is , which is used to reduce the moving speed of the cutting head in the high-risk area. For example, the original cutting speed is , cutting speed in high risk areas By reducing the cutting speed, the heat input can be reduced and the thermal stress can be reduced. At the same time, the laser power attenuation curve is optimized based on the gradient descent method. The laser power attenuation curve describes the change of laser power as the cutting head moves in the high-risk area. Assume that the laser power is , the cutting head position is , the laser power attenuation curve can be expressed as ( is the initial laser power, is the attenuation coefficient). Using the gradient descent method, the attenuation coefficient is continuously adjusted , which makes the change of laser power in high-risk areas more reasonable, ensuring the smooth progress of cutting and effectively reducing thermal stress.

[0041] The optimized parameters are input into the pulse width modulation module, generating adaptive control instructions. The module controls the cutting equipment by adjusting the pulse width based on the input cutting speed and laser power parameters. For example, when the cutting speed decreases, the pulse width is adjusted accordingly, shortening the laser's action time and reducing heat input. This generates control instructions that adapt to the cutting conditions in real time, ensuring a stable cutting process and high-quality welds.

[0042] Example 4: When optimizing cutting accuracy and equipment energy consumption simultaneously based on a multi-objective optimization algorithm, the following steps are performed: First, the cutting accuracy objective function and energy consumption constraint function are defined to construct the Pareto frontier model. The cutting accuracy objective function is used to measure the closeness between the cut solder piece and the target geometry. Assume that the actual coordinates of a point on the solder piece are , the target coordinates are , cutting accuracy objective function It can be expressed as ,in is the number of points on the solder piece involved in the calculation. This formula calculates the sum of the distances between the actual positions of multiple points on the solder piece and the target positions. The smaller the sum of the distances, the higher the cutting accuracy.

[0043] In terms of energy consumption constraint function, the energy consumption relationship model between laser power and cutting speed is established. Assume that the laser power is , cutting speed is , energy consumption The relationship between them can be expressed as ,in is the length of the cutting path. According to the rated power of the equipment and heat dissipation efficiency , calculate the dynamic energy consumption threshold The heat dissipation efficiency indicates the ratio of the heat dissipated by the device to the heat generated per unit time. Assuming that the heat generated by the device per unit time is , the heat dissipated is Dynamic energy consumption threshold The calculation formula is ,in The dynamic energy consumption threshold is used as a hard constraint of the Pareto frontier model to ensure that the energy consumption of the equipment does not exceed the allowable range during the optimization process.

[0044] Next, the cutting speed, power, and path parameters are jointly optimized using a non-dominated sorting genetic algorithm. This algorithm incorporates multiple objectives (such as cutting accuracy and energy consumption) into the optimization process. By non-dominated sorting of individuals in the population (i.e., different cutting parameter combinations), the individuals are divided into different levels. Individuals with higher levels are prioritized for genetic manipulation, and the optimization is continuously iterated to gradually find the optimal solution that meets these multiple objectives.

[0045] In each iteration, an elite retention strategy is used to update the candidate solution set until the convergence condition is met. This strategy involves retaining individuals with good fitness in the current population during each iteration, preventing these individuals from being eliminated during genetic operations, thereby accelerating the algorithm's convergence. The convergence condition can be set to a threshold where the change in the objective function value over multiple consecutive iterations is less than a certain threshold. When this condition is met, the algorithm is considered converged and the optimal cutting parameter combination is output.

[0046] Example 5: During the cutting process, in order to ensure the smooth progress of cutting and the quality of the weld, the following measures were taken: Acoustic emission signals and vibration spectrum data are collected in real time during the cutting process. Acoustic emission signals are elastic wave signals generated by internal structural changes in the weld during cutting, and can reveal defects and cracks within the weld. Vibration spectrum data reflects the vibration characteristics of the cutting equipment during the cutting process. Abnormal vibration may indicate problems in the cutting process.

[0047] Wavelet transform is used to extract signal features and identify abnormal cutting events. Wavelet transform is a signal processing method that can decompose the signal at different time and frequency scales and extract the characteristic information of the signal. Assume that the original signal is , the wavelet function is , then the wavelet transform The formula is ,in is the scale parameter, which controls the expansion and contraction of the wavelet function; is the translation parameter, which controls the translation of the wavelet function; for By performing wavelet transform on the acoustic emission signal and vibration spectrum data, the characteristics of the signal at different scales and frequencies can be obtained. Based on these characteristics, it can be determined whether there are any abnormal cutting events, such as weld crack expansion and cutting head wear.

[0048] If an abnormality is detected, the emergency stop protocol is triggered and the cutting path is replanned. The execution of the emergency stop protocol includes: selecting local pause or global stop mode according to the level of abnormal event. The level of abnormal event can be divided according to the degree of abnormality of the signal characteristics. For example, a slight vibration abnormality may be classified as a lower level, while a strong acoustic emission signal may be classified as a higher level. In local pause mode, a redundant path is used to bypass the abnormal area. The redundant path is a pre-planned backup cutting path. When an abnormal area is detected, the cutting head can continue cutting along the redundant path to avoid further processing of the abnormal area and reduce the scrap rate. In global stop mode, the cutting parameters are reset and the self-test program is started. Resetting the cutting parameters can restore parameters such as cutting speed and laser power to the initial state. The self-test program checks the various components of the cutting equipment to ensure that the equipment is not damaged and prepares for the subsequent resumption of cutting.

[0049] Example 6: After the cutting is completed, in order to improve the accuracy and quality of subsequent cutting, the following operations will be performed: An optical scanner is used to obtain the actual geometric parameters of the solder pad. Using optical principles, an optical scanner can accurately measure parameters such as the shape and size of the solder pad. For example, it can transmit light and receive reflected light, calculating the coordinates of each point on the solder pad's surface based on the light's travel time and angle.

[0050] Compare the actual geometric parameters with the target geometric shape data and calculate the shape error matrix. Assume that the actual coordinates of a point on the solder joint are , the target coordinates are , the elements in the shape error matrix It can be expressed as ,in Represents different points on the solder piece. This formula calculates the distance between the actual position and the target position of each point on the solder piece. The resulting shape error matrix comprehensively reflects the overall shape error of the solder piece.

[0051] Based on the shape error matrix, the segmented optimization weights in the cutting path generation algorithm are reverse-calibrated. These weights influence the direction and degree of trajectory optimization in the cutting path generation algorithm. By analyzing the shape error matrix, areas with large errors are identified, and the weights for these areas in the segmented optimization are adjusted. For example, if a region has large shape errors, indicating unsatisfactory cutting path optimization results in that area, the segmented optimization weight for that region can be appropriately increased. This allows the algorithm to focus more on that region during subsequent cutting processes, allowing for more refined optimization of the cutting path and ultimately improving cutting accuracy.

[0052] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "includes," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0053] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A method for efficiently cutting vacuum brazing sheets, characterized in that: include: Receiving material parameters and target geometry data of the welding piece to be cut, wherein the material parameters include melting point, thermal conductivity and thickness distribution; Based on a preset cutting path generation algorithm, an initial cutting trajectory is generated according to the target geometric shape data, and the trajectory is segmented and optimized; Combined with real-time temperature field monitoring data, the thermal stress distribution during the soldering process is calculated using finite element analysis; According to the thermal stress distribution, the cutting speed and laser power parameters are dynamically adjusted to generate adaptive control instructions; Based on a multi-objective optimization algorithm, cutting accuracy and equipment energy consumption are simultaneously optimized, and the final cutting parameters are output to the vacuum brazing control system.

2. The method for efficiently cutting vacuum brazing sheets according to claim 1, characterized in that: The steps of constructing the cutting path generation algorithm include: Collect historical cutting trajectory data and cutting quality scores to build a training data set; Performing path optimization on the training data set by using a genetic algorithm to generate a set of candidate trajectories; Using a Bayesian optimization algorithm to select the optimal segmentation points in the candidate trajectory set; The segment point coordinates are combined with the cutting head kinematic model to generate the smooth initial cutting trajectory.

3. The method for efficiently cutting vacuum brazing sheets according to claim 1, characterized in that: The execution of the finite element analysis method includes: Establish a three-dimensional heat conduction model of the solder joint, divide the mesh nodes and set boundary conditions; Calculate the temperature gradient and thermal expansion coefficient of each node based on real-time temperature field data; Combined with the material elastic modulus, the thermal stress tensor equation is solved and the thermal stress distribution diagram is output; Wherein, the thermal stress tensor equation is: Where, Represents the stress component of the solder joint in the (i, j) direction in the three-dimensional coordinate system, is the elastic modulus, represents the strain component of the solder joint in the (i, j) direction, is the coefficient of thermal expansion, is the temperature change, is the Kronecker function.

4. The method for efficiently cutting vacuum brazing sheets according to claim 1, characterized in that: The dynamic adjustment of cutting speed and laser power parameters includes: Based on the thermal stress distribution map, stress concentration areas are identified and marked as high-risk areas; Assign a deceleration factor to the high-risk area and optimize the laser power attenuation curve based on the gradient descent method; The optimized parameters are input into the pulse width modulation module to generate the adaptive control instructions.

5. The method for efficiently cutting vacuum brazing sheets according to claim 1, characterized in that: The execution of the multi-objective optimization algorithm includes: Define the cutting accuracy objective function and energy consumption constraint function, and construct the Pareto frontier model; The cutting speed, power and path parameters are jointly optimized using a non-dominated sorting genetic algorithm; In each iteration, the elite retention strategy is adopted to update the candidate solution set until the convergence condition is met.

6. The method for efficiently cutting vacuum brazing sheets according to claim 2, characterized in that: The screening step of the Bayesian optimization algorithm includes: Construct a response surface model of cutting quality and segmentation point location; Calculate the expected improvement value of each candidate trajectory through Gaussian process regression; The segmentation point with the largest expected improvement value is selected as the optimal segmentation point.

7. The method for efficiently cutting vacuum brazing sheets according to claim 1, characterized in that: Also includes: Real-time collection of acoustic emission signals and vibration spectrum data during the cutting process; Extract signal features through wavelet transform and identify abnormal cutting events; If an anomaly is detected, the emergency stop protocol is triggered and the cutting path is replanned.

8. The method for efficiently cutting vacuum brazing sheets according to claim 5, characterized in that: The setting of the energy consumption constraint function includes: Establish the energy consumption relationship model between laser power and cutting speed; Calculate the dynamic energy consumption threshold based on the equipment's rated power and heat dissipation efficiency; The dynamic energy consumption threshold is used as a hard constraint condition of the Pareto frontier model.

9. The method for efficiently cutting vacuum brazing sheets according to claim 7, characterized in that: Execution of the emergency shutdown protocol includes: Select local pause or global shutdown mode according to the abnormal event level; In local pause mode, redundant paths are used to bypass abnormal areas; In global stop mode, reset cutting parameters and start the self-test procedure.

10. The method for efficiently cutting vacuum brazing sheets according to claim 1, characterized in that: Also includes: After cutting is completed, the actual geometric parameters of the welding piece are obtained through an optical scanner; Compare the actual geometric parameters with the target geometric shape data and calculate the shape error matrix; According to the shape error matrix, the segment optimization weights in the cutting path generation algorithm are reversely calibrated.

Images