A laser space-time parameter intelligent optimization method, system, device and medium

Abstract

This invention belongs to the field of laser data processing technology, specifically relating to a method, system, device, and medium for intelligent optimization of laser spatiotemporal parameters. The method includes the following steps: setting a processing target and simultaneously inputting material properties and initial laser parameters to provide a data foundation for controlling the laser spatiotemporal parameters; establishing a physical model library and a mapping database, where the physical model library describes the degree of change in material properties under laser irradiation, and the mapping database is a relational database constructed based on historical laser processing data and physical model simulation results; and establishing an AI optimization engine including machine learning prediction models and optimization algorithms to incorporate the physical model simulation results. This invention constructs a closed-loop control process combining physical models, real-time monitoring, and AI optimization algorithms to actively control the shape of femtosecond laser pulses to regulate the electron dynamics within the material, thereby optimizing micro / nano processing results.

Description

Technical Field

[0001] This invention belongs to the field of laser data processing technology, specifically relating to a method, system, device, and medium for intelligent optimization of laser spatiotemporal parameters. Background Technology

[0002] Femtosecond laser processing can achieve structure manufacturing with a resolution of less than 1μm or even 0.3nm, which is crucial for applications such as manufacturing micro-holes, precision cutting lines, high aspect ratio slits, and engraving complex surface terrain. It is a micro-nano processing that is difficult or impossible to achieve with traditional methods.

[0003] Current laser process parameters are generally controlled in multiple stages using a PID (Proportional-Integral-Derivative) controller. This involves acquiring the time series of error signals from the laser system in real time, inputting it into a trained deep learning model, and outputting a frequency-locked state score and fast / slow dual-loop PID parameters. These parameters are compared with preset conditions, and the deep learning model is iteratively optimized until the corresponding preset conditions are met. The optimized deep learning model is then output to the PID controller, achieving intelligent control of the laser system's process parameters. However, in practical laser parameter processing, while deep learning models can optimize process parameters, their optimization scope only considers and focuses on the laser parameters themselves, neglecting the varying degrees of influence of laser-induced electron dynamics on different materials. This makes it difficult to meet the precise mapping requirements of multi-parameter coupling relationships in the fabrication of complex micro / nano structures. Summary of the Invention

[0004] The purpose of this invention is to provide a method, system, device, and medium for intelligent optimization of laser spatiotemporal parameters. This method can construct a closed-loop control process that combines physical models, real-time monitoring, and AI optimization algorithms to actively control the shape of femtosecond laser pulses to regulate the electronic dynamics within the material, thereby optimizing the micro-nano fabrication results.

[0005] The specific technical solution adopted by this invention is as follows: A method for intelligent optimization of laser spatiotemporal parameters includes the following steps: Set the processing target and input the material properties and initial laser parameters to provide a data basis for the control of laser spatiotemporal parameters; A physical model library and a mapping database are established. The physical model library is used to describe the degree of change in the material properties of the material under laser irradiation. The mapping database is a related database constructed based on historical laser processing data and physical model simulation results. An AI optimization engine is established, which includes a machine learning prediction model and an optimization algorithm. The simulation results of the physical model, the laser parameter vector, and the material property vector are input into the machine learning prediction model, and the predicted processing results are output. The optimal parameter combination is obtained after optimization by the optimization algorithm. The optimal parameter combination output by the AI ​​optimization engine is converted into PID control instructions and sent to the laser processing equipment to monitor the laser processing of the material. The monitoring results are transmitted as feedback data to the AI ​​optimization engine. After comparison with the processing target, a parameter update strategy is given based on the comparison results to realize the feedback closure of the AI ​​optimization engine. Set database update rules so that each processed data is used to update the AI ​​optimization engine, thereby improving the prediction accuracy and optimization efficiency of the AI ​​optimization engine.

[0006] As an optional solution, the physical model library includes: Electron dynamics model is used to predict electron excitation and temperature changes inside materials under different laser pulse shapes; Molecular dynamics models are used to predict material phase transition processes, including melting, ablation, and resolidification phase transitions. Plasma models are used to predict the possible ionization and plasma formation processes of materials when exposed to lasers. A two-temperature model is used to predict the electron-lattice energy transfer process when materials are subjected to laser irradiation.

[0007] As an alternative, the processing objectives include specifying the morphology required for crystal processing, microchannels with a specific aspect ratio, a substrate with a high SERS enhancement factor, nanowires with specific conductivity, taper-free micropores, and high etching rates.

[0008] As an alternative, the material properties include band structure, thermal conductivity, and plasma frequency, which serve as the data basis for the physical model.

[0009] As an optional approach, the initial laser parameters include center wavelength, pulse width range, and energy range, which are used by the AI ​​algorithm to combine the physical model with historical laser processing data to select the laser spatiotemporal parameters that best match the processing target.

[0010] As an optional approach, monitoring the laser processing of the material includes: Laser-induced breakdown spectroscopy is performed to analyze plasma composition and indirectly reflect the material removal status. Perform rapid imaging detection to observe changes in the surface morphology of materials or plasma luminescence during laser processing; Finally, a feedback loop is established, where the monitored laser processing process signals or final measurement results are transmitted as feedback data to the AI ​​optimization engine. The AI ​​optimization engine compares the feedback data with the processing target and provides a parameter update strategy based on the comparison results.

[0011] As an optional solution, the database update rules include: Each successful processing attempt and its data are used to update the AI ​​optimization engine and physics model library; By continuously learning the optimal parameter combinations for subsequent materials and processing targets, the prediction accuracy and optimization efficiency of the AI ​​optimization engine can be improved, enabling intelligent automatic adjustment of laser spatiotemporal parameters.

[0012] A laser spatiotemporal parameter intelligent optimization system includes the following components: The data input module is used to set the processing target, material properties, and initial laser parameters, providing a data basis for the control of laser spatiotemporal parameters. The database is used to establish a physical model library and a mapping database. The physical model library is used to describe the degree of change of the material properties of the material itself under laser irradiation. The mapping database is a related database constructed based on historical laser processing data and the simulation results of the physical model. The AI ​​computing module is used to establish an AI optimization engine that includes a machine learning prediction model and an optimization algorithm. It inputs the physical model simulation results, laser parameter vectors and material property vectors into the machine learning prediction model, outputs the predicted processing results, and obtains the optimal parameter combination after optimization by the optimization algorithm. The feedback module is used to convert the optimal parameter combination output by the AI ​​optimization engine into PID control instructions and send them to the laser processing equipment. It monitors the laser processing of the material, transmits the monitoring results as feedback data to the AI ​​optimization engine, compares them with the processing target, and gives a parameter update strategy based on the comparison results, thereby realizing the feedback closure of the AI ​​optimization engine. The data update module is used to set database update rules and use each processed data to update the AI ​​optimization engine, thereby improving the prediction accuracy and optimization efficiency of the AI ​​optimization engine.

[0013] A computer-readable medium for storing program code for executing the intelligent optimization method for laser spatiotemporal parameters of the present invention.

[0014] An electronic device, the electronic device comprising: At least one processor; and a memory communicatively connected to the at least one processor; The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the laser spatiotemporal parameter intelligent optimization method, system, device and medium.

[0015] The technical effects achieved by this invention are as follows: This invention modulates the electronic dynamics within materials by actively controlling the shape (time and space) of femtosecond laser pulses, thereby optimizing micro-nano fabrication results. By automatically adjusting the laser spatiotemporal parameters through a preset AI optimization algorithm, a closed-loop control process combining physical models, real-time monitoring, and AI optimization algorithms can be constructed.

[0016] This invention enables the integration of a laser spatiotemporal parameter intelligent optimization system into existing laser processing equipment. By combining AI optimization algorithms with a robust physical model library, it utilizes electronic dynamics models, molecular dynamics models, plasma models, and dual-temperature models as constraints and prior knowledge, avoiding purely "black box" learning and improving efficiency and interpretability. Ultimately, this invention serves the user; the user only needs to set the processing target and material, and the AI ​​optimization algorithm can automatically find and execute the optimal laser parameter scheme, achieving high-quality, high-efficiency, and highly repeatable micro- and nano-processing. Attached Figure Description

[0017] Figure 1 This is a system block diagram of the control signal transmission state of the intelligent optimization system for laser spatiotemporal parameters in Embodiment 1 of the present invention; Figure 2 This is a flowchart of the intelligent optimization method for laser spatiotemporal parameters in Embodiment 2 of the present invention; Figure 3 This is a statistical graph of the calculation results of the electronic dynamic model in Embodiment 2 of the present invention; Figure 3 a) is a statistical graph of the calculation results from the traditional electronic dynamical model; Figure 3 (b) is a statistical graph of the calculation results of the electronic dynamic model of the present invention; Figure 4 This is a schematic diagram of the electronic device in Embodiment 2 of the present invention.

[0018] The components represented by each number in the attached diagram are as follows: 1. Data input module; 2. Database; 3. AI calculation module; 4. Feedback module; 5. Data update module. Detailed Implementation

[0019] To make the objectives and advantages of this invention clearer, the invention will be specifically described below with reference to embodiments. It should be understood that the following text is merely used to describe one or more specific embodiments of the invention and does not strictly limit the scope of protection specifically claimed by the invention.

[0020] Example 1: like Figure 1 As shown, a laser spatiotemporal parameter intelligent optimization system includes: Data input module 1 is used to set the processing target, material properties and initial laser parameters, providing a data basis for the control of laser spatiotemporal parameters; Database 2 is used to establish a physical model library and a mapping database. The physical model library is used to describe the degree of change of the material properties of the material itself under laser irradiation. The mapping database is a related database constructed based on historical laser processing data and physical model simulation results. AI computing module 3 is used to establish an AI optimization engine that includes a machine learning prediction model and an optimization algorithm. It inputs the physical model simulation results, laser parameter vectors and material property vectors into the machine learning prediction model, outputs the predicted processing results, and obtains the optimal parameter combination after optimization by the optimization algorithm. Feedback module 4 is used to convert the optimal parameter combination output by the AI ​​optimization engine into PID control instructions and send them to the laser processing equipment to monitor the laser processing of the material. The monitoring results are transmitted as feedback data to the AI ​​optimization engine. After comparing with the processing target, a parameter update strategy is given according to the comparison results to realize the feedback closure of the AI ​​optimization engine. The data update module 5 is used to set database update rules, and to use each processed data to update the AI ​​optimization engine, thereby improving the prediction accuracy and optimization efficiency of the AI ​​optimization engine.

[0021] Example 2: like Figures 2-4 As shown, an intelligent optimization method for laser spatiotemporal parameters is applied to the intelligent optimization system for laser spatiotemporal parameters provided in Example 1. This example uses the processing of SiC materials as an example. Its core idea is to actively control the shape (time and space) of the femtosecond laser pulse to regulate the energy-dependent calibration within the SiC material, thereby optimizing the micro-nano processing results. By automatically adjusting the laser spatiotemporal parameters through a preset AI algorithm, a closed-loop control process combining a physical model, real-time monitoring, and AI algorithms can be constructed. This intelligent optimization method includes the following steps: Target definition and input: Before material processing, the processing target is pre-set, and the material properties and initial laser parameters are input to provide a data foundation for the control of laser spatiotemporal parameters. Specifically, this includes the following: Processing target setting: After the material arrives, the staff pre-specifies the processing target on the industrial control computer of the laser processing station. This includes specifying the morphology required for crystal processing, microchannels with a specific aspect ratio, substrates with high SERS (Surface-Enhanced Raman Scattering) enhancement factor, nanowires with specific conductivity, non-tapered micropores, high etching rate, etc. This processing target is used to guide the AI ​​algorithm to screen the initial laser parameters based on the material properties. At the same time, it combines the historical laser processing data of the corresponding material to obtain a set of laser spatiotemporal parameters that meet the processing target, so that the AI ​​algorithm can automatically adjust the laser spatiotemporal parameters in subsequent laser processing. Material property input: Input the known physical properties of the material to be processed, including band structure, thermal conductivity, plasma frequency, etc., to provide the data foundation for the physical model and facilitate the AI ​​algorithm to fully understand the material properties; Initial laser parameters: Input the initial laser parameters, including center wavelength, pulse width range, energy range, etc. These laser parameters can be a large range of values ​​or multiple dispersed ranges of values, so that the AI ​​algorithm can select the laser spatiotemporal parameters that best match the processing target based on the above range of values, combined with the physical model and historical laser processing data. It should be noted that the set of laser spatiotemporal parameters can be within the above range of values, or can be partially or completely outside the above range of values. Physical Models and Databases: First, a physical model library is established to describe the degree of change in material properties under laser irradiation. This physical model library includes: An electronic dynamic model is used to predict the electronic excitation and temperature changes inside materials under different laser pulse shapes (energy distribution, time-delayed sub-pulses). The evolution of electron density and temperature is described by the following formulas (1) and (2): Formula (1) Formula (2) in, This indicates the calculation of partial derivatives. Represents the density of free electrons. Indicates electron temperature, Indicates lattice temperature, This indicates the electron generation rate generated by laser excitation. Indicates electron position, , Indicates the electron recombination rate. Indicates the electron diffusion coefficient. Indicates the material absorption coefficient. This represents the spatiotemporal distribution of laser intensity. Indicates electron heat capacity, Indicates the electron-lattice relaxation time. Indicates electron heat; At this point, in this embodiment, 0.2 J / m 2 Taking the processing of a 200nm gold film by a laser beam irradiated with a 140fs, 1053nm laser pulse as an example, Figure 3 As shown, the electron temperature and phonon temperature are recorded respectively. Under the calculation of the traditional electron dynamics model and the electron dynamics model of this embodiment, the calculation results are fitted as shown in Figure a) and b) respectively. Molecular dynamics models are used to predict material phase transition processes, including melting, ablation, and resolidification, and are calculated using the following formula (3): Formula (3) in, Indicates the first The mass of an atom , Indicates atomic position, This represents the interatomic potential energy function. To represent differentiation, for example , wait; The plasma model is used to predict the possible ionization and plasma formation processes of materials when subjected to laser irradiation, and is calculated using the following formula (4): Formula (4) in, Indicates the laser-induced ionization rate. Indicates the electron-ion recombination coefficient. Indicates the electron diffusion loss coefficient; The two-temperature model (or improved model) is used to predict the electron-lattice energy transfer process of materials under laser irradiation, and is calculated using the following formulas (5) and (6): Formula (5) Formula (6) in, Indicates lattice temperature, Indicates lattice heat capacity, Represents the electron-lattice coupling coefficient. Indicates the laser source term, and at the same time, ; Secondly, a mapping database of "laser parameters-electron dynamics-processing results" is established. Based on historical laser processing data (e.g., data instances after laser processing of materials of different sizes) and physical model simulation results, an associated database is constructed. AI optimization engine: This invention constructs a machine learning prediction model driven by historical laser processing data to directly establish a complex mapping of "laser parameters - material properties - processing results". This mapping relationship can be represented by formula (7), thereby avoiding the difficulties of explicit physical modeling, capturing the hidden interactions between parameters, and predicting the processing results with a much higher accuracy than traditional empirical formulas. The trained model can provide predictions in milliseconds, providing a foundation for online monitoring and real-time control. Formula (7) is as follows: Formula (7) in, This indicates the predicted processing result. The parameter is Neural network or machine learning model, This represents a vector of laser parameters, such as energy, pulse width, and time-varying control parameters. Represents a material property vector. The characteristics of the electron dynamic state can be obtained from the output of the physical model; Meanwhile, an optimization algorithm is given. Based on the machine learning prediction model and the processing target set by the user, the optimal combination of laser parameters, including center wavelength, pulse width, total energy, time-shaping sequence, spatial light modulator phase diagram, etc., is searched using optimization algorithms (such as reinforcement learning, Bayesian optimization, evolutionary algorithm, etc.). The optimization algorithm is expressed in the following formulas (8) and (9): Formula (8) Formula (9) in, Describe the objective function. This represents a function for evaluating processing quality. This indicates processing costs (such as time and energy consumption). This indicates the preset weighting coefficient. Indicates being bound by, The feasible region representing the laser parameters; At this point, the output of the machine learning prediction model is constrained by the feasible region of the laser parameters to obtain the optimal parameter combination, which can then be used as the output of the laser spatiotemporal parameters. Automatic adjustment and execution of laser parameters: 1.1 Control command generation: Convert the optimal parameter combination output by the AI ​​optimization engine into specific PID control commands; 1.2 Hardware Control: PID control commands are sent to the laser control system (adjusting energy and pulse width), pulse shaper (adjusting temporal shape), and spatial light modulator (adjusting spatial shape to generate double peaks, Bessel beams, etc.). This embodiment is also applicable to existing laser processing equipment, such as the MJ-Works ultrafast laser micro-nano processing center, which can modify or etch the interior and surface of glass, optical fiber, and crystal. It can also process hard materials such as metals, alloys, and ceramics with micron-level precision, including drilling, surface structure treatment, selective laser ablation, modification, and other functions. Real-time monitoring and feedback: Monitoring the laser processing of materials involves real-time or in-situ monitoring using pre-defined diagnostic protocols, including: 2.1 Laser-Induced Breakdown Spectroscopy (LIBS) Detection: Analyzes plasma composition to indirectly reflect the material removal status; 2.2. Charge-Coupled Device (CCD) Inspection: Observing changes in the surface morphology of materials or plasma luminescence during laser processing; After processing, key indicators of the actual laser processing results can be obtained by means of microscopic imaging (Scanning Electron Microscope, SEM; Atomic Force Microscope, AFM), electrical testing, and optical testing (such as Surface-Enhanced Raman Scattering, SERS measurement). 2.3 Feedback closed loop: The monitored process signal of laser processing or the final measurement result is used as feedback data and transmitted to the AI ​​optimization engine. The AI ​​optimization engine compares the feedback data with the processing target and gives a parameter update strategy based on the comparison result. The expression forms are as follows: Formula (10) and Formula (11): Formula (10) Formula (11) in, Indicates the first The actual measurement results of this experiment This represents the prediction result of the machine learning prediction model. Represents the loss function. This represents the regularization term, used to prevent overfitting. Represents the regularization coefficient. Indicates the learning rate. This indicates that the neural network or machine learning model is in The parameters of this experiment; Iterative learning and system improvement: 3.1 Database Update: Preset database update rules, use each successful processing attempt and its data (failed processing data can also be included in the reference range) to update the AI ​​optimization engine and physical model library, specifically expressed in the following formula (12): Formula (12) in, Indicates the first The database after the next iteration This represents a complete data record after one processing step. 3.2 The system continuously learns the optimal parameter combinations under new materials and new targets, improves the prediction accuracy and optimization efficiency of the AI ​​optimization engine, and achieves increasingly intelligent automatic parameter adjustment.

[0022] This embodiment also provides a computer-readable medium for storing program code for executing the intelligent optimization method for laser spatiotemporal parameters according to the present invention.

[0023] This embodiment also provides an electronic device, see [link to documentation]. Figure 3 The electronic device includes: At least one processor; and memory that is communicatively connected to at least one processor; The memory stores a computer program that can be executed by at least one processor, which enables the at least one processor to execute the intelligent optimization method for laser spatiotemporal parameters.

[0024] The processors in the aforementioned electronic devices can be of various types, such as CPUs, GPUs, or TPUs, to adapt to different computing needs and ensure efficient processing of multidimensional and complex data. The memory can be of various types, such as RAM, ROM, or SSDs, to store large amounts of data, support fast read and write operations, and ensure stable system operation. In addition, the electronic devices are equipped with high-precision sensors to monitor environmental changes in real time, ensuring the accuracy and timeliness of data acquisition, as well as arithmetic units, input devices, and output devices. The arithmetic unit can be an FPGA or ASIC, responsible for high-speed parallel computing. Input devices such as keyboards and touch screens facilitate operation, while output devices such as displays and printers intuitively display the results. The entire system works collaboratively to improve the response speed and decision support capabilities of the laser spatiotemporal parameter intelligent optimization method.

[0025] Embodiments of the present invention are described with reference to flowchart illustrations and / or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0026] The aforementioned computer program instructions may also be stored in a computer-readable storage medium capable of directing a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0027] The aforementioned computer program instructions can also be loaded onto a computer or other programmable data processing terminal equipment, causing a series of operational steps to be executed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0028] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element. The above descriptions are merely optional embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention. Structures, devices, and operating methods not specifically described and explained in this invention are implemented according to conventional means in the art unless otherwise specified or limited.

Claims

1. A method for intelligent optimization of laser spatiotemporal parameters, characterized in that, Includes the following steps: Set the processing target and input the material properties and initial laser parameters to provide a data basis for the control of laser spatiotemporal parameters; A physical model library and a mapping database are established. The physical model library is used to describe the degree of change of the material properties of the material under laser irradiation. The mapping database is a related database constructed based on historical laser processing data and physical model simulation results. An AI optimization engine is established, which includes a machine learning prediction model and an optimization algorithm. The simulation results of the physical model, the laser parameter vector, and the material property vector are input into the machine learning prediction model, and the predicted processing results are output. The optimal parameter combination is obtained after optimization by the optimization algorithm. The optimal parameter combination output by the AI ​​optimization engine is converted into PID control instructions and sent to the laser processing equipment to monitor the laser processing of the material. The monitoring results are transmitted as feedback data to the AI ​​optimization engine. After comparison with the processing target, a parameter update strategy is given based on the comparison results to realize the feedback closure of the AI ​​optimization engine. Set database update rules so that each processed data is used to update the AI ​​optimization engine, thereby improving the prediction accuracy and optimization efficiency of the AI ​​optimization engine.

2. The intelligent optimization method for laser spatiotemporal parameters according to claim 1, characterized in that: The physical model library includes: Electron dynamics model is used to predict electron excitation and temperature changes inside materials under different laser pulse shapes; Molecular dynamics models are used to predict material phase transition processes, including melting, ablation, and resolidification phase transitions. Plasma models are used to predict the possible ionization and plasma formation processes of materials when exposed to lasers. A two-temperature model is used to predict the electron-lattice energy transfer process when materials are subjected to laser irradiation.

3. The intelligent optimization method for laser spatiotemporal parameters according to claim 1, characterized in that: Monitoring the laser processing of the material includes: Laser-induced breakdown spectroscopy is performed to analyze plasma composition and indirectly reflect the material removal status. Perform rapid imaging detection to observe changes in the surface morphology of materials or plasma luminescence during laser processing; Finally, a feedback loop is established, where the monitored laser processing process signals or final measurement results are transmitted as feedback data to the AI ​​optimization engine. The AI ​​optimization engine compares the feedback data with the processing target and provides a parameter update strategy based on the comparison results.

4. The intelligent optimization method for laser spatiotemporal parameters according to claim 1, characterized in that: The database update rules include: Each successful processing attempt and its data are used to update the AI ​​optimization engine and physics model library; By continuously learning the optimal parameter combinations for subsequent materials and processing targets, the prediction accuracy and optimization efficiency of the AI ​​optimization engine can be improved, enabling intelligent automatic adjustment of laser spatiotemporal parameters.

5. The intelligent optimization method for laser spatiotemporal parameters according to claim 1, characterized in that: The processing objectives include specifying the morphology required for crystal processing, microchannels with a specific aspect ratio, substrates with high SERS enhancement factors, nanowires with specific conductivity, taper-free micropores, and high etching rates.

6. The intelligent optimization method for laser spatiotemporal parameters according to claim 1, characterized in that, The material properties, including band structure, thermal conductivity, and plasma frequency, serve as the data basis for the physical model.

7. The intelligent optimization method for laser spatiotemporal parameters according to claim 1, characterized in that, The initial laser parameters include center wavelength, pulse width range, and energy range, which are used by the AI ​​algorithm to select the laser spatiotemporal parameters that best match the processing target by combining the physical model with historical laser processing data.

8. A laser spatiotemporal parameter intelligent optimization system, applied to the laser spatiotemporal parameter intelligent optimization method according to any one of claims 1-7, characterized in that, Includes the following parts: The data input module (1) is used to set the processing target, material properties and initial laser parameters, providing a data basis for the control of laser spatiotemporal parameters; Database (2) is used to establish a physical model library and a mapping database. The physical model library is used to describe the degree of change of the material properties of the material under laser action. The mapping database is based on historical data of laser processing and simulation results of the physical model to build an associated database. AI computing module (3) is used to establish an AI optimization engine that includes a machine learning prediction model and an optimization algorithm. It inputs the physical model simulation results, laser parameter vector and material property vector into the machine learning prediction model, outputs the predicted processing results, and obtains the optimal parameter combination after optimization by the optimization algorithm. Feedback module (4) is used to convert the optimal parameter combination output by the AI ​​optimization engine into PID control instructions and send them to the laser processing equipment to monitor the laser processing process of the material. The monitoring results are transmitted to the AI ​​optimization engine as feedback data. After comparing with the processing target, a parameter update strategy is given according to the comparison results to realize the feedback closure of the AI ​​optimization engine. The data update module (5) is used to set database update rules and use each processed data to update the AI ​​optimization engine, thereby improving the prediction accuracy and optimization efficiency of the AI ​​optimization engine.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and a memory communicatively connected to the at least one processor; The memory stores a computer program that can be executed by the at least one processor, which is then executed by the at least one processor to enable the at least one processor to perform the laser spatiotemporal parameter intelligent optimization method according to any one of claims 1 to 7.

10. A computer-readable medium, characterized in that: The computer-readable medium is used to store program code for executing the laser spatiotemporal parameter intelligent optimization method according to any one of claims 1 to 7.

Images