Combined protection method and system for monitoring, regulation and control of laser hole drilling process
By constructing a penetration time prediction model and a hole-making stage identification model, combined with beam shaping technology, the laser processing process is controlled in real time, and overablation problems in laser processing are solved, achieving efficient and high-precision wall-free damage processing, which is improved Quality and controllability of hollow cavity material processing.
Patent Information
- Application Number
- PCT/CN2023/135233
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2023-05-29
- Filing Date
- 2023-11-29
- Publication Date
- 2024-12-05
AI Technical Summary
Due to contactless processing and Gaussian light transmission characteristics during laser processing, the processing depth is difficult to control, and the transmission of light is easily disturbed by structural evolution and plasma eruption, resulting in fluctuations in the processing process, causing overablation problems, affecting processing quality and workpieces. life.
By collecting signal evolution information and motion trajectory information, a penetration time prediction model and a hole making phase identification model are constructed, combined with the confidence of different hole making phases, the laser processing process is controlled in real time, different hole making strategies are adopted, and beam shaping technology is used to adjust. The longitudinal energy distribution of the Gaussian beam enables no damage to the wall.
It realizes efficient and high-precision processing of the laser hole making process, ensures no wall damage, improves processing quality and workpiece life, and enhances the controllability of processing of hollow cavity materials.
Smart Images

Figure CN2023135233_05122024_PF_FP_ABST
Abstract
Description
A laser hole making process monitoring and control combined protection method and system Technical Field
[0001] The present invention belongs to the field of laser processing and manufacturing, and in particular relates to a combined protection method and system for monitoring and regulating a laser hole-making process. Background Art
[0002] Laser processing has many characteristics, including high processing precision, high processing quality, the ability to process almost any material, and contactless processing. However, due to its contactless processing and Gaussian light transmission characteristics, the processing depth cannot be controlled by axis feed, and the laser in the range near the focus will still cause damage to the material. At the same time, the transmission of light during laser processing is easily disturbed by phenomena such as structural evolution during the processing and plasma eruption, resulting in fluctuations in the processing process and problems with processing repeatability and stability. Therefore, when processing hollow cavity workpieces (blades, fuel injectors, etc.), over-ablation often occurs, resulting in poor processing quality or reduced workpiece service life, which is unacceptable in most cases.
[0003] Currently, there are two main methods to solve the problem of over-ablation: cavity material filling and laser processing process monitoring. Cavity material filling is to fill the hollow cavity with material to weaken or even eliminate the effect of laser energy. Laser processing process monitoring is to monitor the hole-making status in real time and regulate the processing process according to different hole-making states. However, the current cavity material filling cannot feedback the protection status, making it difficult to achieve protection for narrow cavities. The current connection between the signals obtained by processing process monitoring and the processing process is often indirect, making it difficult to achieve accurate control of the processing process. This seriously hinders the application of laser processing on workpieces with hollow cavities and limits the development of laser processing technology.
[0004] Summary of the Invention
[0005] The purpose of the present invention is to provide a combined protection method and system for monitoring and controlling a laser hole-making process, which solves the defect of poor processing quality in existing laser processing.
[0006] In order to achieve the above object, the technical solution adopted in the present invention is:
[0007] The present invention provides a combined protection method for monitoring and controlling a laser hole making process, comprising the following steps:
[0008] Step 1: Collect signal evolution information, current hole depth, and motion trajectory information during the laser hole making process;
[0009] Step 2: Extract features from the signal evolution information obtained in step 1 to obtain time series feature values that evolve over time, and construct a penetration time prediction model based on the obtained time series feature values;
[0010] Step 3: Combine the current hole depth and motion trajectory information obtained in step 1 with the time series characteristic value to construct a hole-making stage identification model;
[0011] Step 4: The prediction results of the penetration time prediction model are integrated with the confidence of the identification results of the hole making stage identification model at different times to construct a state identification model;
[0012] Step 5: The current hole-making stage is determined based on the obtained state recognition model, and the laser processing process is controlled based on the determination result, with different hole-making strategies being adopted in different hole-making stages.
[0013] Preferably, in step 2, a penetration time prediction model is constructed based on the obtained time series characteristic values, and the specific method is:
[0014] The hole making process is divided into four stages, namely, the non-penetration stage, the early penetration stage, the hole forming stage and the hole completion stage.
[0015] According to the evolution process of the set non-penetration stage and the early penetration stage, the remaining hole-making penetration time value corresponding to the time series characteristic value at different moments is obtained;
[0016] The obtained time series feature values are combined with laser parameters and material parameters as training features, and the remaining hole penetration time values are used as training labels. The penetration time prediction model is constructed using the autoregressive deep learning method.
[0017] Preferably, in step 3, the current hole depth and motion trajectory information obtained in step 1 are combined with the time series characteristic value to construct a hole making stage identification model, and the specific method is:
[0018] The current hole depth and motion trajectory information obtained in step 1 are combined to obtain the depth information of a specific point on the hole-making trajectory;
[0019] Form three-dimensional point cloud information based on the obtained depth information;
[0020] The obtained three-dimensional point cloud information is filtered, segmented and fitted in sequence to obtain a three-dimensional point cloud model of the hole;
[0021] Perform feature extraction on the 3D point cloud model of the hole to obtain the hole's entrance and exit diameters and other morphological features;
[0022] Combining the depth features, morphology features and time series feature values of the holes, and using the calibrated depth features and morphology features of the holes corresponding to different hole-making stages as labels, a hole-making stage identification model was constructed using a machine learning method.
[0023] Preferably, in step 4, a state recognition model is constructed by combining the penetration time prediction model and the hole making stage identification model. The specific combination method is:
[0024] Input the time series characteristic values and morphological features corresponding to different moments into the hole-making stage identification model established in step 3 to obtain the confidence level of the hole-making stage identification results at different moments in real time;
[0025] Input the time series feature values corresponding to different moments into the penetration time prediction model established in step 2 to predict the remaining penetration time corresponding to the current moment in real time;
[0026] The confidence levels of the hole-making stage identification results at different times are weighted and fused to obtain the comprehensive confidence level at the current time.
[0027] The remaining penetration time predicted at the current moment is probabilistically fused with the comprehensive confidence to obtain a state recognition model.
[0028] Preferably, in step 5, the different hole-making strategies are:
[0029] When the current hole processing stage is the non-penetration stage, the processing parameters are adjusted based on the processing efficiency;
[0030] When the current hole processing stage is the early penetration stage and the hole forming stage, the light field distribution of the laser processing is adjusted with the goal of hole depth control;
[0031] When the hole making stage switches from the hole forming stage to the hole completing stage, processing stops.
[0032] Preferably, when the current hole processing stage is the non-penetration stage, the processing parameters are adjusted with processing efficiency as the goal, and the specific method is:
[0033] The current hole-making depth, laser power, and focal position are used as inputs, and the actual ablation rate change is output. A neural network is used to establish a correlation model between the ablation rate change and the current hole-making depth, laser power, and focal position, and the processing parameters are adjusted using this correlation model.
[0034] Preferably, when the current hole processing stage is the early penetration stage and the hole forming stage, the light field distribution of laser processing is adjusted with the hole depth control as the goal, and the specific method is as follows:
[0035] The processing point coordinates are located by coaxial vision, and the Gaussian processing optical path is switched to the beam shaping optical path;
[0036] A beam shaper is used to shape the Gaussian beam into a Bessel beam with axial ablation limitation.
[0037] The shaped beam is used to modify the hole.
[0038] A combined protection system for monitoring and controlling a laser hole-making process includes a laser, a beam transmission system, a dichroic mirror, a sensing system, a beam switching system, a beam shaping system, a focusing lens, and a scanning galvanometer. The laser beam output by the laser passes through the beam transmission system and then through the dichroic mirror before being incident on the beam switching system. The output light path of the beam switching system is divided into two paths, one of which passes through the beam shaping system and then is incident on the focusing lens for focusing, and the other is incident on the scanning galvanometer for focusing. The laser beam output by the focusing lens and the scanning galvanometer acts on a target material.
[0039] Preferably, the beam shaping system includes a beam shaping element and a 4f system, wherein the output light path of the beam switching system passes through the beam shaping element and is incident on the 4f system to form Bessel light.
[0040] Compared with the prior art, the present invention has the following beneficial effects:
[0041] The present invention provides a combined protection method for monitoring and controlling the laser hole-making process, which divides the hole-making process into four stages. By extracting the differences in signal distribution during the processing process and reconstructing and extracting the features of the three-dimensional morphology of the hole, a state recognition model for distinguishing different hole-making stages is established. Different hole-making strategies are adopted according to different hole-making stages. By adjusting the longitudinal energy distribution of the Gaussian beam and combining visual positioning, precise switching between the hole-making optical path and the shaping optical path is achieved, ensuring efficient, high-precision and wall-damage-free processing during the laser hole-making process.
[0042] The present invention provides a combined protection system for monitoring and controlling the laser hole-making process. By combining a dichroic mirror with a beam splitter, the system realizes coaxial coupling of multiple sensors with the processing optical path, monitors the laser hole-making process in real time, and identifies the laser hole-making stage in real time. The optical shaping element is used to adjust the longitudinal energy distribution of the Gaussian light, and the laser ablation depth is controlled within a certain focal depth range to ensure processing without damaging the wall. In combination with visual positioning technology, the system realizes precise switching between the Gaussian beam hole-making optical path and the beam shaping and modification optical path to meet the different hole-making strategies required for different hole-making stages, thereby ensuring efficient, high-precision and wall-damage-free processing of the laser hole-making process. BRIEF DESCRIPTION OF THE DRAWINGS
[0043] FIG1 is a general flow chart of the method of the present invention;
[0044] FIG2 is a flow chart of a method for obtaining laser hole depth information according to the present invention;
[0045] FIG3 is a schematic diagram of the hole making stage division and calibration of the present invention;
[0046] FIG4 is a flow chart of establishing a state recognition model according to the present invention;
[0047] FIG5 is a flow chart of a method for extracting three-dimensional pore morphology and features according to the present invention;
[0048] FIG6 is a flow chart of the hole making strategy method of the present invention;
[0049] FIG7 is a flow chart of the visual positioning method of the present invention;
[0050] FIG8 is a general schematic diagram of the system of the present invention;
[0051] FIG9 is a schematic diagram of the sensing system of the present invention;
[0052] FIG10 is a schematic diagram of an interferometric measurement system according to the present invention;
[0053] FIG11 is a schematic diagram of a beam shaping system according to the present invention. DETAILED DESCRIPTION
[0054] In the following description, specific details such as specific system structures and techniques are provided for purposes of illustration rather than limitation to facilitate a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obscuring the description of the present application with unnecessary detail.
[0055] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections thereof.
[0056] It will also be understood that the term "and / or" used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
[0057] As used in this specification and the appended claims, the term "if" can be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.
[0058] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.
[0059] References to "one embodiment" or "some embodiments" in this specification mean that a particular feature, structure, or characteristic described in conjunction with that embodiment is included in one or more embodiments of the present application. Thus, phrases such as "in one embodiment," "in some embodiments," "in other embodiments," and "in other embodiments" appearing in various places in this specification do not necessarily refer to the same embodiment, but rather mean "one or more but not all embodiments," unless otherwise specifically emphasized. The terms "including," "comprising," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.
[0060] The present invention will be further described in detail below with reference to the accompanying drawings.
[0061] The purpose of the present invention is to provide a combined protection method and system for monitoring and controlling the laser hole-making process, so as to achieve high efficiency, high quality and wall-damage-free processing in the laser hole-making process, enhance the controllability of the laser processing process, and promote the application of laser processing technology in the field of hollow cavity material processing.
[0062] As shown in FIG1 to FIG6 , the present invention provides a laser hole making process monitoring and control combined protection method, comprising the following steps:
[0063] Step 1: Using a sensor system to collect historical data of the target material during the laser hole making process, the historical data includes signal evolution information, current hole depth, and motion trajectory information;
[0064] Step 2: The hole making process is divided into four stages, namely, the non-penetration stage, the early penetration stage, the hole forming stage, and the hole completion stage;
[0065] As shown in Figure 3, the setting method is based on the photodiode sensor signal and the hole shape for calibration. The specific calibration method is:
[0066] When the workpiece is not penetrated by the laser, the laser cannot be emitted from the back of the workpiece, and the photodiode signal amplitude difference is at the lowest state, which is regarded as the non-penetration stage;
[0067] When the workpiece is just penetrated by the laser, the workpiece outlet is extremely small, only a small part of the laser is emitted from the back of the workpiece, and the photodiode signal amplitude difference is at the highest state, which is considered to be the early penetration stage;
[0068] When the workpiece is penetrated by the laser for a period of time, the workpiece outlet becomes larger, the laser is stably emitted from the back of the workpiece, and the photodiode signal amplitude difference is in a stable changing state, which is regarded as the hole forming stage;
[0069] When the workpiece is penetrated by the laser for a period of time, the workpiece outlet remains almost unchanged and the laser has almost no ablation effect on the workpiece, the photodiode signal amplitude is in a stable state, which is regarded as the hole completion stage.
[0070] Feature extraction is performed on the signal evolution information obtained in step 1 to obtain the time series characteristic values that evolve over time. According to the evolution process of the set non-penetration stage and the early penetration stage, the remaining hole-making penetration time values corresponding to the time series characteristic values at different moments are obtained. The obtained time series characteristic values are combined with the laser parameters and material parameters as training features, and the remaining hole-making penetration time values are used as training labels. The penetration time prediction model is constructed using the autoregressive deep learning method.
[0071] The time series characteristic values include average value, peak value, variance, etc.
[0072] The laser parameters include laser power and repetition rate.
[0073] The material parameters include light absorptivity, thermal conductivity, thickness, etc. corresponding to the current material.
[0074] The penetration time prediction model continuously combines the collected data to predict the remaining penetration time for hole making at the current moment.
[0075] As shown in Figure 4, the current hole depth (Z-axis information) and motion trajectory information (XY plane information) obtained in step 1 are integrated to obtain the depth information of a specific point on the hole-making trajectory, thereby forming a three-dimensional point cloud (X, Y, Z) information. The obtained three-dimensional point cloud information is filtered, segmented, and fitted in sequence to establish a three-dimensional point cloud model of the hole.
[0076] Extracting the depth and morphological features of the hole based on the three-dimensional point cloud model, wherein the morphological features include the diameter of the entrance and exit, etc.
[0077] The obtained depth characteristics and morphological characteristics of the hole are combined with the time series characteristic values. The depth characteristics and morphological characteristics of the hole corresponding to different calibrated hole-making stages are used as labels. A machine learning method is used to establish a hole-making stage identification model to realize the identification of the non-penetration stage, early penetration stage, hole forming stage and hole completion stage according to the signal characteristics collected during the processing process.
[0078] According to the historical data corresponding to different moments obtained in step 1, the time series characteristic values and morphological features corresponding to different moments are obtained; the time series characteristic values and morphological features corresponding to different moments are input into the hole-making stage identification model established in step 3 to obtain the confidence level of the hole-making stage identification results at different moments in real time;
[0079] The time series feature values corresponding to different moments are input into the penetration time prediction model established in step 2 to predict the remaining penetration time corresponding to the current moment in real time;
[0080] The confidence levels of the hole-making stage identification results at different times are weighted and fused to obtain the comprehensive confidence level at the current time.
[0081] The obtained comprehensive confidence is probabilistically fused with the predicted remaining penetration time of the hole production output by the penetration time prediction model to establish a state recognition model.
[0082] Step 3: Set the laser processing parameters and perform hole-making processing on the target material, obtain the parameters of the current processing stage, input the relevant parameters into the state recognition model constructed in step 2, and judge the current hole-making processing stage in real time. According to the judgment results, the laser processing process is regulated and different hole-making strategies are adopted in different hole-making stages.
[0083] As shown in Figure 5, when the current hole processing stage is the non-penetration stage, the high-speed processing strategy is adopted, and the processing parameters are adjusted with the processing efficiency as the goal. The specific method is as follows:
[0084] The current hole-making depth, laser power, and focal position are used as inputs, and the actual ablation rate change is output. A neural network is used to establish a correlation model between the ablation rate change and the current hole-making depth, laser power, and focal position. The ablation rate of the next pulse or the next cycle is predicted based on the input ablation rate change. The laser focal position is used as the controlled object, and the actual ablation rate change is output. The hole-making depth is measured in real time by an interferometric measurement system and converted into real-time ablation rate change as feedback. The laser ablation rate change is always positive or unchanged by adjusting the focal position in real time. Based on the above ideas and combined with the model predictive control method, a laser hole-making high-speed processing control model is established to achieve high-efficiency hole-making.
[0085] When the current hole processing stage is the early penetration stage and the hole forming stage, a quantitative removal processing strategy is adopted. With the goal of controlling the hole depth, the light field distribution of the laser processing is adjusted. The traditional Gaussian laser distribution with hyperbolic transmission characteristics is adjusted to a Bessel-like beam distribution with limited axial transmission. This can achieve hole shaping without protective materials and ensure that the processing depth is as constant as possible, avoiding damage to the back wall.
[0086] The current hole processing stage is the hole completion stage, and the processing process is stopped.
[0087] Specifically, as shown in FIG2 , in step 1, the current hole depth during the machining process is acquired in real time using the sensing system. The specific method flow is as follows:
[0088] S101, using a spectrometer in an interferometric measurement system to collect interference signals in real time during the laser hole making process;
[0089] S102, processing the interference signal to obtain depth information, where:
[0090] Preprocessing the interference signal obtained in S101 by DC removal and wave number linearization in sequence to obtain a preprocessed interference signal;
[0091] Then, the pre-processed interference signal is demodulated using Fourier transform to obtain the depth information of each point in the Z direction;
[0092] S103, combined with the motion trajectory information, considering the impact of debris, plasma eruption and hole shape evolution during the processing on data acquisition, the depth information recovered by the interference signal collected at the same position point is subjected to noise reduction processing, the depth information obtained by scanning multiple time frames is averaged, and the depth information is further filtered to reduce noise points, and then the remaining depth points are clustered and segmented to extract the depth information during the processing process, and the depth information is maximized, and its maximum depth is used as the current hole depth.
[0093] In step 2, the three-dimensional shape of the hole is reconstructed based on the acquired depth information and motion trajectory information, and depth features and shape features are proposed. The specific method flow is as follows:
[0094] S601, using the position comparison output function of the motion controller, when the motion axis or galvanometer axis reaches a specific position, the motion controller outputs a signal to trigger the interferometric measurement sensor system to collect the current hole depth information in real time, thereby obtaining the plane coordinates (x, y) and depth information z of the processing point in real time, that is, the three-dimensional coordinate point cloud data (x, y, z).
[0095] S602: Process the point cloud obtained during the machining process, remove noise points through point cloud filtering, and segment the point cloud data based on the similarity of the point cloud. Then, fit the point cloud data into a plane through a fitting algorithm, and reconstruct the point cloud into a 3D model by establishing the 3D topological relationship of the point cloud data, thus achieving real-time reconstruction of the 3D shape during the hole making process.
[0096] S603, considering the key features of the hole shape in laser drilling, such as hole entrance diameter, hole exit diameter, hole roundness, etc., extracting the above morphological features based on the reconstructed 3D model
[0097] In step 3, different hole-making strategies are adopted according to different hole-making stages. The specific hole-making strategies are as follows:
[0098] S701, collecting sensor signals in the laser drilling process in real time, and identifying the drilling stage according to the state recognition model;
[0099] S702: When the laser processing process is in the non-penetration stage, a high-speed processing strategy is adopted. That is, the current hole depth, laser power, focus position and other parameters are used as inputs, and a neural network is used to establish a correlation model between the ablation rate change and the current hole depth, laser power, and focus position. The ablation rate of the next pulse or the next cycle time is predicted based on the input ablation rate change. The laser focus position is used as the controlled object, and the actual ablation rate change is used as the output. The hole depth is measured in real time by an interferometer measurement system and converted into a real-time ablation rate change as feedback. The focus position is adjusted in real time to ensure that the laser ablation rate change is always positive or unchanged. Based on the above ideas and combined with the model predictive control method, a laser hole high-speed processing control model is established to achieve high-efficiency hole production.
[0100] S703: When the laser processing process transitions from the non-penetration stage to the early penetration stage, the processing strategy switches to a quantitative removal processing strategy. This strategy uses coaxial vision to locate the processing point coordinates, switches the Gaussian processing optical path to a beam shaping optical path, and uses the shaped beam to shape the hole. Simultaneously, an interferometric measurement sensor system measures the processing depth in real time, ensuring high-quality processing without damaging the wall.
[0101] S704, when the laser processing process is in the hole completion stage, stop processing.
[0102] In step 3, the parameters of the current processing stage are obtained. The specific method is:
[0103] S31, obtaining signal evolution information, current hole depth, and motion trajectory information during the laser hole making process;
[0104] S32, obtaining a time series characteristic value based on the signal evolution information; combining the current hole depth and motion trajectory information to establish a three-dimensional point cloud model;
[0105] S33, using the three-dimensional point cloud model to extract the morphological features of the hole, the hole morphological features, hole depth and timing characteristic values are the parameters of the current processing stage.
[0106] As shown in FIG7 , in step 3, the conventional Gaussian laser profile with hyperbolic transmission characteristics is adjusted to a Bessel-like beam profile with axial transmission limitation. The specific method is as follows:
[0107] S301, calibrating the laser processing system and camera. Given the coordinate system of the multi-axis motion stage in the laser processing system, the camera is used to collect position information of different points on the motion stage. A relationship model corresponding to any pixel on the camera image and the processing coordinates can be obtained. Solving this relationship model can establish a conversion model between the motion stage coordinate system and the camera coordinate system.
[0108] Similarly, by combining the motion of the motion stage, the laser processes at different positions, and the camera is used to obtain the coordinates corresponding to the processing position, the association model between the laser pose and the camera coordinate system can be established, thereby obtaining the conversion model between the three coordinate systems;
[0109] S302, using a camera to capture an image of the processing area, performing pre-processing operations such as enhancement and filtering on the image, extracting the coordinate position of the center of the hole in the processing area, and converting it to the coordinates of the multi-axis motion stage;
[0110] S303: Use the beam switching system to convert the Gaussian beam transmission optical path into a beam shaping optical path. Consider the difference in laser posture between the Gaussian beam transmission optical path and the beam shaping optical path, convert it into the difference in position coordinates between the multi-axis motion stage, and use the multi-axis motion stage to move the workpiece so that the center of the processing area coincides with the center of the laser focus position of the beam shaping optical path to further modify the hole.
[0111] The specific shaping principle of the beam shaping optical path is as follows:
[0112] S3031, using an analytical method to calculate the phase distribution of the Gaussian beam shaped into a Bessel-like beam with axial ablation limitation, such as the corresponding phase distribution calculated according to the following formula:
[0113] Where R is the right angle of the diffraction plane, Z1 and Z2 are the starting and ending points of the light beam respectively;
[0114] S3032: Use the phase distribution to input into a spatial light modulator or make a corresponding diffractive optical element to achieve the regulation of the axial distribution of the light beam. Combined with the 4f system, its focal depth is limited to a specific area to meet the processing requirements.
[0115] In step 1, the target material may be a material having a hollow cavity, such as an engine blade or a fuel injector.
[0116] In step 1, the sensing system mainly includes an interferometric measurement system, a camera, and a photodiode, etc., wherein the interferometric measurement system can measure the depth of the hole, the camera can be a black and white camera, a color camera, or a thermal imaging camera, etc., and the photodiode can be replaced by an instrument such as a spectrometer.
[0117] In step 1, the motion trajectory information mainly refers to the position coordinates of the current multi-axis motion stage, which can be obtained through grating feedback or reading by the system controller.
[0118] In step S302, the center position of the hole in the processing area is extracted mainly by using edge extraction and template matching method.
[0119] As shown in Figure 7, the present invention provides a laser hole-making process monitoring and control combined protection system, which includes a laser 1, a beam transmission system 2, a dichroic mirror 3, a sensing system 4, a beam switching system 5, a beam shaping system 6, a focusing lens 7, a multi-axis motion stage 10, a scanning galvanometer 11, a system controller 12 and an industrial computer 13. The laser beam output by the laser 1 passes through the beam transmission system 2 and then through the dichroic mirror 3 to be incident on the beam switching system 5; the output light path of the beam switching system 5 is divided into two paths, one of which passes through the beam shaping system 6 and then is incident on the focusing lens 7 for focusing, and the other is incident on the scanning galvanometer 11 for focusing; the laser beam output by the focusing lens 7 and the scanning galvanometer 11 acts on the target material 8 on the multi-axis motion stage 10.
[0120] The beam switching system 5 is used to control the switching of the laser transmission light path.
[0121] The beam shaping system 6 is used to adjust the longitudinal energy distribution of the Gaussian beam and control the ablation depth within a certain range.
[0122] The system controller 12 is connected to the sensing system 4, the laser 1, the beam switcher 5, the scanning galvanometer 11 and the multi-axis motion stage 10, and is used to process the signals collected by the sensing system, feedback the processing status and coordinate the control of the multi-axis motion stage, the scanning galvanometer, the laser, etc.
[0123] The industrial computer 13 is connected to the system controller 12 and is used to control the command logic of the system controller.
[0124] As shown in FIG10 , the beam shaping system 6 includes a beam shaping element 25 and a 4f system 26 , wherein the beam shaping element 25 is a spatial light modulator, a diffractive optical element, an axon, or a metasurface element; the high-filament light passes through the beam shaping element 25 and is incident on the 4f system 26 to form Bessel light.
[0125] As shown in Figure 8, the sensing system 4 includes a photodiode 14, a camera 16 and an interferometric measurement system 17, wherein the photodiode 14 is placed on the back of the target material for calibrating the laser hole-making stage, and the photodiode 14 is coaxially placed with the camera 16 through a beam splitter 15 for monitoring the temporal change of the plasma radiation signal during the hole-making process; the camera is coaxially coupled with the interferometric measurement system 17 through a dichroic mirror 18 for monitoring the spatial distribution and positioning of the surface light radiation signal during the hole-making process, and the interferometric measurement system 17 is coupled with the processing light through a dichroic mirror 3 for measuring the hole depth during the hole-making process.
[0126] As shown in Figure 9, the interference measurement system 17 includes a detection light source 20, a collimator 122, a beam splitter 21, a collimator 224 and a signal detector 19, wherein the detection light source 20 emits a detection light beam and is incident on the beam splitter 21. The beam splitter 21 splits one beam of light into two beams of light, one of which passes through the collimator 122 and is incident on the reference mirror 23, and the other beam of light passes through the collimator 224 and the dichroic mirror 18 to couple with the processing light beam and focus on the target material. The sample light reflected from the target material and the reference light reflected from the reference mirror 23 return to the beam splitter 21 to interfere, and are further incident on the signal detector 19; the signal detector 19 is used to obtain the interference spectrum signal generated by the interference between the sample light and the reference light.
[0127] The detection light source 20 is a superluminescent diode, a swept laser light source, a fiber laser or a semiconductor laser.
[0128] The signal detector 19 is a photodiode, a spectrometer or a balanced detector.
[0129] Although this specification uses lasers, beam switching systems, beam transmission systems, beam shaping systems, dichroic mirrors, sensing systems, scanning galvanometers, focusing lenses, target materials, multi-axis motion stages, system controllers, industrial computers, interferometric sensing systems, photodiodes, cameras, detection light sources, collimators, beam splitters, signal detectors, state recognition models, high-speed processing strategies, quantitative removal processing strategies, etc. more frequently, it does not exclude the possibility of using other terms. These terms are used only to more conveniently describe the essence of the present invention. Interpreting them as any additional restrictions is contrary to the spirit of the present invention.
[0130] Example 1: No filling material
[0131] Taking the laser processing of blade film cooling holes as an example, the target material is a single crystal high-temperature alloy blade with a cavity thickness of 0.5mm to 3mm. The main steps include:
[0132] Step 1: Determine the machining parameters based on the hole machining diameter, depth, and tilt angle, and machine the blade. The sensing system acquires the parameters of the current machining stage in real time.
[0133] Step 2: Based on the calibrated laser hole-making stages and the timing characteristic values and laser processing parameters obtained in the processing stage parameters, an autoregressive deep learning method is used to establish a penetration time prediction model; and the obtained hole depth characteristics, morphology characteristics and timing characteristic values are combined, and the hole shape characteristics and timing characteristics corresponding to the calibrated different hole-making stages are used to establish a hole-making stage identification model using a machine learning method; the confidence of the identification results output by the hole-making stage identification model at different moments is weighted to obtain the comprehensive confidence of the identification result at the current moment, and the prediction results of the penetration time prediction model are integrated to form a state recognition model of the laser hole-making stage.
[0134] Step 3: During the laser hole making process, the parameters of the current processing stage are obtained in real time, and the relevant parameters are input into the established state recognition model. The state recognition model is used to determine the current hole making stage. In the non-penetration stage, a high-speed processing strategy is adopted, and the focus position is adjusted in real time according to the measured hole depth and ablation rate for high-speed processing. After identifying that the hole making stage has entered the early penetration stage, the hole making strategy is adjusted to a quantitative removal processing strategy.
[0135] Step 4: Use coaxial vision to locate the coordinates of the processing point, switch the Gaussian processing light path to the beam shaping light path, use the beam switching system to switch the processing light path to the beam shaping system, use the coaxial camera to identify the coordinates of the center of the hole, and based on the established camera, motion stage and laser position coordinate system conversion model, move the processing workpiece to the beam shaping processing light path position. At this time, use the shaped Bessel light to shape the hole, and monitor the hole depth in real time to ensure that it does not exceed the sum of the hole depth and the cavity thickness; after monitoring that the laser hole making stage reaches the hole completion stage, stop processing.
[0136] Comparative Example 1: With filling material
[0137] Taking the laser processing of blade film cooling holes as an example, ceramic particles with a diameter of 50μm to 200μm are used as the protective material, single crystal high-temperature alloy blades are used as the target material, and the cavity thickness is 0.5mm to 3mm. The main steps include:
[0138] Step 1: Ceramic particles of corresponding diameter are selected according to the thickness of the cavity and filled into the blade cavity;
[0139] Step 2: Determine the machining parameters based on the hole machining diameter, depth, and tilt angle, and machine the blade. The sensor system acquires the parameters of the current machining stage in real time.
[0140] Step 3: Based on the calibrated laser hole-making stages and the information such as the timing characteristic values and laser processing parameters obtained in the processing stage parameters, an autoregressive deep learning method is used to establish a penetration time prediction model; and the obtained hole depth characteristics, morphology characteristics and timing characteristic values are combined, and the hole shape characteristics and timing characteristics corresponding to the calibrated different hole-making stages are used to establish a hole-making stage identification model using a machine learning method; the confidence of the identification results output by the hole-making stage identification model at different moments is weighted to obtain the comprehensive confidence of the identification result at the current moment, and the prediction results of the penetration time prediction model are integrated to form a state recognition model of the laser hole-making stage.
[0141] Step 4: During the laser hole making process, the parameters of the current processing stage are obtained in real time, and the relevant parameters are input into the established state recognition model. The state recognition model is used to determine the current hole making stage. In the non-penetration stage, a high-speed processing strategy is adopted, and the focus position is adjusted in real time according to the measured hole depth and ablation rate for high-speed processing. After identifying that the hole making stage has entered the early penetration stage, the hole making strategy is adjusted to a quantitative removal processing strategy.
[0142] Step 5: Use coaxial vision to locate the coordinates of the processing point, switch the Gaussian processing light path to the beam shaping light path, use the beam switching system to switch the processing light path to the beam shaping system, use the coaxial camera to identify the coordinates of the center of the hole, and based on the established camera, motion stage and laser position coordinate system conversion model, move the processing workpiece to the beam shaping processing light path position. At this time, use the shaped Bessel light to trim the hole, and monitor the hole depth in real time to ensure that it does not exceed the sum of the hole depth and the cavity thickness; after monitoring that the laser hole making stage reaches the hole completion stage, stop processing.
[0143] Combined with Figure 11, the beam shaping features of this patent are further explained:
[0144] During the machining process, the laser generally exhibits a Gaussian distribution, with its axial transmission being quasi-hyperbolic, which enables the laser to have contactless machining characteristics. However, when processing materials with hollow cavities, the laser will continue to transmit to the inner wall of the cavity after penetrating the surface material, causing damage to the cavity inner wall. As shown in the first figure in Figure 11, without protective materials and beam shaping, it is very easy to cause damage to the cavity inner wall.
[0145] To solve this problem, filling the cavity with protective materials is a common method currently used in the industry to weaken or even eliminate the laser energy, as shown in the second picture in Figure 11. However, since this does not change the ablation characteristics of the laser itself, it will still damage the protective material. When the laser irradiation time is too long or the cavity is too narrow, it will still cause damage to the cavity wall.
[0146] Therefore, this patent is based on the principle of axial beam shaping and control, and controls the axial energy distribution of the laser to change its energy distribution of axial transmission in space, so as to achieve controllable axial ablation depth of the laser. The traditional Bessel beam has a long focal depth characteristic, but at the same time its energy outside the focal depth is also limited. The axial energy distribution of its Bessel beam is shown in the third figure of Figure 11. However, its energy utilization is low, and the beam transmission range is long, making it difficult to achieve wall-free processing of narrow cavities without protective materials. Therefore, on this basis, the beam is further shaped and its axial direction is controlled to become a Bessel beam with limited axial ablation, as shown in the fourth figure in Figure 11. This makes it possible to achieve shaping of different positions without damaging the back wall by controlling the laser feed, ensuring wall-free processing in narrow cavities.
[0147] It should be noted that any attempt to achieve wall-damage-free processing by regulating the axial beam energy distribution is unlikely to deviate from the spirit and scope of this application.
[0148] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.
Claims
1. A laser hole making process monitoring and control combined protection method, characterized in that: The following steps are involved: Step 1, collecting signal evolution information, current hole depth and motion trajectory information during laser hole making processing; Step 2, extracting features from the signal evolution information obtained in step 1, obtaining time series feature values that evolve over time, and constructing a penetration time prediction model based on the obtained time series feature values; Step 3, combining the current hole depth and motion trajectory information obtained in step 1 with the time series characteristic value to construct a hole making stage identification model; Step 4, combining the prediction results of the penetration time prediction model with the confidence of the identification results of the hole making stage identification model at different times, to construct a state identification model; Step 5: The current hole making process stage is determined according to the obtained state recognition model, and the laser processing process is controlled according to the determination result, and different hole making strategies are adopted in different hole making stages.
2. A laser hole making process monitoring and control combined protection method according to claim 1, characterized in that: In step 2, a penetration time prediction model is constructed based on the obtained time series characteristic values. The specific method is: The hole making process is divided into four stages, namely, the non-penetration stage, the early penetration stage, the hole forming stage and the hole completion stage; According to the evolution process of the set non-penetration stage and the early penetration stage, the remaining hole-making penetration time values corresponding to the time series characteristic values at different moments are obtained; The obtained time series feature values are combined with laser parameters and material parameters as training features, and the remaining hole-making penetration time values are used as training labels. The penetration time prediction model is constructed using the autoregressive deep learning method.
3. A laser hole making process monitoring and control combined protection method according to claim 1, characterized in that: In step 3, the current hole depth and motion trajectory information obtained in step 1 are combined with the time series characteristic value to construct a hole making stage identification model. The specific method is: The current hole depth and motion trajectory information obtained in step 1 are combined to obtain the depth information of a specific point on the hole making trajectory; Form three-dimensional point cloud information according to the obtained depth information; The obtained three-dimensional point cloud information is filtered, segmented and fitted in sequence to obtain a three-dimensional point cloud model of the hole; Extract features from the three-dimensional point cloud model of the hole to obtain the hole's entrance and exit diameters and other morphological features; Combining the depth features, morphological features and time series feature values of the holes, the depth features and morphological features of the holes corresponding to different hole-making stages were calibrated as labels, and a machine learning method was used to construct a hole-making stage identification model.
4. A laser hole making process monitoring and control combined protection method according to claim 1, characterized in that: In step 4, a state recognition model is constructed by combining the penetration time prediction model and the hole making stage identification model. The specific combination method is: Input the time series characteristic values and morphological characteristics corresponding to different moments into the hole-making stage identification model established in step 3, so as to obtain the confidence of the hole-making stage identification results at different moments in real time; Input the time series characteristic values corresponding to different moments into the penetration time prediction model established in step 2 to predict the remaining penetration time corresponding to the current moment in real time; The confidence of the hole-making stage identification results at different times is weighted and fused to obtain the comprehensive confidence at the current time. The remaining penetration time predicted at the current moment is probabilistically fused with the comprehensive confidence to obtain the state recognition model.
5. The laser hole making process monitoring and control combined protection method according to claim 1 is characterized in that: In step 5, the different hole-making strategies are: When the current hole processing stage is the non-penetration stage, the processing parameters are adjusted with the processing efficiency as the goal; When the current hole processing stage is the early penetration stage and the hole forming stage, the light field distribution of the laser processing is adjusted with the hole depth control as the goal; When the hole making stage switches from the hole forming stage to the hole completion stage, processing stops.
6. A laser hole making process monitoring and control combined protection method according to claim 1, characterized in that: When the current hole processing stage is the non-penetration stage, the processing parameters are adjusted with processing efficiency as the goal. The specific method is: The current hole making depth, laser power and focal position are taken as inputs, and the actual ablation rate change is output. A neural network is used to establish a correlation model between the ablation rate change and the current hole making depth, laser power and focal position, and the processing parameters are adjusted using the correlation model.
7. A laser hole making process monitoring and control combined protection method according to claim 5, characterized in that: When the current hole processing stage is the early penetration stage and the hole forming stage, the light field distribution of laser processing is adjusted with the hole depth control as the goal. The specific method is as follows: The processing point coordinates are located by coaxial vision, and the Gaussian processing optical path is switched to the beam shaping optical path; A beam shaping device is used to shape the Gaussian beam into an axially ablation-limited Bessel beam; The hole is reshaped using the shaped beam.
8. A laser hole making process monitoring and control combined protection system, characterized in that: The invention comprises a laser (1), a beam transmission system (2), a dichroic mirror (3), a sensor system (4), a beam switching system (5), a beam shaping system (6), a focusing lens (7) and a scanning galvanometer (11), wherein the laser beam output by the laser (1) passes through the beam transmission system (2) and then passes through the dichroic mirror (3) and is incident on the beam switching system (5); the output light path of the beam switching system (5) is divided into two paths, one of which passes through the beam shaping system (6) and then is incident on the focusing lens (7) for focusing, and the other is incident on the scanning galvanometer (11) for focusing; the laser beam output by the focusing lens (7) and the scanning galvanometer (11) acts on the target material (8).
9. A laser hole making process monitoring and control combined protection system according to claim 7, characterized in that: The beam shaping system (6) comprises a beam shaping element (25) and a 4f system (26), wherein the output light path of the beam switching system (5) passes through the beam shaping element (25) and is incident on the 4f system (26) to form Bessel light.
Citation Information
Patent Citations
Precision laser cutting and micro-hole machining device
CN104690432A
Laser cutting device and cutting method
CN106891096A
High-precision, high-efficiency and ultrafast laser processing method for micropores with large depth-diameter ratio
CN112756818A
Laser processing rear wall combined protection method and system based on interference measurement
CN113634873A
Method and device for monitoring micropore penetration in laser processing process and medium
CN114425668A
Cited By
Full-automatic laser ablation inductively coupled plasma mass spectrometer system and detection method
CN119269617A
Optimized machining method for oil passing hole of automobile clutch
CN120551718A
