A structured management method and system for various laser deposition process data

By constructing a structured coupling of basic process feature sets and dynamic process feature sets, the problems of data dispersion and low retrieval efficiency in laser deposition data management are solved, realizing unified storage and intelligent retrieval of various process data, and adapting to various laser deposition processes.

CN123115231APending Publication Date: 2026-11-17YANQIHU BASIC MFG TECH RES INST (BEIJING) CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202611389598.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-09-08
Publication Date
2026-11-17

AI Technical Summary

Technical Problem

Existing laser deposition data management methods lack a unified classification standard, resulting in scattered and duplicate data storage, a lack of effective correlation between different types of data, low retrieval efficiency, inability to quickly locate target data, and difficulty in compatibility with multiple processes and the addition of new data types.

Method used

By analyzing the process configuration instructions, a basic process feature set is constructed. A communication link is established to collect dynamic process feature sets in real time. The theoretical design data and the actual generated data are structurally coupled to generate deposition process packages for specific scenarios, enabling the classification, storage, association, and intelligent retrieval of multi-type laser deposition process data.

Benefits of technology

It enables the orderly storage and rapid retrieval of various laser deposition process data, improves the convenience of data retrieval and integration efficiency, supports multiple process compatibility and expansion of new data types, and is compatible with laser deposition equipment from different manufacturers.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN123115231A_ABST
    Figure CN123115231A_ABST
Patent Text Reader

Abstract

This invention discloses a structured management method and system for various laser deposition process data, belonging to the field of digital data information retrieval and database structure technology. It includes receiving process configuration instructions for a target deposition scenario and performing dimensional analysis to extract equipment attribute parameters, material attribute parameters, process parameters, program parameters, and simulation model parameters to construct a basic process feature set; establishing a communication link with the deposition control equipment based on the basic process feature set, collecting real-time process status parameters and deposition process characteristic parameters during continuous deposition, and generating a dynamic process feature set; extracting theoretical design data from the basic process feature set and actual generated data from the dynamic process feature set and performing structured coupling to generate a deposition process package for a specific scenario. This invention achieves classified storage, associated retrieval, and intelligent searching of multiple types of laser deposition data, adapting to three mainstream processes: powder delivery, wire delivery, and simultaneous powder and wire delivery, thus improving data reuse efficiency.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of digital data information retrieval and database structure technology, and in particular to a structured management method and system for various laser deposition process data. Background Technology

[0002] Laser deposition technology is one of the core processes in metal additive manufacturing. It uses high-energy lasers to melt and deposit metal powder or wire layer by layer to manufacture and repair metal components, and has been widely applied in aerospace and high-end equipment fields. Mainstream laser deposition processes are divided into three categories: powder feeding, wire feeding, and simultaneous powder and wire feeding. The actual deposition process involves various types of process data, including equipment parameters, material properties, process combinations, deposition procedures, and simulation models, as well as process characteristic data such as melt pool temperature, melt pool flow, deposition state, and three-dimensional morphology. These data form the information foundation for process optimization and quality traceability, and their storage and retrieval methods directly affect data retrieval efficiency.

[0003] Existing laser deposition data management systems mostly employ a distributed storage approach, storing equipment parameters, material properties, process parameters, simulation models, and other data in different files or devices. These data types are named and archived according to operator preferences, requiring manual searching through file directories to locate the target data. Some systems configure dedicated storage formats for single deposition processes, compiling the parameters involved in that process into fixed spreadsheet files. Operators manually enter and update these files, transferring data between different tasks by copying the files when reuse is needed.

[0004] The aforementioned distributed storage method lacks a unified classification standard for data such as equipment parameters, material properties, process parameters, and simulation models. This data is scattered across different files and devices, easily leading to data loss or duplicate storage. Furthermore, there is a lack of effective correlation between various data types; process parameters and deposition programs, as well as material properties and simulation models, cannot be linked and accessed. The system lacks a standardized search interface, requiring manual filtering and making it impossible to quickly locate data based on multiple dimensions such as equipment type, material type, and process parameters. It also lacks a complete process data package organization format, making it impossible to package, store, and reuse data such as equipment, materials, processes, and programs adapted to specific scenarios. Systems designed for a single deposition process cannot be compatible with multiple mainstream processes such as powder feeding, wire feeding, and simultaneous powder and wire feeding, and are difficult to expand to include new data types such as real-time monitoring and quality inspection. Summary of the Invention

[0005] To address the aforementioned issues, this invention provides a structured management method and system for various laser deposition process data. By analyzing process configuration instructions to construct a basic process feature set, collecting and generating a dynamic process feature set in real time via communication links, and structurally coupling theoretical design data with actual generated data, it can achieve classified storage, associated retrieval, and intelligent searching of multiple types of laser deposition process data. It is also suitable for three mainstream deposition processes: powder delivery, wire delivery, and simultaneous powder and wire delivery, forming a reusable deposition process package for specific scenarios.

[0006] The above objectives can be achieved through the following approach: A structured management method for various laser deposition process data includes receiving process configuration instructions for a target deposition scenario and performing dimensional analysis to extract equipment attribute parameters, material attribute parameters, process parameters, program parameters, and simulation model parameters to construct a basic process feature set; establishing a communication link with the deposition control equipment based on the basic process feature set to collect real-time process status parameters and deposition process characteristic parameters during continuous deposition to generate a dynamic process feature set; and extracting theoretical design data from the basic process feature set and actual generated data from the dynamic process feature set and performing structured coupling to generate a deposition process package for a specific scenario.

[0007] Optionally, the construction of the basic process feature set includes: identifying the process type identifier in the process configuration instruction, determining the target deposition process type, wherein the target deposition process type includes powder feeding process, wire feeding process, and simultaneous powder feeding process; calling the corresponding process information input interface according to the target deposition process type, and obtaining the interface configuration data input by the user in the process information input interface; classifying and parsing the interface configuration data, and extracting equipment attribute parameters, material attribute parameters, process parameters, program parameters, and simulation model parameters to construct the basic process feature set.

[0008] Optionally, the step of extracting material property parameters includes: extracting material classification tags from the interface configuration data to determine the target material type; traversing the independent storage path corresponding to the target material type and reading the material information file under the independent storage path; parsing the material information file, extracting chemical composition ratio parameters and thermophysical property parameters, and generating material property parameters.

[0009] Optionally, the step of extracting process parameters includes extracting the deposition material identifier and substrate material identifier from the interface configuration data to generate a material combination tag; querying the process card library according to the target deposition process type and the material combination tag to match the target process card; and extracting the process operation data from the target process card to generate process parameters.

[0010] Optionally, generating the dynamic process feature set includes: parsing the equipment attribute parameters in the basic process feature set to determine the target monitoring equipment and communication protocol; activating the target monitoring equipment according to the communication protocol, acquiring the melt pool state data and deposition morphology data output by the target monitoring equipment, and generating deposition process feature parameters; synchronously reading the operation log of the deposition control system and extracting real-time process state parameters; and generating the dynamic process feature set based on the deposition process feature parameters and the real-time process state parameters.

[0011] Optionally, generating a specific scenario deposition process package includes: extracting simulation model parameters from the basic process feature set, performing simulation operations, and generating theoretical prediction result data; extracting deposition process feature parameters from the dynamic process feature set as actual observation result data; aligning the theoretical prediction result data with the actual observation result data using timestamps and spatial coordinate mapping to generate a comparison mapping matrix; and encapsulating the basic process feature set, the dynamic process feature set, and the comparison mapping matrix to generate a specific scenario deposition process package.

[0012] Optionally, the step of extracting simulation model parameters from the basic process feature set, performing simulation operations, and generating theoretical prediction result data includes: parsing the simulation model parameters from the basic process feature set, extracting model type labels, initial condition parameters, and boundary condition parameters; loading the corresponding physics solver according to the model type labels; inputting the initial condition parameters and the boundary condition parameters into the physics solver for iterative calculation to generate theoretical prediction result data.

[0013] Optionally, the step of encapsulating the basic process feature set, the dynamic process feature set, and the contrast mapping matrix to generate a deposition process package for a specific scenario includes: extracting process type features, deposition material features, and substrate material features from the basic process feature set, and splicing them to generate a process package naming tag; establishing a hierarchical storage directory according to the process package naming tag; and writing the basic process feature set, the dynamic process feature set, and the contrast mapping matrix into the hierarchical storage directory to construct an association index and generate a deposition process package for a specific scenario.

[0014] Optionally, the step of writing the basic process feature set, the dynamic process feature set, and the contrast mapping matrix into the hierarchical storage directory to construct an association index and generate a specific scenario deposition process package includes: storing the basic process feature set, the dynamic process feature set, and the contrast mapping matrix into the hierarchical nodes corresponding to the hierarchical storage directory; extracting laser power parameters and deposition rate parameters from the basic process feature set to generate process feature nodes; extracting melt pool temperature parameters from the dynamic process feature set to generate quality feature nodes; establishing a bidirectional mapping link between the process feature nodes and the quality feature nodes to generate an association index; and encapsulating and generating a specific scenario deposition process package based on the association index.

[0015] Based on the same inventive concept, this invention also provides a structured management system for various laser deposition process data. The system includes: a basic feature construction module, used to receive process configuration instructions for a target deposition scenario and perform dimensional analysis, extracting equipment attribute parameters, material attribute parameters, process parameters, program parameters, and simulation model parameters to construct a basic process feature set; a dynamic feature generation module, used to establish a communication link with the deposition control equipment based on the basic process feature set, collect real-time process status parameters and deposition process characteristic parameters during continuous deposition, and generate a dynamic process feature set; and a process package coupling module, used to extract theoretical design data from the basic process feature set and actual generated data from the dynamic process feature set and perform structured coupling to generate a deposition process package for a specific scenario.

[0016] Compared with the prior art, the present invention has the following advantages: This invention performs dimensional analysis on the process configuration instructions of the target deposition scenario, extracting equipment attribute parameters, material attribute parameters, process parameters, program parameters, and simulation model parameters, and constructing a basic process feature set. This integrates various types of process data, originally scattered across different files and devices, into a unified classification structure for orderly storage. Based on the process type identifier, it distinguishes between powder feeding processes, wire feeding processes, and simultaneous powder and wire feeding processes, and calls the corresponding process information input interface. This allows data from various mainstream laser deposition processes to be archived in a consistent and standardized manner, solving the problems of scattered, disordered, and duplicated data storage, and providing standardized storage support for the entire process data management.

[0017] This invention establishes a communication link with the deposition control equipment based on a basic process feature set. During continuous deposition, it synchronously collects real-time process status parameters and deposition process characteristic parameters to generate a dynamic process feature set. By aligning with the time base, it integrates melt pool status data, deposition morphology data, and operation logs collected from different data sources into a unified time axis. This allows theoretical design data and actual generated data to be correlated under the same organizational structure, solving the problem of lack of effective correlation between various types of data and the inability to link and call them, thus improving the integration efficiency and retrieval convenience of process data.

[0018] This invention structurally couples theoretical design data from the basic process feature set with actual generated data from the dynamic process feature set. It generates a comparison mapping matrix through timestamp alignment and spatial coordinate mapping, and generates process package naming tags based on process type features, deposition material features, and substrate material features. It establishes a hierarchical storage directory and a bidirectional mapping link between process feature nodes and quality feature nodes. This forms a specific scenario deposition process package that can be quickly retrieved and reused as a whole based on multiple attributes. It solves the problem of repeated debugging of similar components due to the lack of process data package organization, and shortens the data search and process debugging cycle.

[0019] The categorized storage structure constructed in this invention supports the addition and editing of various data types such as equipment, materials, processes, programs, and simulation models. It can also be expanded to include new dimensions such as real-time monitoring data and quality inspection data. It is compatible with laser deposition equipment from different manufacturers and can adapt to three mainstream processes: powder feeding, wire feeding, and simultaneous powder and wire feeding, as well as subsequent process upgrade needs. It solves the problem that systems designed for a single process are difficult to be compatible with multiple processes and expand to include new data types, thus providing adaptability for the diversified data management needs of intelligent manufacturing of laser deposition. Attached Figure Description

[0020] Figure 1 This is a flowchart illustrating a structured management method for various laser deposition process data according to an embodiment of the present invention.

[0021] Figure 2 This is a schematic diagram of a structured management system for various laser deposition process data according to an embodiment of the present invention. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0023] Reference Figure 1 One embodiment of the present invention proposes a structured management method for various laser deposition process data. By parsing the process configuration instruction dimension to construct a basic process feature set, collecting and generating a dynamic process feature set in real time through communication links, and structurally coupling theoretical design data with actual generated data, it can realize the classification, storage, association, and intelligent retrieval of multiple types of laser deposition process data. It is also suitable for three mainstream deposition processes: powder delivery, wire delivery, and simultaneous delivery of powder and wire, forming a reusable deposition process package for specific scenarios.

[0024] The method described in this embodiment specifically includes: S1. Receive the process configuration instructions for the target deposition scene and perform dimensional analysis to extract equipment attribute parameters, material attribute parameters, process parameters, program parameters and simulation model parameters, and construct a basic process feature set; In one embodiment of the present invention, step S1 includes the following steps: Identify the process type identifier in the process configuration instruction to determine the target deposition process type, which includes powder feeding process, wire feeding process, and simultaneous powder and wire feeding process. According to the target deposition process type, call the corresponding process information input interface and obtain the interface configuration data entered by the user in the process information input interface; The interface configuration data is classified and parsed to extract equipment attribute parameters, material attribute parameters, process parameters, program parameters, and simulation model parameters, and a basic process feature set is constructed.

[0025] Optionally, the steps for extracting material property parameters include: Extract the material classification tags from the interface configuration data to determine the target material type; Traverse the independent storage paths corresponding to the target material type and read the material information files under the independent storage paths; The material information file is parsed to extract chemical composition ratio parameters and thermophysical property parameters, and material property parameters are generated.

[0026] Optionally, the steps for extracting process parameters include: Extract the deposition material identifier and substrate material identifier from the interface configuration data to generate a material combination label; Based on the target deposition process type and the material combination label, query the process card library and match the target process card; Extract the process operation data from the target process card to generate process parameters.

[0027] Specifically, when the system receives a process configuration instruction for the target deposition scenario, it first performs dimensional parsing on the instruction content. This dimensional parsing process determines the target deposition process type by identifying the process type identifier carried in the configuration instruction. The process type identifier is encoded as a string in the header field of the configuration instruction and is parsed using a predefined identifier mapping table. The mapping table maps "DP" to a powder feeding process, "DW" to a wire feeding process, and "DPW" to a powder and wire feeding process. The parser reads the 3-byte identifier in the instruction header and compares it with the mapping table one by one. If a match is found, the target deposition process type is determined.

[0028] After determining the target deposition process type, the system calls the corresponding process information input interface based on the process type. The process information input interface adopts a graphical interactive design, with dedicated parameter input forms designed for powder feeding, wire feeding, and simultaneous powder and wire feeding processes. The powder feeding process interface includes parameter input boxes for laser power, powder feeding rate, carrier gas flow rate, and scanning speed; the wire feeding process interface includes parameter input boxes for laser power, wire feeding speed, protective gas flow rate, and scanning speed; the simultaneous powder and wire feeding process interface includes all parameter input boxes for both powder feeding and wire feeding. Users enter the parameter values ​​in the interface, and the system packages these values ​​along with the parameter names to form the interface configuration data. The interface configuration data is stored using a key-value pair structure, where the key is the parameter name string, and the value is the user-entered value and its unit.

[0029] The system categorizes and parses the interface configuration data, dividing it into five dimensions based on data source and functional attributes: equipment attribute parameters, material attribute parameters, process parameters, program parameters, and simulation model parameters. The categorization process automatically classifies parameters based on prefixes in their names: parameters starting with "DEV_" are categorized as equipment attribute parameters, those starting with "MAT_" as material attribute parameters, those starting with "PROC_" as process parameters, those starting with "PROG_" as program parameters, and those starting with "SIM_" as simulation model parameters. After classification, the parameter sets from the five dimensions are assembled into a basic process feature set. The basic process feature set is represented using a nested dictionary structure, expressed as: , in, Represents the basic process feature set, Represents a set of device attribute parameters. Represents a set of material property parameters. Represents a set of process parameters. Represents the set of program parameters. This represents the set of parameters for the simulation model.

[0030] The process of extracting material property parameters begins by locating the material category tags in the interface configuration data. These tags are stored in the interface configuration data with the key "MAT_TYPE," and their values ​​indicate the target material type, such as "titanium alloy," "aluminum alloy," or "stainless steel." After determining the target material type based on the category tags, the system accesses the hierarchical storage structure of the material library. The material library establishes independent storage paths for each material type, with each path corresponding to a folder named after the material type. The system traverses the independent storage paths corresponding to the target material type, reading all Excel-formatted material information files within those paths. These material information files are written using standardized templates and contain two worksheets: a chemical composition table and a thermophysical property table.

[0031] The chemical composition table uses element symbols as row labels and mass percentages as data columns, recording the precise proportions of each element in the material. The system reads the chemical composition table row by row, extracting the element symbols and their corresponding mass percentage values ​​to construct chemical composition proportion parameters. These parameters are stored as a dictionary with element symbols as keys and mass percentages as values. The thermophysical property table contains rows for parameters such as thermal conductivity, coefficient of thermal expansion, specific heat capacity, melting point, and thermal stability. Each row records the parameter name, value, and unit. The system parses the thermophysical property table row by row, extracting the parameter names and values ​​to construct thermophysical property parameters. These parameters are also stored as a key-value dictionary. The chemical composition proportion parameters and thermophysical property parameters are then merged to generate material property parameters, expressed as: , in, Indicates material property parameters, Indicates the proportion of chemical components. These represent thermophysical property parameters.

[0032] The process of extracting process parameters reads the deposition material identifier and substrate material identifier from the interface configuration data. The deposition material identifier and substrate material identifier are stored in the interface configuration data with "MAT_DEPO" and "MAT_SUBS" as keys, respectively, and their values ​​are material name strings, such as "TC11 titanium alloy" and "TC4 titanium alloy". The system concatenates the deposition material identifier and substrate material identifier, connecting them with a hyphen, to generate a material combination tag. The expression for generating the material combination tag is: , in, Indicates material combination label, This represents the identifier string for the deposited material. This represents a string indicating the substrate material identification. This indicates a string concatenation operation.

[0033] The system queries the process card library based on the target deposition process type and material combination tag. The process card library is divided into sub-libraries for powder feeding processes, wire feeding processes, and simultaneous powder and wire feeding processes. Each sub-library stores multiple process cards, with card files named using the material combination tag and saved in JSON format. The system searches the corresponding process type sub-library for process card files whose filenames exactly match the material combination tag, reads the file content, and completes the matching of the target process card. The target process card records process operation data in key-value pairs, including parameters such as laser power, scanning speed, powder feeding rate (powder feeding process), wire feeding speed (wire feeding process), carrier gas flow rate, protective gas flow rate, spot diameter, and defocusing amount. The system extracts all key-value pairs from the process card and outputs them as process parameters. The structural expression of the process parameters is: , in, Represents a set of process parameters. Indicates laser power. Indicates the scanning speed. Indicates the material supply rate (powder feeding rate or wire feeding speed). Indicates gas flow rate, Indicates the diameter of the light spot. Indicates the amount of defocus.

[0034] The extraction of equipment attribute parameters is achieved by parsing parameters prefixed with "DEV_" in the interface configuration data. Equipment attribute parameters include information such as equipment name, equipment type, equipment model, and technical specifications. The system filters all key-value pairs starting with "DEV_" from the interface configuration data and categorizes them as equipment attribute parameters. Equipment types are divided into eight categories based on function: energy equipment, mass equipment, motion equipment, laser head equipment, atmosphere equipment, cooling equipment, monitoring equipment, and other equipment. Energy equipment mainly refers to lasers, whose technical specifications include maximum output power, wavelength, and beam quality factor. Mass equipment includes powder feeders and wire feeders; powder feeder specifications include powder feeding rate range and powder particle size adaptation range, while wire feeder specifications include wire feeding speed range and compatible wire diameter range. Motion equipment refers to industrial robots, whose technical specifications include workspace dimensions, repeatability, and maximum movement speed. Laser head equipment is divided into powder feeding heads and wire feeding heads, with technical specifications including focal length, beam adjustment range, and working distance. Atmosphere equipment refers to gas supply devices, with technical specifications including gas supply pressure range and flow rate adjustment range. The cooling equipment is a water-cooled chiller, and its technical specifications include cooling power and operating temperature range. Monitoring equipment includes temperature sensors, high-speed cameras, and spectrometers, and its technical specifications include measurement range, sampling frequency, and resolution.

[0035] The extraction of program parameters is accomplished by reading parameters prefixed with "PROG_" from the interface configuration data. These parameters include the deposition program file path, program name, program type, number of layers, and number of passes. Deposition program files are stored in a program library, categorized by process type. Program names follow the naming convention of "number of layers-number of passes-power-deposition rate," for example, "L1P2-2000-5" represents a single-layer, two-pass program with a laser power of 2000W and a deposition rate of 5mm / s. The system locates the target program file in the program library based on the program name, reads the file path and program content, and generates the program parameters.

[0036] The simulation model parameters are extracted by parsing parameters prefixed with "SIM_" in the configuration data of the interface. These parameters include a model type label, initial condition parameters, and boundary condition parameters. The model type label indicates the physical model used in the simulation, including molten pool multiphase flow models, thermo-phase change coupling models, lattice Boltzmann method (LBM) models, and physical information neural network (PINN) models. The initial condition parameters record the initial temperature distribution of the simulation domain, including the initial model temperature. relative to the initial ambient temperature Boundary condition parameters record the type and value of heat exchange conditions at the simulation domain boundaries, including convective-radiative boundaries, isothermal boundaries, and adiabatic boundaries. For convective-radiative boundaries, the convective heat transfer coefficient must be recorded. With emissivity The constant temperature value needs to be recorded at the constant temperature boundary. No additional parameters are required for the adiabatic boundary. The structure expression for the simulation model parameters is as follows: , in, Indicates the parameters of the simulation model. Indicates the model type label. Represents boundary condition parameters. This represents the initial condition parameters.

[0037] After extracting parameters from the five dimensions, the system will then extract the device attribute parameters. Material property parameters Process parameters Program parameters and simulation model parameters Assembly is the basic process feature set .

[0038] For example, taking a powder feeding deposition scenario with TC11 titanium alloy as the deposition material and TC4 titanium alloy as the substrate as an example, the complete execution process of step S1 is explained. The system receives a process configuration instruction, the 3-byte identifier of which is "DP". After the parser reads the identifier, it compares it with the mapping table item by item. When a match is found in the mapping table corresponding to the powder feeding process for "DP", the target deposition process type is determined to be a powder feeding process.

[0039] After determining the powder feeding process, the system calls up the powder feeding process information input interface. The user fills in various parameters on the interface. The entered deposition material identifier is "TC11 titanium alloy", the substrate material identifier is "TC4 titanium alloy", the material classification label is "titanium alloy", the laser power is 2000W, the scanning speed is 5mm / s, the powder feeding rate is 8.7g / min, the carrier gas flow rate is 6L / min, the protective gas flow rate is 25L / min, the spot diameter is 4.5mm, and the defocusing amount is 16mm. The system packages these entered contents along with the parameter names into interface configuration data and stores them in key-value pairs. For example, the key "PROC_LASER" corresponds to the value 2000W, the key "PROC_SCAN" corresponds to the value 5mm / s, the key "MAT_DEPO" corresponds to the value "TC11 titanium alloy", and the key "MAT_SUBS" corresponds to the value "TC4 titanium alloy".

[0040] The system categorizes and parses the interface configuration data. It iterates through all key-value pairs in the interface configuration data, reading the prefix identifier of each key. For the key "DEV_LASER_POWER", its prefix is ​​"DEV_", classifying it as an equipment attribute parameter; for the key "MAT_TYPE", its prefix is ​​"MAT_", classifying it as a material attribute parameter; for the keys "PROC_LASER" and "PROC_SCAN", their prefix is ​​"PROC_", classifying them as process parameters; for the key "PROG_NAME", its prefix is ​​"PROG_", classifying it as a program parameter; and for the key "SIM_MODEL_TYPE", its prefix is ​​"SIM_", classifying it as a simulation model parameter. After each category is categorized, five sets are obtained: equipment attribute parameters, material attribute parameters, process parameters, program parameters, and simulation model parameters.

[0041] When extracting material property parameters, the system reads the value of the material classification label "MAT_TYPE" in the interface configuration data as "titanium alloy," confirming that the target material type is titanium alloy. The system accesses the independent storage path corresponding to titanium alloy in the material library, where two material information files, "TC11 titanium alloy.xlsx" and "TC4 titanium alloy.xlsx," are stored. Taking "TC11 titanium alloy.xlsx" as an example, the system opens the chemical composition worksheet of this file and reads it line by line. It reads that the element symbol Al corresponds to a mass percentage of 6.5%, the element symbol Mo corresponds to 3.5%, the element symbol Zr corresponds to 1.5%, the element symbol Si corresponds to 0.25%, and the element symbol Ti corresponds to the remaining amount. These element symbols and mass percentages are used to construct a dictionary of chemical composition proportion parameters. The system then opens the thermophysical property worksheet and reads it line by line, obtaining a thermal conductivity of 7.2 W / (m·K) and a coefficient of thermal expansion of 9.6 × 10⁻⁻⁻⁶. 6 / K, specific heat capacity 540 J / (kg·K), melting point 1650℃, thermal stability temperature 500℃. Construct a dictionary of thermophysical property parameters using the names and values ​​of these parameters. Combine the chemical composition ratio parameters with the thermophysical property parameters according to the expression. The material property parameters of TC11 titanium alloy were obtained.

[0042] When extracting process parameters, the system reads the deposition material identifier "TC11 titanium alloy" and the substrate material identifier "TC4 titanium alloy" from the interface configuration data. Based on the material combination label, an expression is generated, concatenating the two identifiers with a hyphen, and then substituting them into the calculation process. After splicing, the material combination label obtained is "TC11 titanium alloy-TC4 titanium alloy". The system searches the powder feeding process sub-database of the process card library based on the target deposition process type (powder feeding process) and the material combination label "TC11 titanium alloy-TC4 titanium alloy". It compares the filenames one by one in the powder feeding process sub-database. When a process card with the filename "TC11 titanium alloy-TC4 titanium alloy.json" is found, a match is found, and the file is read. The system parses all key-value pairs in the JSON file, extracting the following parameters: laser power 2000W, scanning speed 5mm / s, powder feeding rate 8.7g / min, carrier gas flow rate 6L / min, protective gas flow rate 25L / min, spot diameter 4.5mm, and defocusing amount 16mm. Based on the process parameter structure expression... Fill in the above values ​​in the corresponding positions, where the laser power is... Select 2000W, scanning speed Take 5 mm / s as the material supply rate. Powder feeding rate: 8.7 g / min; gas flow rate: Take the carrier gas flow rate and the protective gas flow rate, and the spot diameter. Take 4.5mm, defocus amount Take 16mm as an example, and generate the process parameters for the TC11 titanium alloy to TC4 titanium alloy powder feeding process.

[0043] When extracting device attribute parameters, the system filters all key-value pairs prefixed with "DEV_" in the configuration data. It identifies the energy device as a laser with a maximum output power of 6000W, wavelength of 1070nm, and beam quality factor of 8mm·mrad; the quality device as a powder feeder with a powder feeding rate range of 2 to 30g / min and a powder particle size adaptation range of 45 to 150μm; the motion device as a KUKA industrial robot with a repeatability of 0.05mm and a maximum movement speed of 2m / s; the laser head device as a powder feeder with a focal length of 200mm, a spot adjustment range of 1 to 5mm, and a working distance of 16mm; and the monitoring devices as a high-speed camera and a temperature sensor. The high-speed camera has a sampling frequency of 1000 frames per second and a resolution of 1024×1024 pixels, while the temperature sensor has a measurement range of 300 to 2500℃ and a sampling frequency of 100Hz. These key-value pairs are then categorized and constructed as device attribute parameters.

[0044] When extracting program parameters, the system reads key-value pairs prefixed with "PROG_" from the interface configuration data. Upon reading the program name "L1P2-2000-5", and following the naming convention of "layer number-pass number-power-deposition rate", it parses the program as a single-layer, two-pass system with a laser power of 2000W and a deposition rate of 5mm / s. The system then accesses the powder feeding process category in the program library, locates the corresponding .src and .dat files, reads the file paths and contents, and generates the program parameters.

[0045] When extracting simulation model parameters, the system reads key-value pairs prefixed with "SIM_" from the interface configuration data. It reads the model type label as "thermodynamic phase change coupled model" and the initial temperature of the model as the initial condition parameter. 25℃, initial ambient temperature The temperature is 25℃, the boundary condition parameters are convective-radiative boundary, and the convective heat transfer coefficient is... 20 W / (m²·K), emissivity The value is 0.7. This is based on the parameter structure expression of the simulation model. Fill in the model type label, boundary condition parameters, and initial condition parameters in the corresponding positions to generate simulation model parameters.

[0046] After extracting the parameters from the five dimensions, the system uses the basic process feature set expression. The equipment attribute parameters, material attribute parameters, process parameters, program parameters and simulation model parameters extracted under the above TC11 titanium alloy-TC4 titanium alloy powder feeding process scenario are filled in one by one to assemble and generate the basic process feature set of the scenario, thus completing the entire execution process of step S1.

[0047] S2. Based on the aforementioned basic process feature set, establish a communication link with the deposition control equipment, collect real-time process status parameters and deposition process feature parameters during the continuous deposition process, and generate a dynamic process feature set. In one embodiment of the present invention, step S2 includes the following steps: Analyze the equipment attribute parameters in the basic process feature set to determine the target monitoring equipment and communication protocol; The target monitoring device is activated according to the communication protocol, and the melt pool state data and deposition morphology data output by the target monitoring device are obtained to generate deposition process characteristic parameters. Synchronously read the operation log of the deposition control system and extract real-time process status parameters; A dynamic process feature set is generated based on the deposition process characteristic parameters and the real-time process status parameters.

[0048] Specifically, after generating the basic process feature set in step S1, the system enters the real-time data acquisition phase. First, the system parses the equipment attribute parameters in the basic process feature set to locate relevant information about the monitoring equipment and determine the target monitoring equipment and communication protocol. The equipment attribute parameters record the equipment type, equipment model, communication address, and communication protocol identifier for each monitoring device. The system iterates through the entries marked as monitoring devices in the equipment attribute parameters and extracts the communication address and communication protocol identifier for each monitoring device. The communication address is represented in the form of an IP address plus a port number, and the communication protocol identifier indicates the type of protocol used for data transmission, including TCP / IP, Modbus, serial port, etc. If an entry for a monitoring device in the basic process feature set is empty, it means that the corresponding feature for that item will not be collected, and the system skips that device.

[0049] After determining the target monitoring equipment and communication protocol, the system activates the target monitoring equipment according to the communication protocol. The activation process is achieved by initiating a connection request to the communication address of the target monitoring equipment. For monitoring equipment using the TCP / IP protocol, the system, as a client, initiates a socket connection to the monitoring equipment's IP address and port. After the connection is established, it enters the data receiving state. The target monitoring equipment includes a temperature sensor that captures the temperature and flow of the molten pool and a high-speed camera that captures the deposition state and morphology. The temperature sensor continuously outputs molten pool state data, including molten pool temperature and size values. The high-speed camera continuously outputs deposition morphology data, which is a frame-by-frame image of the deposition area. The system receives the molten pool state data and deposition morphology data output by the target monitoring equipment, timestamps them according to the acquisition time, and merges them to generate deposition process characteristic parameters. The structural expression of the deposition process characteristic parameters is: , in, Indicates characteristic parameters of the deposition process, Indicates the first The timestamp of the collection moment. Indicates the first The molten pool temperature value at each acquisition time. Indicates the first The size of the molten pool at each acquisition time. Indicates the first Images of the depositional area at each acquisition time, This represents the total number of data collection moments.

[0050] While collecting characteristic parameters of the deposition process, the system simultaneously reads the operation log of the deposition control system and extracts real-time process status parameters. The operation log of the deposition control system records the actual operating values ​​of each device during the deposition process in chronological order, including the actual output power of the laser, the actual movement speed of the robot, the actual powder feeding rate of the powder feeder, and the actual gas supply flow rate of the gas cylinder. The system reads the latest record line of the operation log at fixed sampling intervals, parses out each actual operating value, and generates real-time process status parameters along with the timestamp. The structural expression of the real-time process status parameters is: , in, Indicates real-time process status parameters, Indicates the first The timestamp of each sampling moment Indicates the first The actual output power of the laser at each sampling time. Indicates the first The actual speed of the robot at each sampling time. Indicates the first The actual powder delivery rate of the powder feeder at each sampling time. Indicates the first Actual gas supply flow rate at each sampling time This represents the total number of sampling times.

[0051] The deposition process characteristic parameters and real-time process status parameters are collected from different data sources with inconsistent sampling frequencies, and the timestamp references may also be biased. To integrate these two types of data into a unified dynamic process characteristic set, the system uses the clock of the deposition control system as a unified time reference to align the two types of data. Time alignment employs a nearest neighbor matching method, matching each timestamp in the deposition process characteristic parameters. Find the sampling time with the smallest time difference from the real-time process status parameters. The two are then correlated. The expression for calculating the time difference is: , in, The characteristic parameter of the deposition process is represented by the first... The time-in-time and real-time process status parameters The absolute value of the time difference at each moment. Indicates the time of data collection for characteristic parameters of the deposition process. This indicates the sampling time for real-time process status parameters. The system samples each... Select to make Take the minimum value After completing the correlation, the correlated deposition process characteristic parameters are integrated with the real-time process status parameters along a unified time axis to generate a dynamic process feature set. The structural expression of the dynamic process feature set is as follows: , in, This represents the dynamic process feature set. The meanings of each symbol are consistent with the corresponding symbols in the aforementioned deposition process feature parameters and real-time process state parameters. The subscripts are uniformly represented by... This indicates the time sequence number after alignment with a unified timeline.

[0052] For example, following the powder deposition scenario in step S1 where TC11 titanium alloy is used as the deposition material and TC4 titanium alloy is used as the substrate, the complete execution process of step S2 is explained. The system parses the device attribute parameters in the basic process feature set generated in step S1 and locates the monitoring device entries. It reads that the monitoring devices include a temperature sensor and a high-speed camera. The communication address of the temperature sensor is port 502 on 192.168.1.10, and the communication protocol is identified as TCP / IP; the communication address of the high-speed camera is port 8000 on 192.168.1.11, and the communication protocol is identified as TCP / IP. Therefore, the system determines that the target monitoring devices are the temperature sensor and the high-speed camera, both using the TCP / IP protocol.

[0053] The system activates the target monitoring device according to the TCP / IP protocol. As a client, it initiates a socket connection to port 502 of 192.168.1.10. After the connection is established, the temperature sensor continuously outputs melt pool status data. It also initiates a socket connection to port 8000 of 192.168.1.11. After the connection is established, the high-speed camera continuously outputs deposition morphology data. Temperature sensor data is acquired at a sampling frequency of 100Hz. The timestamp at the first acquisition time is... The molten pool temperature value was read in 0.00s. The temperature is 1820℃, and the size of the molten pool is [value missing]. The value is 4.3 mm; at the second acquisition time, the timestamp is... The molten pool temperature was read in 0.01s. The temperature is 1835℃, and the size of the molten pool is [value missing]. The thickness is 4.4 mm. Simultaneously, a high-speed camera acquires images of the deposition area at 1000 frames per second. The system merges the molten pool temperature and size values ​​with the deposition area image by timestamp, based on the expression... , generating characteristic parameters of the deposition process.

[0054] The system synchronously reads the deposition control system operation log. The latest record line is read at sampling intervals of 0.02 seconds, with the timestamp at the first sampling moment. The actual output power of the laser was determined at 0.005s. 1985W, actual robot movement speed The actual powder feeding rate of the powder feeder is 4.98 mm / s. 8.6 g / min, actual gas supply flow rate It is 5.95 L / min. According to the expression... Generate real-time process status parameters.

[0055] The system uses the deposition control system clock as a unified time reference to perform nearest-neighbor time alignment on the two types of data. This is applied to the characteristic parameters of the deposition process. At time 0.00s, find the sampling time with the smallest time difference in the real-time process status parameters, substitute it into the time difference expression, and calculate. s, this time difference takes the minimum value among all sampling times of the real-time process status parameters, therefore... The characteristic parameters of the deposition process at 0.00 s and The system correlates real-time process status parameters at 0.005s intervals. After correlating all acquired data points one by one, the system uses the dynamic process feature set expression... The molten pool temperature (1820℃), molten pool size (4.3mm), corresponding deposition area image, actual laser output power (1985W), actual robot movement speed (4.98mm / s), actual powder feeding rate (8.6g / min), and actual gas supply flow rate (5.95L / min) are integrated into the first moment of a unified time axis. After integrating them moment by moment, a dynamic process feature set of the powder feeding deposition scenario is generated, thus completing the entire execution process of step S2.

[0056] S3. Extract the theoretical design data from the basic process feature set and the actual generated data from the dynamic process feature set, and perform structured coupling to generate a deposition process package for a specific scenario.

[0057] In one embodiment of the present invention, step S3 includes the following steps: The simulation model parameters in the basic process feature set are analyzed, and the model type label, initial condition parameters, and boundary condition parameters are extracted. Load the corresponding physics solver according to the model type label; The initial condition parameters and the boundary condition parameters are input into the physics field solver for iterative calculation to generate theoretical prediction result data. The sedimentation process characteristic parameters are extracted from the dynamic process characteristic set and used as actual observation result data; The theoretical prediction data and the actual observation data are time-stamp aligned and spatial coordinate mapped to generate a comparison mapping matrix. Extract the process type features, deposition material features, and substrate material features from the basic process feature set, and splice them together to generate process package naming tags; Establish a hierarchical storage directory according to the naming tags of the process packages; The basic process feature set, the dynamic process feature set, and the comparison mapping matrix are stored in the hierarchical nodes corresponding to the hierarchical storage directory, respectively. Extract the laser power parameters and deposition rate parameters from the basic process feature set to generate process feature nodes; Extract the molten pool temperature parameters from the dynamic process feature set to generate quality feature nodes; Establish a bidirectional mapping link between the process feature nodes and the quality feature nodes, and generate an association index; Based on the associated index, a deposition process package for a specific scenario is generated.

[0058] Specifically, after generating the basic process feature set in step S1 and the dynamic process feature set in step S2, the system enters the structured coupling stage between theoretical design data and actual generated data. First, the simulation model parameters in the basic process feature set are analyzed, and model type labels, initial condition parameters, and boundary condition parameters are extracted. The model type label indicates the type of physical model used in the simulation, the initial condition parameters record the initial temperature distribution of the simulation domain, and the boundary condition parameters record the type and value of heat exchange conditions at the boundary of the simulation domain.

[0059] The system loads the corresponding physics solver based on the model type tag. A physics solver is a numerical calculation program written for a specific physical model; different model type tags correspond to different solvers. For example, a thermodynamic phase change coupling model corresponds to a heat conduction and latent heat coupling solver, a molten pool multiphase flow model corresponds to a fluid dynamics solver, a lattice Boltzmann method model corresponds to a lattice Boltzmann solver, and a physical information neural network model corresponds to a neural network predictor. The system searches the solver library for a matching solver program based on the model type tag and loads it into memory.

[0060] The system inputs initial and boundary condition parameters into the physics solver for iterative calculation, generating theoretical prediction results. Taking a thermodynamic phase transition coupled model as an example, the solver performs discrete iterative calculations of the temperature field in the deposition region based on the heat conduction control equation. The expression for the heat conduction control equation is: , in, Indicates the density of the material. Indicates specific heat capacity. Indicates temperature. Indicates time, Indicates thermal conductivity, This represents the power per unit volume input to the laser heat source.

[0061] The laser heat source term uses a Gaussian distribution model to describe the spatial distribution of laser energy in the deposition region, and its expression is: , in, Indicates laser absorption rate, Indicates laser power. Indicates the radius of the light spot. Indicates the depth of laser energy absorption. This represents the radial distance from the calculation point to the center of the light spot.

[0062] The solver divides the simulation domain into a finite number of grid cells, using initial condition parameters as the starting temperature for iteration and boundary condition parameters to constrain the heat exchange behavior of the boundary grid. It then progressively advances the temperature field calculation according to time steps. Within each time step, the solver updates the temperature value of each grid cell based on the heat conduction control equation. When the grid cell temperature reaches its melting point, the latent heat of phase change is introduced to correct the equivalent specific heat capacity and reflect the phase change process. Iterative calculations continue until the simulation duration of the deposition process ends, outputting the temperature distribution of each grid cell at each time point, i.e., the theoretical prediction results. The structure expression of the theoretical prediction results is as follows: , in, This represents the theoretical prediction results data. Indicates the first Simulation time for each data point , , Indicates the first The spatial coordinates of each data point in the simulation domain. Indicates the first Simulated temperature values ​​for each data point. This indicates the total number of data points.

[0063] The system extracts depositional process characteristic parameters from the dynamic process feature set as actual observation result data. The actual observation result data retains the timestamp, melt pool temperature, melt pool size, and depositional region image from the depositional process characteristic parameters; its structural expression is as follows: , in, This represents the actual observation results data, and the meaning of each symbol is consistent with the corresponding symbols of the sedimentation process characteristic parameters in step S2.

[0064] The system aligns theoretical prediction data with actual observation data using timestamps and maps them to spatial coordinates, generating a comparison mapping matrix. Timestamp alignment is based on the timestamps of the actual observation data. Using this as a benchmark, the simulation time is located in the theoretical prediction results data. and The data point with the smallest time difference. Spatial coordinate mapping maps the measurement location of the molten pool temperature in the actual observation data to the simulation domain coordinate system, and finds the corresponding simulated temperature value at that location. The system pairs the actual molten pool temperature value and the simulated temperature value at the same location at the same time, calculates the deviation between the two, and forms the elements of the comparison mapping matrix. The expression for calculating the temperature deviation is: , in, Indicates the first Temperature deviation at each alignment point Indicates the first The actual molten pool temperature at each alignment point Indicates the relationship with the first The simulated temperature values ​​corresponding to each alignment point in spacetime. The structural expression of the comparison mapping matrix is: , in, This represents the comparison mapping matrix, with each row corresponding to an alignment point. The four columns represent the alignment time, actual molten pool temperature, simulated temperature, and temperature deviation, respectively. This indicates the total number of alignment points.

[0065] The system extracts process type features, deposition material features, and substrate material features from the basic process feature set, and concatenates them to generate process package naming tags. The expression for generating process package naming tags is: , in, Indicates the naming label for the process package. Represents the process type characteristic string, Represents the characteristic string of the deposited material. This represents a string indicating the substrate material characteristics. This indicates a string concatenation operation.

[0066] The system establishes a hierarchical storage directory based on process package naming tags. The hierarchical storage directory uses the process package naming tag as the root node, and has three child nodes: a basic feature hierarchical node, a dynamic feature hierarchical node, and a comparison mapping hierarchical node. The system writes the basic process feature set to the basic feature hierarchical node, the dynamic process feature set to the dynamic feature hierarchical node, and the comparison mapping matrix to the comparison mapping hierarchical node, thus completing the hierarchical storage of the three types of data.

[0067] Based on hierarchical storage, the system constructs a relational index. First, laser power parameters and deposition rate parameters are extracted from the basic process feature set to generate process feature nodes. These process feature nodes record the laser power for that scenario. With deposition rate Subsequently, the melt pool temperature parameters from the dynamic process feature set are extracted to generate quality feature nodes. These quality feature nodes record the sequence of melt pool temperature values ​​collected for that scenario. The system establishes a bidirectional mapping link between process feature nodes and quality feature nodes. This bidirectional mapping link allows for locating a corresponding quality feature node from a process feature node, and also allows for reverse locating from a quality feature node to a corresponding process feature node, thereby generating an association index. Based on this association index, the system encapsulates the basic process feature set, the dynamic process feature set, and the comparison mapping matrix to generate a deposition process package for a specific scenario.

[0068] For example, taking the aforementioned powder deposition scenario using TC11 titanium alloy as the deposition material and TC4 titanium alloy as the substrate, the complete execution process of step S3 is explained. The system analyzes the simulation model parameters in the basic process feature set generated in step S1, extracting the model type tag as "thermal phase change coupling model". The initial condition parameters include an initial model temperature of 25℃ and an initial ambient temperature of 25℃. The boundary condition parameters are convective and radiative boundaries, with a convective heat transfer coefficient of 20W / (m²·K) and an emissivity of 0.4. The system searches the solver library according to the model type tag "thermal phase change coupling model" and loads the heat conduction and latent heat coupling solver.

[0069] The system inputs the initial and boundary condition parameters into the solver for iterative calculation. The solver reads the TC11 titanium alloy material properties: density 4480 kg / m³, specific heat capacity 540 J / (kg·K), and thermal conductivity 7.2 W / (m·K). It also reads the process parameters: laser power 2000 W, spot diameter 4.5 mm (spot radius 2.25 mm). A laser absorptivity of 0.35 and a laser energy absorption depth of 0.5 mm are used. These values ​​are substituted into the laser heat source term expression, and the radial distance at the center of the spot is calculated. The value is 0, the exponent term takes the value 1, and the calculation process is as follows: First calculate the molecule Then calculate the denominator. Dividing by this, the unit volume power of the laser heat source input at the center of the light spot is approximately The solver uses the heat source distribution as the laser heat source term in the heat conduction control equation, with an initial model temperature of 25℃ as the iteration starting temperature. It uses convection and radiation boundaries to constrain the boundary mesh, progressively advancing the temperature field calculation according to the time step. When the mesh element temperature reaches the melting point of TC11 titanium alloy (1650℃), a latent heat of phase transformation correction is introduced. Iterative calculations continue until the simulation duration of the deposition process ends, based on the theoretical prediction results and data expressions. It outputs the simulated temperature values ​​of each grid cell at each time point, generating theoretical prediction results data.

[0070] The system extracts sedimentation process characteristic parameters from the dynamic process feature set generated in step S2, and then uses the data expressions based on actual observation results. The system retains timestamps, melt pool temperature values, melt pool size values, and images of the deposition area to generate actual observation data. The first time stamp is 0.00s, and the actual melt pool temperature is 1820℃.

[0071] The system aligns actual observation data with theoretical prediction data using timestamps and maps them to spatial coordinates. Using the first timestamp of the actual observation data (0.00s) as a baseline, it searches for the data point in the theoretical prediction data with the smallest time difference between the simulation time and 0.00s. Simultaneously, it maps the actual molten pool temperature measurement location to the simulation domain coordinate system, finds the corresponding simulated temperature value for the grid cell, and obtains the simulated temperature value of 1798℃ for that time and space. Substituting this into the temperature deviation expression, the system calculates... ℃. After the system completes the pairing and deviation calculation for all alignment points one by one, it uses the comparison mapping matrix structure expression as a basis. The alignment time, actual molten pool temperature, simulated temperature and temperature deviation are filled in row by row. The first row is filled with 0.00s, 1820℃, 1798℃ and 22℃. After filling in row by row, a comparison mapping matrix is ​​generated.

[0072] The system extracts the process type feature "powder feeding", the deposition material feature "TC11 titanium alloy", and the substrate material feature "TC4 titanium alloy" from the basic process feature set. These features are then substituted into the process package naming tags to generate an expression, and the calculation process is as follows: The resulting process package naming tag is "Powder Feeding - TC11 Titanium Alloy - TC4 Titanium Alloy". The system establishes a hierarchical storage directory based on this naming tag, with "Powder Feeding - TC11 Titanium Alloy - TC4 Titanium Alloy" as the root node, and includes basic feature level nodes, dynamic feature level nodes, and comparison mapping level nodes. The system writes the basic process feature set to the basic feature level nodes, the dynamic process feature set to the dynamic feature level nodes, and the comparison mapping matrix to the comparison mapping level nodes.

[0073] The system extracts the laser power of 2000W and deposition rate of 5mm / s from the basic process feature set, and combines this with the program name "L1P2-2000-5" and a uniformly aligned timestamp sequence as a joint identifier to generate a unique process feature node. It then extracts the melt pool temperature value sequence (including values ​​such as 1820°C and 1835°C) that strictly corresponds to this timestamp sequence from the dynamic process feature set to generate a unique quality feature node. To address the issue of multiple identical process parameters and quality parameters not being precisely matched, the system establishes a bidirectional mapping link between process feature nodes and quality feature nodes under the same deposition task and time reference, based on the joint identifier of the program name and timestamp sequence. The process feature node with laser power of 2000W and deposition rate of 5mm / s (with a unique joint identifier) ​​can be forward-located to the quality feature node of the melt pool temperature value sequence at that specific moment, and the quality feature node of the melt pool temperature value sequence can be backward-located to the corresponding process feature node, thereby generating a precisely matching association index. Based on this association index, the system encapsulates the basic process feature set, dynamic process feature set, and comparison mapping matrix to generate a specific scenario deposition process package for "powder feeding - TC11 titanium alloy - TC4 titanium alloy", thus completing the entire execution process of step S3.

[0074] Based on the same inventive concept, such as Figure 2 As shown, the present invention also provides a structured management system for various laser deposition process data, the system comprising: The basic feature construction module is used to receive process configuration instructions for the target deposition scene and perform dimensional analysis to extract equipment attribute parameters, material attribute parameters, process parameters, program parameters and simulation model parameters to construct a basic process feature set; The dynamic feature generation module is used to establish a communication link with the deposition control equipment based on the basic process feature set, collect real-time process status parameters and deposition process feature parameters during continuous deposition, and generate a dynamic process feature set. The process package coupling module is used to extract theoretical design data from the basic process feature set and actual generated data from the dynamic process feature set and perform structured coupling to generate a deposition process package for a specific scenario.

[0075] All equivalent changes and modifications made in accordance with the teachings of this invention are still within the scope of this invention. Those skilled in the art will readily conceive of other embodiments of this invention upon considering the specification and the disclosure of practical truth. This application is intended to cover any variations, uses, or adaptations of this invention that follow the general principles of this invention and include common knowledge or conventional techniques in the art not described herein.

Claims

1. A structured management method for various laser deposition process data, characterized in that, The method includes: Receive the process configuration instructions for the target deposition scenario and perform dimensional analysis to extract equipment attribute parameters, material attribute parameters, process parameters, program parameters and simulation model parameters, and construct a basic process feature set; Based on the aforementioned basic process feature set, a communication link is established with the deposition control equipment to collect real-time process status parameters and deposition process feature parameters during continuous deposition, thereby generating a dynamic process feature set. The theoretical design data from the basic process feature set and the actual generated data from the dynamic process feature set are extracted and structurally coupled to generate a deposition process package for a specific scenario. Specifically, generating a deposition process package for a specific scenario includes: extracting simulation model parameters from the basic process feature set, performing simulation operations, and generating theoretical prediction result data; extracting deposition process feature parameters from the dynamic process feature set as actual observation result data; aligning the theoretical prediction result data with the actual observation result data using timestamps and spatial coordinate mapping to generate a comparison mapping matrix; and encapsulating the basic process feature set, the dynamic process feature set, and the comparison mapping matrix to generate a deposition process package for a specific scenario.

2. The structured management method for various laser deposition process data according to claim 1, characterized in that, The basic process feature set includes: Identify the process type identifier in the process configuration instruction to determine the target deposition process type, which includes powder feeding process, wire feeding process, and simultaneous powder and wire feeding process. According to the target deposition process type, call the corresponding process information input interface and obtain the interface configuration data entered by the user in the process information input interface; The interface configuration data is classified and parsed to extract equipment attribute parameters, material attribute parameters, process parameters, program parameters, and simulation model parameters, and a basic process feature set is constructed.

3. The structured management method for various laser deposition process data according to claim 2, characterized in that, The steps for extracting material property parameters include: Extract the material classification tags from the interface configuration data to determine the target material type; Traverse the independent storage paths corresponding to the target material type and read the material information files under the independent storage paths; The material information file is parsed to extract chemical composition ratio parameters and thermophysical property parameters, and material property parameters are generated.

4. The structured management method for various laser deposition process data according to claim 2, characterized in that, The steps for extracting process parameters include: Extract the deposition material identifier and substrate material identifier from the interface configuration data to generate a material combination label; Based on the target deposition process type and the material combination label, query the process card library and match the target process card; Extract the process operation data from the target process card to generate process parameters.

5. A structured management method for various laser deposition process data according to claim 2, characterized in that, The feature set for generating dynamic processes includes: Analyze the equipment attribute parameters in the basic process feature set to determine the target monitoring equipment and communication protocol; The target monitoring device is activated according to the communication protocol, and the melt pool state data and deposition morphology data output by the target monitoring device are obtained to generate deposition process characteristic parameters. Synchronously read the operation log of the deposition control system and extract real-time process status parameters; A dynamic process feature set is generated based on the deposition process characteristic parameters and the real-time process status parameters.

6. The structured management method for various laser deposition process data according to claim 1, characterized in that, The step of extracting simulation model parameters from the basic process feature set, performing simulation operations, and generating theoretical prediction result data includes: The simulation model parameters in the basic process feature set are analyzed, and the model type label, initial condition parameters, and boundary condition parameters are extracted. Load the corresponding physics solver according to the model type label; The initial condition parameters and the boundary condition parameters are input into the physics solver for iterative calculation to generate theoretical prediction results data.

7. The structured management method for various laser deposition process data according to claim 1, characterized in that, The process of encapsulating the basic process feature set, the dynamic process feature set, and the contrast mapping matrix to generate a deposition process package for a specific scenario includes: Extract the process type features, deposition material features, and substrate material features from the basic process feature set, and splice them together to generate process package naming tags; Establish a hierarchical storage directory according to the naming tags of the process packages; The basic process feature set, the dynamic process feature set, and the comparison mapping matrix are written into the hierarchical storage directory to construct an associated index and generate a deposition process package for a specific scenario.

8. A structured management method for various laser deposition process data according to claim 7, characterized in that, The step of writing the basic process feature set, the dynamic process feature set, and the comparison mapping matrix into the hierarchical storage directory to construct an associated index and generate a specific scenario deposition process package includes: The basic process feature set, the dynamic process feature set, and the comparison mapping matrix are stored in the hierarchical nodes corresponding to the hierarchical storage directory, respectively. Extract the laser power parameters and deposition rate parameters from the basic process feature set to generate process feature nodes; Extract the molten pool temperature parameters from the dynamic process feature set to generate quality feature nodes; Establish a bidirectional mapping link between the process feature nodes and the quality feature nodes, and generate an association index; Based on the associated index, a deposition process package for a specific scenario is generated.

9. A structured management system for various laser deposition process data, characterized in that, The system includes: The basic feature construction module is used to receive process configuration instructions for the target deposition scene and perform dimensional analysis to extract equipment attribute parameters, material attribute parameters, process parameters, program parameters and simulation model parameters to construct a basic process feature set; The dynamic feature generation module is used to establish a communication link with the deposition control equipment based on the basic process feature set, collect real-time process status parameters and deposition process feature parameters during continuous deposition, and generate a dynamic process feature set. The process package coupling module is used to extract theoretical design data from the basic process feature set and actual generated data from the dynamic process feature set and perform structured coupling to generate a deposition process package for a specific scenario. Specifically, generating a deposition process package for a specific scenario includes: extracting simulation model parameters from the basic process feature set, performing simulation operations, and generating theoretical prediction result data; extracting deposition process feature parameters from the dynamic process feature set as actual observation result data; aligning the theoretical prediction result data with the actual observation result data using timestamps and spatial coordinate mapping to generate a comparison mapping matrix; and encapsulating the basic process feature set, the dynamic process feature set, and the comparison mapping matrix to generate a deposition process package for a specific scenario.