Adaptive laser processing control method and system based on real-time molten pool monitoring

Abstract

The application discloses a self-adaptive laser processing control method and system based on real-time molten pool monitoring, relates to the field of data processing, and comprises the following steps: firstly, initializing processing conditions based on workpiece parameters and constructing a normal molten pool feature library; during processing, molten pool images, temperature and spectrum data are synchronously collected through multiple sensors, and comprehensive features are obtained through preprocessing and weighted fusion; the real-time features are compared with the feature library; if the features are abnormal, the type is identified and the adjustment direction is determined; a particle swarm optimization algorithm is used to cooperatively optimize laser power and speed parameters; closed-loop verification is carried out until the molten pool returns to normal; and after recording the data in the whole process, the feature library is updated through incremental learning, so that the adaptive adjustment of processing parameters and the continuous optimization of the knowledge base are realized. The application has the following advantages: molten pool data are collected, abnormality is accurately detected through fusion analysis, processing parameters are adjusted through a multi-parameter cooperative optimization model combined with a particle swarm optimization algorithm, the feature library is updated through incremental learning, and high-precision intelligent control of laser processing is realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of data processing, in particular to an adaptive laser processing control method and system based on real-time molten pool monitoring. BACKGROUND

[0002] Laser processing technology is widely used in high-precision manufacturing field, but the traditional processing process relies on preset parameters, which is difficult to cope with the dynamic changes of molten pool caused by material property fluctuations, heat accumulation effects or environmental disturbances, etc., and is easy to cause uneven weld formation, porosity or spatter and other defects. With the improvement of the requirements of industry on processing quality and efficiency, real-time monitoring and adaptive control become the key to break through the bottleneck. The adaptive laser processing method based on real-time molten pool monitoring emerges as the times require.

[0003] The current laser processing method and system on the market rely on a single sensor to monitor the molten pool, such as using only a high-speed camera, which cannot comprehensively obtain the temperature, spectrum and other information of the molten pool, and it is difficult to accurately judge the state of the molten pool. The data processing capability is also relatively weak, and there is a lack of effective preprocessing and fusion of the collected data, resulting in low information utilization rate, inability to form accurate molten pool comprehensive feature data, and large errors in abnormal detection, which easily misses key problems. In response to abnormalities, the traditional method is difficult to quickly determine the adjustment direction of the laser processing parameters once the molten pool appears abnormal, lacks the ability of multi-parameter collaborative optimization, and can only rely on the experience of the operator to adjust manually, which is low in efficiency and poor in adjustment effect, and is difficult to guarantee the processing quality. Moreover, the traditional method usually does not have the function of continuous learning, and cannot record data and update molten pool sample data in real time during processing, which is difficult to adapt to changes of different workpieces and complex working conditions, and has poor adaptability when facing new materials and new processes. SUMMARY

[0004] In order to improve the existing method and system, an adaptive laser processing control method and system based on real-time molten pool monitoring is provided, which synchronously collects molten pool data through multiple source sensors, accurately detects abnormalities through fusion analysis, dynamically adjusts processing parameters through a multi-parameter collaborative optimization model combined with a particle swarm optimization algorithm, and can also update the feature library through incremental learning, realizing high precision, high stability and intelligent control of laser processing.

[0005] To achieve the above purpose, the technical scheme adopted by the present application is as follows:

[0006] The adaptive laser processing control method based on real-time molten pool monitoring comprises:

[0007] Obtaining workpiece parameter data to be processed and normal molten pool sample data under different processing parameter combinations, and initializing laser processing parameters to construct a normal molten pool feature library;

[0008] Based on the initialization of laser processing parameters, the workpiece is processed, and the molten pool image, temperature data and spectrum data collected by the high-speed camera, infrared sensor and spectrum sensor are collected;

[0009] Based on the preprocessing of the collected data, the preprocessed data is fused by a weighted fusion algorithm to obtain the fused molten pool comprehensive feature data.

[0010] The obtained molten pool comprehensive feature data is compared with the normal molten pool feature library to determine whether the current molten pool feature is within the normal threshold range of the corresponding processing stage. If at least one molten pool feature data exceeds the normal threshold range, it is determined that the current molten pool state is abnormal, and the abnormal type is determined through feature matching.

[0011] Based on the matching determined abnormal type, the adjustment direction of the laser processing parameters is determined, and a multi-parameter collaborative optimization model is constructed. The processing parameters are iteratively optimized in the adjustment direction by a particle swarm optimization algorithm to obtain the optimal adjustment parameter group.

[0012] Based on the adjusted molten pool feature data, the molten pool state is compared with the normal molten pool feature library again to determine whether the molten pool state has returned to normal. If the molten pool state is still abnormal, the parameter optimization adjustment process is continued until the molten pool feature returns to the normal threshold range.

[0013] During the laser processing, the processing data is recorded in real time to form a processing database. After processing is completed, the normal molten pool sample data in the database is updated and supplemented by an incremental learning algorithm.

[0014] Preferably, the acquisition of the workpiece parameter data and the normal molten pool sample data under different processing parameter combinations, and the initialization of the laser processing parameters, the construction of the normal molten pool feature library specifically includes:

[0015] The workpiece parameter data includes material properties, thickness size and processing target.

[0016] The normal molten pool sample data includes geometric features, temperature features and spectrum features.

[0017] The laser processing parameters include laser initial power, initial scanning speed, initial defocusing amount and protective gas flow.

[0018] The normal molten pool sample data is trained by a machine learning algorithm to construct a normal molten pool feature library. The feature library contains molten pool feature threshold ranges corresponding to different processing stages.

[0019] Preferably, the processing of the workpiece based on the initialization of the laser processing parameters, and the acquisition of the molten pool image, temperature data and spectrum data collected by the high-speed camera, infrared sensor and spectrum sensor specifically includes:

[0020] The high-speed camera collects real-time images of the molten pool at a frame rate of no less than 1000 fps;

[0021] The infrared sensor collects temperature distribution data of the molten pool area at a sampling frequency of no less than 500 Hz;

[0022] The spectral sensor collects plasma spectral data of the molten pool in a wavelength range of 200-1100 nm;

[0023] The three types of collected data are time-aligned through a synchronous trigger signal to obtain the molten pool image, temperature data and spectral data corresponding to the same processing time.

[0024] Preferably, the collected data is preprocessed, and the preprocessed data is fused through a weighted fusion algorithm to obtain fused comprehensive feature data of the molten pool, which specifically includes:

[0025] The collected molten pool image data is processed through a Gaussian filter algorithm to remove high-frequency noise, histogram equalization to improve the contrast between the molten pool and the background, and edge detection to obtain a clear molten pool contour image and calculate geometric feature parameters;

[0026] The infrared temperature measurement data is processed through a 3σ criterion to remove data points outside the reasonable temperature range and is smoothed to obtain the molten pool center temperature and temperature gradient data;

[0027] The spectral data is baseline corrected and feature spectral lines are extracted to obtain feature spectral line intensity and spectral line half-width data;

[0028] The weight values of each collected data are calculated based on the analytic hierarchy process, and the geometric feature data, temperature feature data and spectral feature data are fused through a weighted fusion algorithm to obtain comprehensive feature data of the molten pool.

[0029] Preferably, the obtained comprehensive feature data of the molten pool is compared with a normal molten pool feature library to determine whether the current molten pool features are within the normal threshold range of the corresponding processing stage. If at least one molten pool feature data is outside the normal threshold range, it is determined that the current molten pool state is abnormal, and the type of abnormality is determined through feature matching, which specifically includes:

[0030] From the normal molten pool feature library, the reference data matching the current processing stage is selected, and each dimension feature of the current molten pool is compared with the normal feature range of the corresponding processing stage;

[0031] If all the comprehensive feature data of the molten pool is within the normal threshold range, it is determined that the current molten pool state is normal, and the processing continues;

[0032] If at least one molten pool feature data is outside the normal threshold range, it is determined that the current molten pool state is abnormal.

[0033] Based on the characteristic dimension beyond the normal range and the deviation direction, the corresponding abnormal type is identified, and the abnormal type includes molten pool overheating, molten pool overcooling, molten pool size being too large, molten pool size being too small, and plasma interference.

[0034] Preferably, the abnormal type determined based on the matching determines the adjustment direction of the laser processing parameter, and a multi-parameter collaborative optimization model is constructed, and the processing parameter is iteratively optimized in the adjustment direction by a particle swarm optimization algorithm to obtain an optimal adjustment parameter group, which specifically includes:

[0035] Based on the matching determined abnormal type, the adjustment direction of the laser processing parameter is obtained;

[0036] Taking the regression of the molten pool characteristics to the normal threshold range as an objective function, a multi-parameter collaborative optimization model is constructed in combination with the coupling relationship among the laser power, the scanning speed and the defocusing amount;

[0037] Based on the particle swarm optimization algorithm, an initial parameter adjustment scheme is generated, and the state change of the molten pool under the scheme is simulated, and if the prediction result shows that the molten pool characteristics do not meet the standard, the parameters are fine-tuned based on the coupling relationship to generate a new adjustment scheme;

[0038] The processing parameter is repeatedly iteratively optimized until a parameter combination that makes the molten pool characteristics return to the normal range is obtained, and the parameter combination is determined as the optimal adjustment parameter group.

[0039] Preferably, the molten pool characteristic data adjusted based on the adjustment is compared with the normal molten pool characteristic library again to determine whether the molten pool state returns to normal, and if the molten pool state is still abnormal, the parameter optimization adjustment process is repeated until the molten pool characteristics return to the normal threshold range, which specifically includes:

[0040] The molten pool characteristic data adjusted based on the optimal adjustment parameter group is compared with the normal molten pool characteristic library again to determine whether the molten pool state returns to normal;

[0041] If all the dimensional characteristics are within the normal threshold range, and the continuous frame fluctuation meets the stability requirement, it is determined that the molten pool state has returned to normal;

[0042] If any dimensional characteristic is still beyond the normal threshold or the continuous frame fluctuation is still unstable, it is determined that the molten pool state is still abnormal, and the historical record of the last parameter adjustment is called to exclude the historical record data in the repeated parameter optimization and adjustment process until the molten pool characteristics return to the normal threshold range;

[0043] If the molten pool state has not returned to normal after three times of parameter adjustment, an alarm mechanism is triggered, the laser processing is suspended, and abnormal prompt information is output.

[0044] Preferably, during the laser processing, the processing data is recorded in real time to form a processing database, and after the processing is completed, the normal molten pool sample data in the database is updated and supplemented by an incremental learning algorithm, which specifically includes:

[0045] During the laser processing, the processing time, workpiece position, molten pool feature data, adjusted processing parameters, and processing quality detection results are recorded in real time to form a processing database.

[0046] After the processing is completed, normal molten pool samples that can be used to update the feature library are selected to supplement the database.

[0047] Based on the initial normal molten pool feature library, new samples are integrated using an incremental learning method, and after updating the feature library, the normal threshold of each dimension is fine-tuned and optimized.

[0048] Further, an adaptive laser processing control system based on real-time molten pool monitoring is proposed, which includes:

[0049] Laser processing module: the module is used to output a laser beam and process a workpiece;

[0050] Molten pool monitoring module: the module synchronously collects molten pool images, temperature, and spectral data through a high-speed camera, an infrared sensor, and a spectral sensor;

[0051] Data preprocessing module: the module filters, denoises, aligns, and extracts features from the original data to generate geometric, temperature, and spectral feature parameters;

[0052] Feature fusion module: the module weightedly fuses multi-source feature data based on the analytic hierarchy process to output a molten pool comprehensive feature vector;

[0053] Abnormality detection module: the module compares the real-time molten pool features with the feature library threshold to identify molten pool overheating and size abnormality fault types;

[0054] Parameter optimization module: the module constructs a multi-parameter collaborative optimization model and generates an optimal adjustment scheme for laser power and speed parameters using a particle swarm optimization algorithm;

[0055] Real-time control module: the module dynamically adjusts the laser processing parameters and feeds back the molten pool state after adjustment to the abnormality detection module for closed-loop verification;

[0056] Data storage and learning module: the module is used to record the processing data throughout the process and update the normal molten pool feature library threshold range through incremental learning;

[0057] Processor: the processor is used to process the calculation process of each formula and the construction and calculation process of each model.

[0058] Compared with the prior art, the application has the advantages that:

[0059] Through multi-source synchronous data collection of high-speed cameras, infrared and spectral sensors, combined with preprocessing and weighted fusion algorithm, the comprehensive characteristics of the molten pool are accurately obtained, laying a reliable foundation for state judgment; secondly, relying on comparison and feature matching of the normal molten pool feature library, various abnormal types can be quickly identified, avoiding the expansion of processing defects; thirdly, the multi-parameter collaborative optimization model is matched with the particle swarm optimization algorithm, which can efficiently iterate the optimal adjustment parameters, and through closed-loop verification to ensure the molten pool to return to normal, and guarantee the processing quality; finally, the processing process database construction combined with the incremental learning algorithm can continuously update the feature library, improve the adaptability of the method to different workpieces and working conditions, and realize high precision, high stability and intelligent control of laser processing as a whole. BRIEF DESCRIPTION OF DRAWINGS

[0060] Figure 1 The method proposed by the application is shown in the schematic diagram;

[0061] Figure 2 The construction of the normal molten pool feature library proposed by the application is shown in the schematic diagram;

[0062] Figure 3 The data acquisition schematic diagram proposed by the application is shown in the schematic diagram;

[0063] Figure 4 The acquisition of fusion molten pool comprehensive feature data proposed by the application is shown in the schematic diagram;

[0064] Figure 5 The determination of abnormal type proposed by the application is shown in the schematic diagram;

[0065] Figure 6 The acquisition of optimal adjustment parameter group proposed by the application is shown in the schematic diagram;

[0066] Figure 7 The adjustment of molten pool feature data optimization proposed by the application is shown in the schematic diagram;

[0067] Figure 8 The database update schematic diagram proposed by the application is shown in the schematic diagram. DETAILED DESCRIPTION

[0068] The following description is used to disclose the application so that those skilled in the art can implement the application. The preferred embodiments in the following description are only as examples, and other obvious variants can be thought of by those skilled in the art.

[0069] The adaptive laser processing control system based on real-time molten pool monitoring comprises:

[0070] The laser processing module is used for outputting a laser beam and processing a workpiece;

[0071] Melt pool monitoring module: the module synchronously collects melt pool image, temperature and spectral data through high-speed camera, infrared sensor and spectral sensor;

[0072] Data preprocessing module: the module filters, denoises, aligns and extracts features of the original data, generating geometric, temperature and spectral feature parameters;

[0073] Feature fusion module: the module weightedly fuses multi-source feature data based on analytic hierarchy process, and outputs melt pool comprehensive feature vector;

[0074] Abnormality detection module: the module compares real-time melt pool features with feature library threshold, and identifies melt pool overheating and size abnormality fault type;

[0075] Parameter optimization module: the module constructs a multi-parameter collaborative optimization model, and generates an optimal adjustment scheme of laser power and speed parameters by using particle swarm optimization algorithm;

[0076] Real-time control module: the module dynamically adjusts laser processing parameters, and feeds back the adjusted melt pool state to the abnormality detection module for closed-loop verification;

[0077] Data storage and learning module: the module is used for recording processing data, and updating normal melt pool feature library threshold range through incremental learning;

[0078] Processor: the processor is used for processing calculation process of each formula and construction calculation process of each model.

[0079] Referring to Figure 1 As shown in the figure, the adaptive laser processing control method based on real-time melt pool monitoring comprises:

[0080] Step one: obtaining workpiece parameter data to be processed and normal melt pool sample data under different processing parameter combinations, and initializing laser processing parameters to construct a normal melt pool feature library;

[0081] Step two: processing the workpiece based on the initialized laser processing parameters, and collecting melt pool image, temperature data and spectral data through high-speed camera, infrared sensor and spectral sensor;

[0082] Step three: preprocessing based on the collected data, and fusing the preprocessed data through a weighted fusion algorithm to obtain fused melt pool comprehensive feature data;

[0083] Step four: comparing the obtained melt pool comprehensive feature data with the normal melt pool feature library to determine whether the current melt pool features are within the normal threshold range of the corresponding processing stage, and if at least one melt pool feature data is out of the normal threshold range, determining that the current melt pool state is abnormal, and determining the abnormal type through feature matching;

[0084] Step 5: Based on the anomaly type determined by matching, determine the adjustment direction of the laser processing parameters, and construct a multi-parameter collaborative optimization model. Use the particle swarm optimization algorithm to iteratively optimize the processing parameters in the adjustment direction to obtain the optimal set of adjustment parameters.

[0085] Step 6: Based on the adjusted molten pool feature data, compare it again with the normal molten pool feature library to determine whether the molten pool state has returned to normal. If the molten pool state is still abnormal, continue the parameter optimization adjustment process until the molten pool features return to the normal threshold range.

[0086] Step 7: During the laser processing, the processing data is recorded in real time to form a processing process database. After the processing is completed, the normal molten pool sample data in the database is updated and supplemented through an incremental learning algorithm.

[0087] See Figure 2 As shown, the process of acquiring workpiece parameter data and normal molten pool sample data under different combinations of processing parameters, initializing laser processing parameters, and constructing a normal molten pool feature library specifically includes:

[0088] The parameter data of the workpiece to be processed includes material properties, thickness dimensions, and processing objectives;

[0089] The normal molten pool sample data includes geometric features, temperature features, and spectral features;

[0090] The laser processing parameters include initial laser power, initial scanning speed, initial defocusing amount, and protective gas flow rate;

[0091] A normal molten pool feature library is constructed by training normal molten pool sample data using machine learning algorithms. The feature library contains the molten pool feature threshold range corresponding to different processing stages.

[0092] See Figure 3 As shown, the workpiece is processed based on the initialized laser processing parameters. The molten pool image, temperature data, and spectral data acquired by the high-speed camera, infrared sensor, and spectral sensor specifically include:

[0093] The high-speed camera captures real-time images of the molten pool at a frame rate of no less than 1000fps;

[0094] Infrared sensors collect temperature distribution data of the molten pool area at a sampling frequency of not less than 500Hz;

[0095] The spectral sensor acquires spectral data of molten pool plasma in the 200-1100 nm wavelength range;

[0096] The three types of data are synchronized by using a synchronous trigger signal to achieve data acquisition time alignment, thereby obtaining the molten pool image, temperature data, and spectral data corresponding to the same processing moment.

[0097] Referring to Figure 4 As shown, based on the collected data, the preprocessed data is fused by a weighted fusion algorithm to obtain fused comprehensive feature data of the molten pool, which specifically includes:

[0098] The collected molten pool image data is processed by a Gaussian filter algorithm to remove high-frequency noise, histogram equalization to improve the contrast between the molten pool and the background, and edge detection to obtain a clear molten pool contour image, and geometric feature parameters are calculated;

[0099] The infrared temperature measurement data is processed by removing data points outside the reasonable temperature range using the 3σ criterion, and smoothing to obtain molten pool center temperature and temperature gradient data;

[0100] Baseline correction and characteristic spectral line extraction are performed on the spectral data to obtain characteristic spectral line intensity and spectral line half-width data;

[0101] Based on the analytic hierarchy process, the weight values of each collected data are calculated, and the geometric feature data, temperature feature data and spectral feature data are fused by a weighted fusion algorithm to obtain comprehensive feature data of the molten pool.

[0102] Specifically, in the original spectral data, in addition to the characteristic spectral signals generated by the molten pool reaction, there is also baseline drift. A baseline correction algorithm such as a polynomial fitting baseline method is used to identify the baseline component in the spectrum, and then the baseline signal is subtracted from the original spectral data through mathematical operation to eliminate the influence of baseline drift, obtaining corrected spectral data containing only the characteristic spectrum of the molten pool;

[0103] The corrected spectral data is analyzed, and the corresponding characteristic spectral lines are located and extracted in the spectral curve according to the known characteristic spectral line wavelengths of the elements involved in the molten pool reaction. For example, if the molten pool contains iron elements, the spectral line peak at the wavelength position in the spectrum can be found according to the characteristic spectral line wavelength of iron;

[0104] For each extracted characteristic spectral line, its characteristic parameters are calculated, wherein the characteristic spectral line intensity is determined by measuring the maximum gray value of the spectral line peak, representing the strength of the characteristic spectral line; the spectral line half-width is measured at the half-height of the spectral line peak, reflecting the sharpness of the spectral line, and recording the characteristic spectral line intensity and spectral line half-width data;

[0105] A hierarchical structure model is constructed to clearly define the target, criteria and scheme layers of the analytic hierarchy. The target layer is to determine the weight of each collected data, which is used for fusion of the comprehensive feature data of the molten pool; the criteria layer is the key factor affecting the importance of the data, such as the accuracy of the data reflecting the molten pool state, the stability of the data collection, and the relevance of the data to the core features of the molten pool; the scheme layer is the three types of data whose weights need to be determined, namely the molten pool geometric feature data, the molten pool temperature feature data, and the molten pool spectral feature data;

[0106] According to the importance of each factor in the criterion layer, experts in the invitation field compare the relative importance of the three types of data in the scheme layer with each other, use the 1-9 scale method to construct a pairwise comparison judgment matrix, and ensure that the elements in the matrix meet the consistency requirements;

[0107] Single ordering and consistency test of hierarchy: calculate the maximum eigenvalue of the judgment matrix and the corresponding eigenvector, normalize the eigenvector to obtain the weight vector of the three types of data in the scheme layer relative to each factor in the criterion layer, and at the same time, calculate the consistency index, random consistency index and consistency ratio. If the consistency ratio is less than 0.1, it is considered that the judgment matrix meets the consistency requirements and the weight distribution is reasonable; if not, the experts need to adjust the judgment matrix again until the consistency requirements are met.

[0108] Referring to Figure 5 The obtained comprehensive molten pool feature data is compared with the normal molten pool feature library to determine whether the current molten pool feature is within the normal threshold range of the corresponding processing stage. If at least one molten pool feature data exceeds the normal threshold range, it is determined that the current molten pool state is abnormal, and the abnormal type is determined through feature matching, which specifically includes:

[0109] From the normal molten pool feature library, the reference data matching the current processing stage are selected, and the dimensional features of the current molten pool are compared with the normal feature range of the corresponding processing stage;

[0110] If all the comprehensive molten pool feature data is within the normal threshold range, it is determined that the current molten pool state is normal, and the processing continues;

[0111] If at least one molten pool feature data exceeds the normal threshold range, it is determined that the current molten pool state is abnormal;

[0112] Based on the feature dimension exceeding the normal range and the deviation direction, the abnormal type is identified, which includes molten pool overheating, molten pool overcooling, molten pool size being too large, molten pool size being too small, and plasma interference.

[0113] Specifically, through the control system of the processing equipment, the process flow record or real-time monitoring data such as processing time, completed work amount, process parameter setting, the specific processing stage of the current molten pool is determined; according to the determined current processing stage, the reference data corresponding to the stage are selected from the normal molten pool feature library, including the normal threshold range of the geometric feature, temperature feature and spectral feature of the molten pool in this stage, to form a list of reference features in the current stage;

[0114] The obtained comprehensive molten pool feature data is decomposed into geometric feature, temperature feature and spectral feature, and the specific parameters of each dimension are compared one by one according to the threshold range in the reference feature list of the current stage:

[0115] Geometric feature comparison: check whether the profile length, area, equivalent diameter, aspect ratio of the current molten pool are within the normal range of geometric features at this processing stage;

[0116] Temperature feature comparison: check whether the center temperature, temperature gradient of the current molten pool are within the normal range of temperature features at this processing stage;

[0117] Spectral feature comparison: check whether the intensity and half-width of each characteristic spectral line of the current molten pool are within the normal range of spectral features at this processing stage;

[0118] If the comparison result shows that all characteristic parameters of the current molten pool in all dimensions are within the normal threshold range corresponding to the reference feature list at the current stage, and none of the parameters exceeds the range, it is determined that the current molten pool state is normal, and no intervention is needed, and the processing equipment continues to process according to the original process parameters.

[0119] If the comparison result shows that at least one characteristic parameter of the current molten pool exceeds the corresponding normal threshold range, it is directly determined that the current molten pool state is abnormal, and the abnormal type identification process needs to be started immediately, and intervention measures are taken according to the subsequent results.

[0120] Referring to Figure 6 , the adjustment direction of the laser processing parameters is determined based on the matching determined abnormal type, and a multi-parameter collaborative optimization model is constructed, and the particle swarm optimization algorithm is used to iteratively optimize the processing parameters in the adjustment direction to obtain the optimal adjustment parameter set, which specifically includes:

[0121] Based on the matching determined abnormal type, the adjustment direction of the laser processing parameters is obtained;

[0122] Taking the regression of the molten pool features to the normal threshold range as the objective function, a multi-parameter collaborative optimization model is constructed in combination with the coupling relationship among the laser power, scanning speed and defocusing amount;

[0123] Based on the particle swarm optimization algorithm, an initial parameter adjustment scheme is generated, and the state change of the molten pool under this scheme is simulated. If the prediction result shows that the molten pool features do not meet the requirements, the parameters are fine-tuned based on the coupling relationship to generate a new adjustment scheme.

[0124] The processing parameters are repeatedly iteratively optimized until the parameter combination that makes the molten pool features return to the normal range is obtained, and the optimal adjustment parameter set is determined.

[0125] Specifically, according to the logic of the particle swarm optimization algorithm, the optimal adjustment parameter set is gradually obtained through the processes of generating an initial scheme, simulating and verifying, fine-tuning parameters, and repeated iteration. The particle position update formula in the particle swarm optimization algorithm is:

[0126]

[0127] in, Let be the velocity of the i-th particle in the d-th dimension. Let i be the position of the i-th particle in the d-th dimension. For inertial weights, , As a learning factor, , A random number in the range [0,1]. Let be the optimal position for the i-th particle. The globally optimal position;

[0128] Based on the previously identified types of molten pool anomalies, and combined with the correlation between laser processing parameters and molten pool characteristics, the parameter adjustment directions corresponding to each anomaly type are clarified, including the adjustment directions corresponding to molten pool overheating, molten pool undercooling, molten pool size being too large, molten pool size being too small, and plasma interference.

[0129] The objective function is defined as minimizing the sum of deviations between the current molten pool characteristic parameters and their corresponding normal threshold ranges. At the same time, the following constraints are set: the laser power must be within the rated power range of the equipment, the scanning speed must meet the processing efficiency requirements, and the defocusing amount must be within the adjustable range of the equipment.

[0130] Coupling of power and scanning speed: When the power is increased, if the scanning speed is increased simultaneously, some of the heat accumulation can be offset (avoiding overheating of the molten pool); when the power is decreased, if the scanning speed is decreased simultaneously, heat loss can be reduced. The two need to be adjusted in coordination to balance the heat input.

[0131] Coupling of power and defocus amount: High power with small defocus amount can easily lead to excessive energy concentration, so the defocus amount needs to be increased simultaneously; low power with large defocus amount can easily lead to insufficient energy, so the defocus amount needs to be reduced simultaneously. The two need to be matched to control energy density.

[0132] Coupling of scanning speed and defocus amount: High scanning speed with large defocus amount can easily lead to an excessively small molten pool size due to short action time and low energy density, so the defocus amount needs to be reduced simultaneously; Low scanning speed with small defocus amount can easily lead to overheating of the molten pool due to long action time and concentrated energy, so the defocus amount needs to be increased simultaneously. The two need to be coordinated to control the balance between molten pool diffusion and heat accumulation.

[0133] See Figure 7 As shown, the adjusted molten pool feature data is compared again with the normal molten pool feature library to determine whether the molten pool state has returned to normal. If the molten pool state is still abnormal, the parameter optimization adjustment process continues until the molten pool features return to the normal threshold range. Specifically, this includes:

[0134] The molten pool feature data adjusted based on the optimal adjustment parameter set is compared again with the normal molten pool feature library to determine whether the molten pool state returns to normal;

[0135] If all dimensional features are within the normal threshold range and the continuous frame fluctuation meets the stability requirement, it is determined that the molten pool state has returned to normal.

[0136] If any dimensional feature still exceeds the normal threshold or the continuous frame fluctuation is still unstable, it is determined that the molten pool state is still abnormal, the historical record of the last parameter adjustment is retrieved, and the historical record data is excluded in the repeated parameter optimization and adjustment process until the molten pool feature returns to the normal threshold range.

[0137] If the molten pool state has not returned to normal after three consecutive parameter adjustments, an alarm mechanism is triggered, the laser processing is suspended, and abnormal prompt information is output.

[0138] Specifically, the baseline data corresponding to the current processing stage is retrieved again from the normal molten pool feature library, and the newly collected molten pool feature data after adjustment is compared with the normal threshold range in the baseline data in a dimension-by-dimension comparison manner, and the specific value of each dimensional feature parameter and whether it is within the normal range are recorded.

[0139] If the molten pool state after adjustment does not meet the normal determination standard, a parameter optimization iteration process is started, the historical record of the last parameter optimization is retrieved from the device parameter adjustment log, including the last abnormal type, initial parameter combination, adjustment direction, and all generated parameter schemes, and is arranged into a historical parameter adjustment list to clearly define the parameter range and adjustment direction that have been tried to avoid repeated use of the same or similar parameter schemes in subsequent iterations and improve optimization efficiency.

[0140] Based on the current existing abnormal type and in combination with the historical parameter adjustment list, the parameter combination range that has been tried is excluded when constructing a new multi-parameter collaborative optimization model to generate a completely new initial parameter adjustment scheme.

[0141] The newly generated parameter scheme is simulated and verified, fine-tuned and optimized according to the process of constructing a multi-parameter collaborative optimization model, particle swarm optimization algorithm iteration optimization and determining an optimal adjustment parameter set to determine a new optimal adjustment parameter set, then adjust the device parameters, collect the molten pool feature data, compare it with the normal feature library, and repeat the above cycle until all dimensional features of the molten pool return to the normal threshold range and the continuous frame fluctuation is stable.

[0142] Referring to Figure 8 During laser processing, processing data is recorded in real time to form a processing process database, and after processing is completed, the normal molten pool sample data in the database is updated and supplemented through an incremental learning algorithm, specifically including:

[0143] In the laser processing process, the processing time, workpiece position, molten pool characteristic data, adjusted processing parameters and processing quality detection results are recorded in real time to form a processing process database;

[0144] After the processing is completed, normal molten pool samples that can be used to update the feature library are screened to supplement the database;

[0145] Based on the initial normal molten pool feature library, new samples are integrated in an incremental learning manner, and after updating the feature library, the normal threshold of each dimension is fine-tuned and optimized.

[0146] Specifically, after all new samples are integrated into the model, the distribution of molten pool features in each processing stage is re-counted based on the output of the updated model, the original sample data of each processing stage is replaced, and the normal threshold range of each dimension feature is fine-tuned based on the new statistical results. If there is a small deviation between the statistical range of a certain feature parameter of the new sample and the initial threshold, the threshold is adjusted in the intersection of the initial threshold and the statistical range of the new sample + reasonable expansion. If the distribution of the feature parameters of the new sample is significantly different from the initial threshold, the processing quality detection results and the opinions of process experts need to be combined to determine whether the normal range is shifted due to changes in equipment state and materials, and then the adjustment range of the threshold is determined to ensure that the adjusted threshold is consistent with the current processing reality and can effectively distinguish between normal and abnormal molten pools;

[0147] After the threshold fine-tuning is completed, the updated normal molten pool feature library is verified: samples in the library are randomly selected, and it is checked whether their feature parameters are within the adjusted threshold range. At the same time, combined with historical processing quality data, it is confirmed that the threshold can accurately correspond to the qualified processing quality. After verification, the updated feature library is saved for subsequent molten pool state determination in laser processing.

[0148] It should be noted that the above-mentioned order of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. The above describes a specific embodiment of the present application. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or may be advantageous.

[0149] Each embodiment in the present specification is described in a progressive manner, and the same or similar parts of each embodiment can be referred to each other. Each embodiment focuses on the differences from other embodiments.

[0150] The above only describes the preferred embodiments of the present application, and does not limit the present application. Any modification, equivalent replacement, improvement, etc. made within the principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method of adaptive laser processing control based on real-time molten pool monitoring, characterized in that, The method comprises the following steps: acquiring workpiece parameter data and normal molten pool sample data under different processing parameter combinations, and initializing laser processing parameters to construct a normal molten pool feature library; processing the workpiece based on the initialized laser processing parameters, and collecting molten pool images, temperature data and spectral data collected by a high-speed camera, an infrared sensor and a spectral sensor; preprocessing the collected data, fusing the preprocessed data through a weighted fusion algorithm, and acquiring fused molten pool comprehensive feature data; comparing the acquired molten pool comprehensive feature data with the normal molten pool feature library to determine whether the current molten pool features are within the normal threshold range of the corresponding processing stage, and if at least one molten pool feature data is outside the normal threshold range, determining that the current molten pool state is abnormal and determining the abnormal type through feature matching; acquiring the adjustment direction of the laser processing parameters based on the matched abnormal type; taking the regression of the molten pool features to the normal threshold range as an objective function, and constructing a multi-parameter collaborative optimization model in combination with the coupling relationship among laser power, scanning speed and defocusing amount; based on the particle swarm optimization algorithm, generating an initial parameter adjustment scheme, simulating the state change of the molten pool under the scheme, and if the prediction result shows that the molten pool features do not meet the standard, fine-tuning the parameters based on the coupling relationship to generate a new adjustment scheme; repeatedly iterating and optimizing the processing parameters until a parameter combination that makes the molten pool features return to the normal range is obtained, and determining the optimal adjustment parameter combination; comparing the adjusted molten pool feature data with the normal molten pool feature library again to determine whether the molten pool state has returned to normal, and if the molten pool state is still abnormal, adjusting the parameter optimization process until the molten pool features return to the normal threshold range; During the laser processing, processing data is recorded in real time to form a processing process database, and after the processing is completed, the normal molten pool sample data in the database is updated and supplemented through an incremental learning algorithm.

2. The adaptive laser processing control method based on real-time molten pool monitoring according to claim 1, characterized in that, The acquisition of the workpiece parameter data and the normal molten pool sample data under different processing parameter combinations, and the initialization of the laser processing parameters to construct the normal molten pool feature library specifically comprises: The workpiece parameter data includes material properties, thickness dimensions and processing targets; The normal molten pool sample data includes geometric features, temperature features and spectral features; The laser processing parameters include initial laser power, initial scanning speed, initial defocusing amount and protective gas flow; The normal molten pool feature library is constructed by training the normal molten pool sample data through a machine learning algorithm, and the feature library contains molten pool feature threshold ranges corresponding to different processing stages.

3. The adaptive laser processing control method based on real-time molten pool monitoring according to claim 1, characterized in that, The processing of the workpiece based on the initialized laser processing parameters, and the acquisition of the molten pool images, temperature data and spectral data collected by the high-speed camera, the infrared sensor and the spectral sensor specifically comprises: The high-speed camera collects real-time molten pool images at a frame rate of not less than 1000 fps; The infrared sensor collects temperature distribution data of the molten pool area at a sampling frequency of not less than 500 Hz; The spectral sensor collects plasma spectral data of the molten pool in a wavelength range of 200-1100 nm; The three collected data are aligned in time by a synchronous trigger signal to obtain the molten pool image, temperature data and spectral data corresponding to the same processing moment.

4. The adaptive laser processing control method based on real-time molten pool monitoring according to claim 1, characterized in that, The preprocessing based on the collected data and the fusion of the preprocessed data by a weighted fusion algorithm to obtain the fused molten pool comprehensive feature data specifically include: The collected molten pool image data are processed by a Gaussian filtering algorithm to remove high-frequency noise, histogram equalization to improve the contrast of the molten pool and background, and edge detection to obtain a clear molten pool contour image and calculate geometric feature parameters; The infrared temperature measurement data are processed by a 3σ criterion to remove data points outside the reasonable temperature range and smoothing processing to obtain the molten pool center temperature and temperature gradient data; The spectral data are baseline corrected and feature spectral line extracted to obtain feature spectral line intensity and spectral line half-width data; The weight values of the collected data are calculated based on the analytic hierarchy process, and the geometric feature data, temperature feature data and spectral feature data are fused by a weighted fusion algorithm to obtain the molten pool comprehensive feature data.

5. The adaptive laser processing control method based on real-time molten pool monitoring according to claim 1, characterized in that, The obtained molten pool comprehensive feature data are compared with the normal molten pool feature library to determine whether the current molten pool feature is within the normal threshold range of the corresponding processing stage. If at least one molten pool feature data is outside the normal threshold range, it is determined that the current molten pool state is abnormal, and the abnormal type is determined by feature matching, which specifically includes: From the normal molten pool feature library, the reference data matching the current processing stage are selected, and the dimensions of the current molten pool are compared with the normal feature range of the corresponding processing stage; If all the molten pool comprehensive feature data are within the normal threshold range, it is determined that the current molten pool state is normal, and the processing continues; If at least one molten pool feature data is outside the normal threshold range, it is determined that the current molten pool state is abnormal; Based on the feature dimensions outside the normal range and the deviation direction, the abnormal type is identified. The abnormal types include molten pool overheating, molten pool overcooling, molten pool size being too large, molten pool size being too small and plasma interference.

6. The adaptive laser processing control method based on real-time molten pool monitoring according to claim 1, characterized in that, The molten pool feature data adjusted based on the adjusted molten pool feature data are compared with the normal molten pool feature library again to determine whether the molten pool state has returned to normal. If the molten pool state is still abnormal, the parameter optimization adjustment process is repeated until the molten pool feature returns to the normal threshold range, which specifically includes: The molten pool feature data adjusted based on the optimal adjustment parameter set are compared with the normal molten pool feature library again to determine whether the molten pool state has returned to normal; If all the dimensional features are within the normal threshold range and the continuous frame fluctuation meets the stability requirement, it is determined that the molten pool state has returned to normal; If any dimensional feature is still outside the normal threshold or the continuous frame fluctuation is still unstable, it is determined that the molten pool state is still abnormal. The historical record of the last parameter adjustment is retrieved, and the historical record data are excluded in the repeated parameter optimization and adjustment process until the molten pool feature returns to the normal threshold range; If the molten pool state has not returned to normal after three consecutive parameter adjustments, the alarm mechanism is triggered, the laser processing is paused and the abnormal prompt information is output.

7. The adaptive laser processing control method based on real-time molten pool monitoring according to claim 1, characterized in that, The processing data is recorded in real time during the laser processing process to form a processing process database, and after the processing is completed, the normal molten pool sample data in the database is updated and supplemented through an incremental learning algorithm, and the specific method comprises the following steps: During the laser processing process, the processing time, workpiece position, molten pool feature data, adjusted processing parameters and processing quality detection results are recorded in real time to form a processing process database; After the processing is completed, normal molten pool samples that can be used to update the feature library are selected to supplement the database; Based on the initial normal molten pool feature library, new samples are integrated in an incremental learning manner, and after updating the feature library, the normal threshold of each dimension is fine-tuned and optimized.

8. Adaptive laser processing control system based on real-time molten pool monitoring for implementing the adaptive laser processing control method based on real-time molten pool monitoring according to any one of claims 1 to 7, characterized in that It comprises: A laser processing module: the module is used to output a laser beam and process a workpiece; A molten pool monitoring module: the module synchronously collects molten pool images, temperature and spectral data through a high-speed camera, an infrared sensor and a spectral sensor; A data preprocessing module: the module filters, denoises, aligns and extracts features of the original data to generate geometric, temperature and spectral feature parameters; A feature fusion module: the module weightedly fuses multi-source feature data based on an analytic hierarchy process to output a molten pool comprehensive feature vector; An abnormality detection module: the module compares real-time molten pool features with feature library thresholds to identify molten pool overheating and size abnormality fault types; A parameter optimization module: the module constructs a multi-parameter collaborative optimization model and generates an optimal adjustment scheme of laser power and speed parameters by using a particle swarm optimization algorithm; A real-time control module: the module dynamically adjusts laser processing parameters and feeds back the molten pool state after adjustment to the abnormality detection module for closed-loop verification; A data storage and learning module: the module is used to record processing process data and update normal molten pool feature library threshold ranges through incremental learning; A processor: the processor is used to process the calculation process of each formula and the construction and calculation process of each model.

Images