Standardized optimization method for multi-process parameter collaborative surface treatment of aviation parts

Abstract

The application provides an aviation part multi-process parameter collaborative surface treatment standardization optimization method, and relates to the technical field of aviation manufacturing surface engineering, which comprises the following steps: S1, constructing a process parameter hierarchical coding system and a correlation mapping model; S2, establishing a parameter solving method based on multi-objective collaborative optimization; S3, constructing a modular process chain; S4, establishing real-time monitoring and closed-loop control of multi-source data fusion; S5, establishing a digital simulation body and verifying; S6, constructing a full-process quality traceability database. Through parameter hierarchical coding and correlation mapping and cross-process chain intelligent decision-making model, the application realizes dynamic collaborative optimization of multi-process parameters, reduces parameter conflict rate, and improves process decision-making efficiency. At the same time, the adaptive optimization engine based on reinforcement learning can correct process parameters in real time, improve batch consistency of key performance indicators, and significantly improve process stability and product quality.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of aviation manufacturing surface engineering, and particularly relates to a multi-process parameter coordinated surface treatment standardization optimization method for aviation parts. BACKGROUND

[0002] In the field of aviation manufacturing, aviation parts such as wing structural parts, engine blades or landing gear components need to withstand extreme working conditions of high temperature, high pressure, high corrosion and complex alternating load for a long time, and the surface performance such as wear resistance, corrosion resistance and high temperature oxidation resistance directly determines the reliability, safety and service life of the equipment. In order to meet this demand, surface treatment technology has become a key link in the manufacturing of aviation parts, which needs to integrate multiple processes such as laser cladding, micro-arc oxidation, chemical plating, thermal spraying and vapor deposition to realize the functionalization of the material surface such as strengthening, corrosion prevention and drag reduction. However, the existing surface treatment technology has significant technical bottlenecks: first, the isolated optimization of process parameters leads to the lack of multi-process coordination, for example, there is a complex thermal-electric-chemical coupling effect between the power and scanning speed of laser cladding and the voltage and frequency of micro-arc oxidation, if the parameters are not optimized coordinately, it is easy to cause interface thermal stress concentration, coating porosity exceeding the standard or microstructure defects such as cracks, un-melted, especially in materials with large differences in thermal physical properties such as titanium alloy and high-temperature alloy, the probability of parameter conflict increases significantly; second, the process sequence depends on experience and lacks thermal-chemical coupling control, for example, if the cooling rate or interval time is not strictly controlled after micro-arc oxidation, the residual stress may accumulate to cause deformation of the substrate, and if the oxide layer residue is not completely removed before chemical plating, the interface reaction may be out of control, forming a brittle phase, but the existing technology lacks a quantitative model for the coupling of process sequence and parameters, resulting in poor process stability; third, the low standardization and random parameter adjustment lead to large fluctuations in product quality, for example, the laser cladding power fluctuates ±20% due to the equipment model and powder characteristics, and the micro-arc oxidation electrolyte formula is not matched according to the thermal expansion coefficient of the material, resulting in coating peeling or insufficient corrosion resistance, such problems are particularly prominent in large-scale production of aviation parts, and the performance difference between batches can reach more than 30%, which is difficult to meet the zero defect requirement.

[0003] In addition, the full-process quality traceability and process reproduction are difficult, the prior art stores the process parameter record and the quality detection data independently, lacks correlation analysis, for example, parameter deviation such as laser cladding power fluctuation and micro-arc oxidation current density abnormality is not bound with coating hardness and bonding strength, so that the defect traceability efficiency is low, and the process parameter dynamic adjustment lacks historical data support, and it is difficult to realize the full life cycle quality control; finally, the intelligent and digital technology fusion is insufficient, the existing surface treatment process mostly stays in the single machine automation stage, lacks real-time perception and collaborative control of process parameters, equipment state and environmental variables, for example, laser cladding spot offset, micro-arc oxidation local breakdown and the like are not identified in time, resulting in an increase in coating defect rate, and the virtual simulation and physical experiment data of the multi-process chain are not closed-loop verified, so that the process collaborative effect cannot be predicted, and the intelligent upgrading of the surface treatment of the aviation part to the direction of high precision, high reliability and high efficiency is limited. Therefore, there is an urgent need for a multi-process parameter collaborative surface treatment standardized integration method, which breaks through the limitations of parameter isolation, process disorder and uncontrollable quality in the traditional technology through parameter collaborative optimization, process chain standardized design, full-process closed-loop control and intelligent quality traceability, and provides technical support for high-performance manufacturing of aviation equipment. SUMMARY

[0004] In order to solve the above-mentioned problems of the prior art, the purpose of the present application is to provide a multi-process parameter collaborative surface treatment standardization optimization method for aviation parts, which realizes the collaborative optimization, standardized integration and full-process quality control of multi-process parameters through a series of technical measures, and can realize dynamic collaborative optimization of multi-process parameters, reduce parameter conflict rate and improve process decision efficiency through parameter hierarchical coding and correlation mapping and cross-process chain intelligent decision model.

[0005] Specifically, the present application provides a multi-process parameter collaborative surface treatment standardization optimization method for aviation parts, which comprises the following steps:

[0006] S1, constructing a process parameter hierarchical coding system and a correlation mapping model: dividing the surface treatment process parameters into basic parameters and collaborative parameters and establishing a three-level coding rule; forming a standardized parameter library and dynamically correcting the coupling threshold in the standardized parameter library;

[0007] S2, establishing a parameter solving method based on multi-objective collaborative optimization: taking the key performance indicators of the surface treatment process as the optimization target, combining the physical constraint conditions, constructing a multi-process parameter collaborative optimization model to solve the optimal parameter combination meeting the multi-constraint conditions:

[0008] ;

[0009] ;

[0010] ;

[0011] ;

[0012] Objective function m key performance indicators as optimization objectives; p physical constraints; q equality constraints; the value range of the i th process parameter;

[0013] S3, build a modular process chain: the surface treatment process is divided into pretreatment, main treatment and post-treatment three modules, each module is divided into multiple process units; Establish the transfer rule of parameters and data between modules, realize the cross-module matching of process parameters through hierarchical coding system, and automatically match the optimal process unit combination;

[0014] S4, establish real-time monitoring and closed-loop control of multi-source data fusion: compare the key state parameters with the threshold range in the standardized parameter library, so that the key state parameters are within the threshold range;

[0015] S5, build a digital simulation body and verify it;

[0016] S6, build a full-process quality traceability database.

[0017] Preferably, in step S1, the process type is identified by primary coding, the parameter category is identified by secondary coding, and the range and precision of the parameter value are identified by tertiary coding, to realize the standardized identification and traceability of the parameters; the correlation between the basic parameters and the collaborative parameters is quantified through experimental design multi-field coupling simulation, a parameter coupling model is established and a collaborative threshold range is defined, forming a standardized parameter library containing parameter classification, coding rules and collaborative constraints; finally, the coupling threshold in the parameter library is dynamically corrected through the feedback mechanism of process execution data.

[0018] Preferably, in step S1, the coupling threshold in the standardized parameter library is dynamically corrected through process execution data, and the coupling threshold correction formula is as follows:

[0019] ;

[0020] Wherein, the correction amount The calculation formula is as follows:

[0021] ;

[0022] In the formula: is the corrected coupling threshold between process parameters i and j; is the original coupling threshold between process parameters i and j in the standardized parameter library; is a correction coefficient, used to control the correction range, and is taken in the range of 0 < a < 1. ≤1; is a correlation coefficient between process parameters i and j, reflecting the correlation strength between the basic parameters and the collaborative parameters, and is taken in the range of 0 ≤ b ≤ 1. ≤1; is an occasional error between process parameters i and j in actual execution; is the maximum allowable occasional error, determined according to process requirements and historical data; and are the upper and lower limits of the coupling threshold between process parameters i and j, respectively.

[0023] Preferably, in step S3, the process content specified by the surface treatment process standard is refined into independent process units, and the standardized input and output interfaces of the three modules are defined.

[0024] Preferably, in step S2, the specific steps of solving the optimal parameter combination satisfying multiple constraint conditions by using the multi-process parameter collaborative optimization model are as follows: a genetic algorithm combined with a response surface method is adopted, an initial parameter population is generated by experimental design, and a finite element simulation and physical experiment data are used to iteratively correct the objective function to quantify the nonlinear coupling effect between parameters; an adaptive weight adjustment strategy is introduced to dynamically balance the competition relationship between multiple objectives to generate an optimal parameter combination satisfying multiple constraint conditions.

[0025] Preferably, in step S3, the optimal process unit combination is automatically matched based on the decision tree algorithm according to the material type, performance requirements and geometric characteristics of the aviation parts.

[0026] Preferably, in step S4, when the key state parameters deviate from the preset threshold, a closed-loop control mechanism is automatically triggered, PID control or fuzzy control algorithm is used to dynamically adjust the process parameters, and the process effect after parameter adjustment is predicted through the digital simulation body in step S5; the parameter data before and after adjustment, state monitoring values and quality detection results are associated and stored in the full-process quality traceability database in step S6 to form a complete closed loop of monitoring-decision-execution-feedback.

[0027] Preferably, in step S5, a digital simulation body covering the whole process of pre-treatment, main treatment and post-treatment is constructed, through a finite element model and a standardized parameter library, the physical field evolution and surface treatment microstructure formation process under the collaborative action of multiple process parameters are simulated in real time; the real-time monitoring data in step S4 and the virtual simulation results are bidirectionally mapped, and the accuracy of the digital simulation body is dynamically iterated through a data-driven model correction mechanism.

[0028] Preferably, in step S6, the specific steps of constructing the full-process quality traceability database are as follows:

[0029] S61, through the standardized parameter coding system of step S1 and the modular process chain of step S3, the base material, process path, process parameters and real-time monitoring data of the aviation part are stored in a structured manner, and the quality detection result is bound to the unique identity of the part;

[0030] S62, a multi-dimensional correlation model is established based on a graph database technology, penetration-type tracing is performed according to part number, process type, time interval or quality defect type, and an abnormal parameter node is located; a machine learning algorithm is integrated to deeply mine historical quality data, automatically extract the correlation rules of parameter deviation and defect mode, and generate a visual defect traceability report and process improvement suggestion;

[0031] S63, cross-department quality data collaboration is realized through a cloud data sharing platform, the continuous optimization of the standardized parameter library is promoted through the closed-loop feedback of historical defect data, and a benign iterative mechanism of quality monitoring-defect traceability-process improvement is formed.

[0032] Preferably, it further comprises step S7, constructing a process intelligent decision and adaptive optimization system, and the specific steps are:

[0033] S71, based on the historical process data in the whole-process quality traceability database in step S6, the real-time monitoring information of the key state parameters in step S4 and the virtual verification results in step S5, a nonlinear relationship between process parameters, environmental variables and surface treatment performance is obtained through a deep learning algorithm, and an intelligent decision model across process chains is established;

[0034] S72, the process execution effect is evaluated in real time based on a reinforcement learning algorithm, and the parameter decision logic is dynamically corrected through a closed-loop feedback mechanism;

[0035] S73, virtual-real interactive verification is performed between a digital simulation body and a physical production line.

[0036] Compared with the prior art, the beneficial effects of the present application are as follows:

[0037] (1) The present application can realize dynamic collaborative optimization of multiple process parameters, reduce parameter conflict rate, and improve process decision efficiency through parameter hierarchical coding and correlation mapping and cross-process chain intelligent decision model. At the same time, the adaptive optimization engine based on reinforcement learning can correct process parameters in real time, improve batch consistency of key performance indicators, and significantly improve process stability and product quality.

[0038] (2) The present application realizes standardization reuse and rapid matching of process modules, improves process chain design efficiency and reduces development cost through modular process chain construction and digital simulation virtual verification. In addition, the virtual verification technology can predict defects in advance, shorten the process development cycle, improve product qualification rate, reduce trial and error cost and resource waste.

[0039] (3) The application constructs a full-process quality traceability database, realizes penetrating traceability from part number to process node through a process-parameter-quality ternary correlation model, improves defect traceability efficiency, and stabilizes process reproduction success rate. At the same time, based on machine learning, the intelligent early warning of defect mode compresses the quality fluctuation range and provides a high-reliability and high-consistency surface treatment solution for aviation manufacturing. BRIEF DESCRIPTION OF DRAWINGS

[0040] Figure 1 A flowchart of the aviation part multi-process parameter collaborative surface treatment standardization optimization method of the application;

[0041] Figure 2 A parameter grading coding and collaborative optimization schematic diagram of the application;

[0042] Figure 3 A modular process chain dynamic reorganization flowchart of the application;

[0043] Figure 4 A digital simulation virtual verification and physical production line interaction diagram of the application;

[0044] Figure 5 A full-process quality traceability database architecture diagram of the application;

[0045] Figure 6 A defect mode intelligent early warning and parameter optimization schematic diagram of the application. DETAILED DESCRIPTION

[0046] Hereinafter, embodiments of the application will be described with reference to the accompanying drawings.

[0047] Specifically, an aviation part multi-process parameter collaborative surface treatment standardization optimization method includes the following steps:

[0048] S1, constructing a process parameter grading coding system and a correlation mapping model: dividing the surface treatment process parameters into basic parameters and collaborative parameters and establishing a three-level coding rule; quantifying the correlation between the basic parameters and the collaborative parameters, establishing a parameter coupling model and defining a collaborative threshold range, forming a standardized parameter library containing parameter classification, coding rule and collaborative constraint, and dynamically correcting the coupling threshold in the standardized parameter library through process execution data; in step S1, the process type is identified by the first-level coding, the parameter category is identified by the second-level coding, and the parameter value range and precision are identified by the third-level coding, realizing the standardized identification and traceability of the parameters; the correlation between the basic parameters and the collaborative parameters is quantified through experimental design and multi-field coupling simulation, a parameter coupling model is established, and a collaborative threshold range is defined, forming a standardized parameter library containing parameter classification, coding rule and collaborative constraint; finally, the coupling threshold in the parameter library is dynamically corrected through the feedback mechanism of process execution data.

[0049] The coupling threshold correction formula is as follows:

[0050] ;

[0051] wherein the correction amount The calculation formula of the correction amount is as follows:

[0052] ;

[0053] In the formula: is the coupling threshold between the corrected process parameters i and j; is the coupling threshold between the original process parameters i and j in the standardized parameter library; is a correction coefficient, used for controlling the correction amplitude, and the range is 0 < a < 1; is a correlation quantization coefficient between the process parameters i and j, reflecting the correlation strength between the basic parameters and the collaborative parameters, and the range is 0 ≤ b ≤ 1; is an occasional error between the process parameters i and j in actual execution; is the maximum allowable occasional error, determined according to process requirements and historical data; and are the upper limit and the lower limit of the coupling threshold between the process parameters i and j, respectively. are the upper limit and the lower limit of the coupling threshold between the process parameters i and j, respectively.

[0054] S2, a parameter solving method based on multi-objective collaborative optimization is established: first, the key performance indicators of the surface treatment process are taken as the optimization objectives, a multi-process parameter collaborative optimization model is constructed in combination with physical constraint conditions, and the multi-process parameter collaborative optimization model is used to solve the optimal parameter combination that meets the multi-constraint conditions; the specific steps of using the multi-process parameter collaborative optimization model to solve the optimal parameter combination that meets the multi-constraint conditions in step S2 are as follows: a genetic algorithm combined with a response surface method is adopted, an initial parameter population is generated through experimental design, and a finite element simulation and physical experimental data are used to iteratively correct the objective function to quantify the nonlinear coupling effect between the parameters; an adaptive weight adjustment strategy is introduced to dynamically balance the competition relationship between the multi-objects to generate the optimal parameter combination that meets the multi-constraint conditions. The multi-process parameter collaborative optimization model is specifically as follows:

[0055] ;

[0056] ;

[0057] ;

[0058] ;

[0059] In the formula: the objective function ​m is the number of key performance indicators as optimization objectives; constraint condition is inequality constraint p is the number of physical constraints; constraint condition is equality constraint q is the number of equality constraints. is the value range of the i th process parameter. and is the minimum value and the maximum value of the i th process parameter, respectively.

[0060] The algorithm is innovative based on the improvement and integration of genetic algorithm, corresponding surface method and adaptive weight adjustment strategy. It can more efficiently process high latitude and nonlinear process parameter optimization problems; at the same time, it iteratively optimizes to improve the reliability of the optimization results.

[0061] S3, Constructing a modular process chain: First, the surface treatment process is divided into pretreatment, main treatment and post-treatment three modules, each module is further refined into an independent process unit, and the standardized input and output interfaces of the three modules are defined; then the transmission rules of parameters and data between modules are established, the cross-module matching of process parameters is realized through the hierarchical coding system of step S1, and the optimal process module combination is automatically matched according to the material type, performance requirements and geometric characteristics of the aircraft parts.

[0062] Firstly, the transmission content such as process parameters, part feature data, quality detection data, etc. is determined, the transmission mode such as direct data transmission, intermediate database transmission or message queue transmission is determined, the data format and conversion rules are formulated; secondly, according to the coding system established in S1, the cross-module matching is carried out according to the process type and the corresponding process parameters; finally, the part feature database is established, and the decision tree algorithm is used to output the optimal process module combination according to the process characteristics.

[0063] S4, Establishing real-time monitoring and closed-loop control of multi-source data fusion: Collecting multi-dimensional data, pre-processing the data, and comparing the key state parameters with the threshold range in the standardized parameter library; when the monitoring data deviates from the preset threshold in step S4, the system automatically triggers the closed-loop control mechanism, dynamically adjusts the process parameters using PID control or fuzzy control algorithm, and predicts the process effect after parameter adjustment through digital simulation model to ensure that the adjusted parameter combination meets the performance target; in addition, the parameter data before and after adjustment, state monitoring value and quality detection result are stored in the whole-process quality traceability database, forming a complete closed loop of monitoring-decision-execution-feedback. Then, the real-time monitoring data in step S4 and the virtual simulation results are bidirectionally mapped, and the precision of the digital simulation body is dynamically iterated through the data-driven model correction mechanism.

[0064] S5, establishing a digital simulation body and verifying: first, a digital simulation body covering the whole process of pretreatment, main treatment and post-treatment is constructed, and through integration of a finite element model and a process parameter standardization library, physical field evolution and surface treatment microstructure formation process under the synergistic action of multiple process parameters are simulated in real time.

[0065] S6, constructing a whole-process quality traceability database. Specifically, the specific steps of constructing the whole-process quality traceability database in step S6 are as follows:

[0066] S61, through the standardized parameter coding system of step S1 and the process chain modularization identification of step S3, the base material, process path, process parameter and real-time monitoring data of the aircraft part are stored in a structured manner, and the quality detection result and the unique identity of the part are bound.

[0067] S62, based on the graph database technology, a multi-dimensional correlation model is established to support penetrating traceability according to part number, process type, time interval or quality defect type, quickly locate abnormal parameter nodes; integrate machine learning algorithm to deeply mine historical quality data, automatically extract parameter deviation and defect mode correlation rules, and generate visual defect traceability report and process improvement suggestions.

[0068] S63, through the cloud data sharing platform, the quality data of cross-department is realized. At the same time, through the closed-loop feedback of historical defect data, the continuous optimization of the standardized parameter library is promoted, and a benign iterative mechanism of "quality monitoring-defect traceability-process improvement" is formed.

[0069] It also includes constructing a process intelligent decision and adaptive optimization system, and the specific steps of constructing the process intelligent decision and adaptive optimization system are as follows:

[0070] S71, based on the historical process data in the whole-process quality traceability database in step S6, the real-time monitoring information in step S4 and the virtual verification result in step S5, the nonlinear relationship between process parameters, environmental variables and surface treatment performance is obtained through deep learning algorithm, an intelligent decision model across process chain is established, and the optimal process parameter combination is automatically recommended according to part type, performance requirement and real-time working condition.

[0071] S72, deploying adaptive optimization engine, real-time evaluating process execution effect based on reinforcement learning algorithm, dynamically correcting parameter decision logic through closed-loop feedback mechanism, so that the process system has the ability of self-learning and continuous improvement.

[0072] S73, through the virtual-real interaction verification of digital simulation body and physical production line, the stability and reliability of the optimized parameter combination under complex working conditions are ensured. Specific embodiments

[0074] The embodiment of the application provides a kind of aviation parts multi-process parameter collaborative surface treatment standardization optimization method, such as Figure 1 As shown, it includes the following steps:

[0075] S1, construct process parameter hierarchical coding system and correlation mapping model: as shown in Figure 2 First, surface treatment process parameters are classified, which are divided into basic parameters and collaborative parameters. Basic parameters such as laser power, spot size, micro-arc oxidation termination voltage, etc. are single-process independent variables. Collaborative parameters such as laser scanning speed and micro-arc oxidation pulse frequency are cross-process coupled variables. Three-level coding rules are established, i.e. process type is identified by first-level coding, such as LC-laser cladding, MAO-micro-arc oxidation, SP-spraying, CN-nitriding or CE-chemical plating. Parameter category is identified by second-level coding, such as P-power, T-temperature, V-voltage, F-frequency, D-thickness or C-concentration. Parameter value range and precision are identified by third-level coding, such as P-LC-1500±50W, indicating laser cladding power range and precision. Standardized identification and traceability of parameters are realized. Then, the correlation between basic parameters and collaborative parameters is quantified through experimental design and multi-field coupling simulation. Parameter coupling model is established and collaborative threshold range is defined, such as when laser power P-LC≥1450W, micro-arc oxidation voltage V-MAO needs to be ≤460V to avoid excessive interface thermal stress. A standardized parameter library containing parameter classification, coding rules and collaborative constraints is formed. Finally, the coupling threshold in the parameter library is dynamically corrected through the feedback mechanism of process execution data, and parameter reuse and collaborative optimization across process chains are supported.

[0076] S2, establish parameter solving method based on multi-objective collaborative optimization: in this embodiment, first, surface treatment key performance indicators such as coating hardness, bonding strength, porosity and residual stress are taken as optimization objectives. Physical constraint conditions such as material thermal expansion coefficient and substrate deformation are combined to construct a multi-process parameter collaborative optimization model. Then, genetic algorithm and response surface method are combined to generate parameter initial population through experimental design. Finite element simulation and physical experiment data are used to iteratively correct objective function, and the nonlinear coupling effect between parameters is quantified, such as the influence of the collaborative action of laser power and micro-arc oxidation voltage on coating crack sensitivity. On this basis, adaptive weight adjustment strategy is introduced to dynamically balance the competition relationship between multiple objectives, such as the contradiction between hardness improvement and porosity control. Optimal parameter combination that meets multiple constraint conditions is generated, such as laser power 1520W, scanning speed 5.5mm / s and micro-arc oxidation voltage 452V collaborative matching.

[0077] S3, construct modular process chain: as shown in Figure 3As shown, the surface treatment full process is first divided into three modules of pretreatment, main treatment and post-treatment, the pretreatment is such as cleaning or sand blasting, the main treatment is such as laser cladding, micro-arc oxidation or chemical plating, and the post-treatment is such as vacuum hole sealing or stress relief heat treatment, each module is further refined into an independent process unit, such as the cleaning module includes sub-units of alkali washing, acid washing, deionized water rinsing and the like, and the standardized input and output interfaces of the module are defined, such as the input of the pretreatment module is the base material and the initial surface roughness, and the output is the cleanliness and the activation energy state; the input of the main treatment module is the base surface after pretreatment, and the output is the coating thickness and the microstructure characteristics; then the transmission rules of the parameters and data between the modules are established, the cross-module matching of the process parameters is realized through a hierarchical coding system such as step S1, such as the surface roughness parameter after sand blasting roughening needs to be dynamically associated with the power-scan speed combination of laser cladding, and a process chain dynamic reorganization algorithm is designed, according to the material type of the aviation part such as titanium alloy, high-temperature alloy, the performance requirement such as wear resistance, corrosion resistance and the geometric characteristics such as thin-walled part and complex cavity, the optimal process module combination is automatically matched, such as for TC4 titanium alloy engine blade, the recommended process chain is “ultrasonic cleaning → sand blasting (Ra3.2μm) → laser cladding (NiCrBSi alloy) → micro-arc oxidation (ceramic coating) → vacuum hole sealing”, and for high-temperature alloy turbine disc, it is adjusted to “chemical degreasing → laser shock peening → chemical nickel plating → heat treatment”.

[0078] S4, real-time monitoring and closed-loop control of multi-source data fusion: first, high-precision sensor arrays are deployed at key process nodes such as laser cladding molten pool, micro-arc oxidation electrolytic cell, and chemical plating reaction cavity, multi-dimensional data such as temperature field, stress distribution, electrochemical signal and spectral characteristics are collected in real time, and data pre-processing such as filtering and noise reduction, feature extraction is carried out through edge computing nodes, and key state parameters such as molten pool temperature fluctuation rate and electrolyte conductivity change rate are compared with the threshold range in the standardized parameter library; when the key state parameter monitoring data deviates from the preset threshold, the system automatically triggers the closed-loop control mechanism, and a fuzzy PID control algorithm is used to dynamically adjust the process parameters, such as if the molten pool temperature exceeds the upper threshold by 5% during laser cladding, the laser power is reduced by 2% and the scanning speed is increased by 3%, and the substrate cooling air flow compensation is started at the same time, and the process effect after parameter adjustment such as coating crystal orientation change and residual stress evolution trend is predicted through the digital simulation model in step S5, to ensure that the adjusted parameter combination still meets the performance target; in addition, the parameter data before and after adjustment, the state monitoring value and the quality detection result such as microhardness and bonding strength are associated and stored in the full-process quality traceability database, forming a complete closed loop of “monitoring-decision-execution-feedback”.

[0079] S5, establishing a digital simulation body and verifying: Figure 4As shown, first, a digital simulation body covering the whole process of pre-processing, main processing and post-processing is constructed, through deep integration of high-precision finite element models such as thermal-electric-chemical multi-field coupling models and process parameter standardization library, real-time simulation of physical field evolution under the synergistic action of multiple process parameters such as laser cladding molten pool flow, micro-arc oxidation plasma discharge, chemical plating layer growth kinetics and coating microstructure formation process such as grain orientation, phase composition distribution; then, the real-time monitoring data in step S4 and the virtual simulation results are bidirectionally mapped, through the model correction mechanism driven by data such as dynamic iteration of parameter calibration based on Bayesian optimization digital simulation body accuracy, so that the prediction error of the coating hardness, bonding strength and porosity and other key performances is controlled within 3%; on this basis, the virtual simulation body is used to carry out process limit test such as coating failure simulation under extreme parameter combination and fault tolerance analysis such as process robustness evaluation when the sensor fails, to identify potential defects such as crack initiation position and interface debonding risk in advance, and output optimization suggestions such as adjusting the laser power gradient and optimizing the micro-arc oxidation pulse waveform; finally, the parameter combination that passes the virtual verification is pushed to the actual production line for execution.

[0080] S6, construct a whole-process quality traceability database: as Figure 5 As shown, first, through the standardized parameter coding system and the process chain modular identification, the substrate material, process path such as "laser cladding + micro-arc oxidation", each process parameter such as laser power, electrolyte concentration and real-time monitoring data such as temperature curve, stress distribution of each batch of aviation parts are stored in a structured manner, and are bound with the quality detection results such as coating hardness, bonding strength, corrosion resistance test value and the unique identity of the part such as two-dimensional code / RFID; then, based on the graph database technology, a multi-dimensional correlation model is established, which supports penetration traceability according to part number, process type, time interval or quality defect type such as excessive porosity and crack initiation, and quickly locates abnormal parameter nodes such as when the coating bonding strength of a batch of parts is found to be insufficient, the abnormal record of the voltage fluctuation exceeding 5% in the micro-arc oxidation process can be traced back; in addition, machine learning algorithms are integrated to deeply mine historical quality data, automatically extract the association rules of parameter deviation and defect mode such as "when the laser scanning speed is lower than 8mm / s and the substrate temperature exceeds 200℃, the coating crack risk increases by 40%", and generate visual defect traceability report and process improvement suggestions; finally, through the cloud data sharing platform, cross-department and cross-enterprise quality data collaboration is realized, the defect traceability efficiency is improved by more than 90%, the process reproduction success rate is stabilized at more than 98%, and through the closed-loop feedback of historical defect data, the continuous optimization of the standardized parameter library in step S1 is promoted, forming a virtuous iteration mechanism of "quality monitoring-defect traceability-process improvement".

[0081] S7, build a process intelligent decision and adaptive optimization system: as Figure 6As shown, first, the historical process data in the whole-process quality traceability database, real-time monitoring information and virtual verification results are integrated, the complex nonlinear relationship between process parameters, environmental variables and coating performance is mined through deep learning algorithms such as graph convolution network, an intelligent decision-making model across the process chain is established, and the optimal process parameter combination is automatically recommended according to the part type such as engine blade, fuselage frame, performance requirement such as high temperature wear resistance, corrosion resistance and real-time working condition such as equipment state fluctuation, environmental temperature and humidity change; for a certain high-temperature alloy part, the model can integrate historical data and real-time equipment state, dynamically adjust the synergistic matching relationship of laser cladding power and micro-arc oxidation voltage; then, the adaptive optimization engine is deployed, the process execution effect is evaluated in real time based on reinforcement learning algorithms such as PPO policy gradient algorithm, and the parameter decision logic is dynamically corrected through a closed-loop feedback mechanism, such as when the coating hardness deviates from the target value, the chemical plating solution pH value and the deposition time compensation amount are automatically adjusted, so that the process system has the ability of self-learning and continuous improvement; finally, through the virtual-real interaction verification between the digital simulation body and the physical production line, the stability and reliability of the optimized parameter combination under complex working conditions are ensured, the process decision-making efficiency is improved by more than 70%, the batch consistency of key performance indicators such as coating life and bonding strength is improved to 95%, and through the self-evolution mechanism of the intelligent decision-making system, the surface treatment process is transformed from experience-driven to data-driven, significantly enhancing the intelligent level and core competitiveness of complex part surface treatment in the field of aviation manufacturing.

[0082] The above-described embodiments are merely preferred embodiments of the present application and are not intended to limit the scope of the present application. Without departing from the design spirit of the present application, various modifications and improvements to the technical solutions of the present application made by those of ordinary skill in the art shall fall within the scope of protection determined by the claims of the present application.

Claims

1. A standardized optimization method for collaborative surface treatment of multiple process parameters for aerospace parts, characterized in that: It includes: S1. Construct a hierarchical coding system and correlation mapping model for process parameters: Divide surface treatment process parameters into basic parameters and collaborative parameters, and establish a three-level coding rule; A standardized parameter library is created and the coupling threshold in the standardized parameter library is dynamically corrected. By using first-level coding to identify process type, second-level coding to identify parameter category, and third-level coding to identify the range and precision of parameter values, standardized identification and traceability of parameters are achieved. Through experimental design and multi-field coupling simulation, the correlation between basic parameters and collaborative parameters is quantified, a parameter coupling model is established, and a collaborative threshold range is defined, forming a standardized parameter library that includes parameter classification, coding rules, and collaborative constraints. Finally, the coupling threshold in the parameter library is dynamically corrected through a feedback mechanism of process execution data. The coupling threshold in the standardized parameter library is dynamically adjusted using process execution data. The formula for adjusting the coupling threshold is as follows: ； Among them, the correction amount The calculation formula is as follows: ； In the formula: This is the coupling threshold between the corrected process parameters i and j; The coupling threshold between the original process parameters i and j in the standardized parameter library; This is a correction factor used to control the correction magnitude; its range is 0 < ≤1; This is a quantification coefficient for the correlation between process parameters i and j, reflecting the strength of the correlation between basic parameters and synergistic parameters, with a range of 0 ≤ ≤1; This represents the occasional error between process parameters i and j during actual execution; The maximum permissible occasional error is determined based on process requirements and historical data; and These are the upper and lower limits of the coupling threshold between process parameters i and j, respectively. S2. Establish a parameter solution method based on multi-objective collaborative optimization: Taking the key performance indicators of surface treatment processes as optimization objectives, and combining physical constraints, construct a multi-process parameter collaborative optimization model to solve for the optimal parameter combination that satisfies multiple constraints. ； ； ； ； Where: objective function Let m key performance indicators be the optimization targets; There are p physical constraints; There are q equality constraints; Let be the range of values ​​for the i-th process parameter; S3. Construct a modular process chain: Decompose the surface treatment process into three major modules: pretreatment, main treatment and posttreatment. Each module is further divided into multiple process units. Establish rules for the transfer of parameters and data between modules. A hierarchical coding system is used to achieve cross-module matching of process parameters and automatically match the optimal combination of process units. S4. Establish real-time monitoring and closed-loop control for multi-source data fusion: compare key state parameters with the threshold range in the standardized parameter library to ensure that the key state parameters are within the threshold range. S5. Establish a digital simulation and verify it; S6. Construct a full-process quality traceability database.

2. The standardized optimization method for collaborative surface treatment of multiple process parameters for aerospace parts according to claim 1, characterized in that: In step S3, each module is further subdivided into independent process units based on the process content specified in the surface treatment process standard, and standardized input and output interfaces of the three major modules are defined.

3. The standardized optimization method for collaborative surface treatment of multiple process parameters for aerospace parts according to claim 1, characterized in that: The specific steps in step S2 for solving the optimal parameter combination that satisfies multiple constraints using a multi-process parameter collaborative optimization model are as follows: using a combination of genetic algorithm and response surface methodology, an initial parameter population is generated through experimental design, and the objective function is iteratively corrected using finite element simulation and physical experimental data to quantify the nonlinear coupling effect between parameters; an adaptive weight adjustment strategy is introduced to dynamically balance the competitive relationship between multiple objectives and generate the optimal parameter combination that satisfies multiple constraints.

4. The standardized optimization method for collaborative surface treatment of multiple process parameters for aerospace parts according to claim 1, characterized in that: In step S3, the optimal combination of process units is automatically matched based on the material type, performance requirements and geometric characteristics of the aerospace parts using a decision tree algorithm.

5. The standardized optimization method for collaborative surface treatment of multiple process parameters for aerospace parts according to claim 1, characterized in that: In step S4, when the key state parameters deviate from the preset threshold, the closed-loop control mechanism is automatically triggered. The process parameters are dynamically adjusted using PID control or fuzzy control algorithms, and the process effect after parameter adjustment is predicted through the digital simulation in step S5. The parameter data before and after adjustment, the state monitoring values, and the quality inspection results are associated and stored in the full-process quality traceability database in step S6, forming a complete closed loop of monitoring-decision-execution-feedback.

6. The standardized optimization method for collaborative surface treatment of multiple process parameters for aerospace parts according to claim 5, characterized in that: In step S5, a digital simulation body covering the entire process of preprocessing, main processing and postprocessing is constructed. Through the finite element model and standardized parameter library, the physical field evolution and surface treatment microstructure formation process under the synergistic effect of multiple process parameters are simulated in real time. The real-time monitoring data in step S4 is bidirectionally mapped to the virtual simulation results, and the accuracy of the digital simulation is dynamically iterated through a data-driven model correction mechanism.

7. The standardized optimization method for collaborative surface treatment of multiple process parameters for aerospace parts according to claim 6, characterized in that: The specific steps for constructing the full-process quality traceability database in step S6 are as follows: S61. Through the standardized parameter coding system of step S1 and the modular process chain of step S3, the base material, process path, parameters of each process and real-time monitoring data of aerospace parts are stored in a structured manner, and the quality inspection results are bound to the unique identification of the parts. S62. Based on graph database technology, establish a multi-dimensional association model to perform penetrating traceability by part number, process type, time interval or quality defect type, and locate abnormal parameter nodes; integrate machine learning algorithms to deeply mine historical quality data, automatically extract the association rules between parameter deviation and defect pattern, and generate a visualized defect tracing report and process improvement suggestions. S63. Achieve cross-departmental quality data collaboration through a cloud-based data sharing platform, and promote continuous optimization of the standardized parameter library through closed-loop feedback of historical defect data, forming a virtuous cycle of quality monitoring, defect tracing, and process improvement.

8. The standardized optimization method for collaborative surface treatment of multiple process parameters of aerospace parts according to claim 1, characterized in that: It also includes step S7, constructing a process intelligent decision-making and adaptive optimization system, the specific steps of which are as follows: S71. Based on the historical process data in the full-process quality traceability database in step S6, the real-time monitoring information of key state parameters in step S4, and the virtual verification results in step S5, the nonlinear relationship between process parameters, environmental variables, and surface treatment performance is obtained through deep learning algorithms, and an intelligent decision-making model across the process chain is established. S72. Real-time evaluation of process execution effect based on reinforcement learning algorithm, and dynamic correction of parameter decision logic through closed-loop feedback mechanism; S73. Verify the interaction between the digital simulation and the physical production line.

Images