A method for monitoring and analyzing the quality of laser selective melting molding

Abstract

The present application belongs to the technical field of laser selective melting forming, and specifically, relates to a method for monitoring and analyzing the quality of laser selective melting forming, including step 1: starting the device, loading a self-learning correction file, and correcting the default process parameters; step 2: inputting a 3D model file into the device, selecting a printing mode to obtain printing parameters, performing a rationality check and compensation correction parameter test, and generating a printing task; step 3: the intelligent printing module controls the printer to print in a single layer, and the intelligent analysis module simultaneously performs real-time data collection, data analysis, and printing effect evaluation on the single layer printing, and prints the next layer after the single layer printing quality is judged to be qualified; step 4: the intelligent analysis module implements self-learning, printing is completed, and an overall printing quality report is output; the method of the present application can realize real-time data collection, data analysis, and printing effect evaluation, and different parameters corresponding to different feature positions can make the quality of the printed layer uniform and improve the quality of the printing effect.

Description

Technical Field

[0001] The present invention belongs to the technical field of laser selective melting forming, and in particular relates to a laser selective melting forming quality monitoring and analysis method. Background Art

[0002] Selective laser melting (SLM) forms parts by stacking layers, and defects are inevitable during the molding process. Detecting these defects early on is a major challenge facing additive manufacturing. In recent years, calls for online monitoring of additive manufacturing have grown increasingly louder. Implementing online monitoring can identify and resolve manufacturing problems immediately, ensuring molding quality. With technological advancements, the demands for additive manufacturing quality are becoming increasingly stringent, and existing detection methods are no longer able to meet the high automation and rapid response requirements of modern manufacturing. Therefore, a new method for online monitoring of additive manufacturing quality is needed. Summary of the Invention

[0003] In response to the shortcomings of the existing technology, the present invention proposes a method for monitoring and analyzing the quality of laser selective melting molding. The 3D model file is input into the computer control system, and printing parameters are generated by selecting an adaptive printing mode or a manually input printing mode. The intelligent printing module controls the printer to print in a single layer, and the intelligent analysis module simultaneously performs real-time data collection, data analysis and printing effect evaluation on the single layer printing. Compared with traditional data management, the data targets are more specific and accurate. Different parameters corresponding to different feature positions can make the quality of the printed layer uniform. At the same time, it has a self-learning function, can optimize the printing parameters, and improve the quality of the printing effect.

[0004] To achieve the above-mentioned purpose, the technical solution adopted by the present invention provides a method for monitoring and analyzing the quality of laser selective melting molding, and the method comprises:

[0005] Step 1: Start the laser selective melting equipment, initialize the equipment settings, restore the process parameters to the default values, load the self-learning correction file, and correct the default process parameters;

[0006] Step 2: After the process parameters of step 1 are corrected, the 3D model file is input into the computer control system of the equipment. According to the printing mode type and printing requirements, the adaptive printing mode or the manual input printing mode is selected to obtain the model parameters. After rationality verification and compensation correction, the printing task is generated.

[0007] Step 3: Based on the print task generated in step 2, the intelligent printing module controls the printer to print a single layer. The intelligent analysis module simultaneously performs real-time data collection, data analysis, and printing effect evaluation on the single layer printing. After the single layer printing quality is evaluated as qualified, the next layer is printed. The single layer printing process is repeated until the printing is completed.

[0008] Step 4: During the overall printing process in step 3, various data during the printing process are recorded in the database, and the default printing parameters are adjusted in combination with past printing records to achieve self-learning of the intelligent analysis module. After the overall printing is completed, an overall printing quality report is output.

[0009] Furthermore, generating a print task in step 2 specifically includes:

[0010] Step 2.1: Select the adaptive printing mode to obtain the basic parameters of the 3D model file, perform intelligent analysis of the model based on the basic parameters, and generate the printing parameters of the adaptive printing mode; select the manual input printing mode to obtain the printing parameters of the 3D model file, and implement default value completion for the printing parameters of the manual input printing mode;

[0011] Step 2.2: The intelligent analysis module performs a rationality check based on the printing parameters generated by the adaptive printing mode in step 2.1 or the printing parameters generated by the manual input printing mode, and performs compensation correction based on the relevant process parameters set in step 1. After the compensation correction is completed, printing is ready.

[0012] Furthermore, step 3 implements intelligent printing and print quality evaluation based on step 2, specifically including:

[0013] Step 3.1: Single-layer printing begins. The intelligent printing module controls the equipment to spread powder. The intelligent analysis module collects data for single-layer printing, capturing real-time images of the melt pool to obtain information such as melt pool size, melt pool temperature field, and spatter. Images of the formed surface are captured to obtain the molded surface morphology, molded surface temperature field, molded dimensions, and related information. Finally, images of the powder-spreading surface are captured.

[0014] Step 3.2: The intelligent analysis module in the computer control system performs real-time analysis of the powder laying quality, melt pool, spatter, temperature field data, and molding surface of the single-layer printing;

[0015] Step 3.3: After the single-layer printing is completed, the laser scanning stops, and the intelligent analysis module evaluates the single-layer printing effect. The printing quality is scored on a 10-point scale based on the number of Class II defects and Class III defects found.

[0016] Step 3.4: Repeat steps 3.1 to 3.3, and print the next layer after the printing quality of each layer is judged to be qualified, until the entire printing is completed.

[0017] Furthermore, the analysis by the intelligent analysis module in step 3.2 specifically includes:

[0018] Step 3.2.1: First, analyze the powder spreading quality by comparing images before and after spreading. Calculate the percentage of powder coverage area through visual monitoring, spreading force, acceleration, and vibration monitoring. If the spreading is unsatisfactory, re-spread the powder.

[0019] Step 3.2.2: After the powder coating is tested and qualified in step 3.2.1, the intelligent analysis module analyzes and determines whether the environmental parameters meet the printing conditions by monitoring and analyzing the environmental parameters. If it is judged to be unqualified, it waits for the conditions to be met;

[0020] Step 3.2.3: After the environmental parameters in step 3.2.2 meet the printing conditions, the printer starts laser scanning and monitors the printing power, forming vision and forming temperature field in real time. If Class I defects are detected during the printing process, printing is terminated; if the printing process monitoring is normal, the printer continues printing until the current layer is printed.

[0021] Furthermore, the print quality scoring method in step 3.3 specifically includes:

[0022] If 10 points > score ≥ 8 points, the current layer printing ends and the next layer printing begins;

[0023] If 8 points > score ≥ 4 points, the system will handle it automatically;

[0024] If 4 points > score ≥ 2 points, printing will be stopped and an alarm will be issued, prompting manual intervention to modify the printing parameters. The process parameters will be manually modified according to the printing quality and the modified parameters will be displayed;

[0025] If the score is less than 2 points, printing will be terminated and an alarm will be issued, indicating that a serious defect has occurred and manual processing is required;

[0026] After the problem defects of 8 points > score ≥ 4 points and 2 points > score ≥ 4 points are processed, the intelligent analysis module re-scores the quality of the current layer, and enters the next layer printing if the score is ≥ 8.

[0027] Furthermore, the defect types recorded by the intelligent analysis module include Type I defects, Type II defects, and Type III defects;

[0028] Class I defects require machine downtime to resolve, significantly impacting the build quality and preventing further printing. These defects include interlayer fractures, macro cracks, severe local warping, and related defects.

[0029] Class II defects are defects that have a moderate impact on the mechanical properties, density, and surface quality of the formed parts, including pores, lack of fusion, microcracks, protrusions, and related defects;

[0030] Class III defects are defects that have a slight impact on the mechanical properties, density, and surface quality of the formed parts, including surface powder adhesion, spatter, and related defects.

[0031] Furthermore, the basic parameters in the adaptive printing mode of step 2.1 include laser power, scanning speed, scanning spacing, layer thickness, substrate temperature and related parameters;

[0032] The printing parameters in the manual input printing mode include basic parameters, printing angle, layer rotation angle, volume compensation coefficient and printing layer depth coefficient.

[0033] Furthermore, the intelligent analysis of the model in step 2.1 includes model feature identification and classification, model risk assessment and intelligent support;

[0034] Feature recognition classification includes supports and entities. Entities include thin-wall, non-thin-wall, outer surface, transition layer, and inner layer features. Model risk assessment identifies locations where problems may occur during the printing process and issues warnings. Intelligent support adds support reinforcement structures to the original supports or at risk locations.

[0035] Furthermore, the rationality check of the printing parameters in step 2.2 is performed by reading the 3D model file based on the intelligent analysis module, automatically analyzing the model features, analyzing the process parameters matching different feature parts of the model, and autonomously selecting matching process parameters from the database according to the material type of the model for printing; if there are no matching process parameters in the database, the laser selective melting molding device prompts manual intervention, manually inputs the process parameters used for the relevant features, and records the printing results and related data, and supplements the database;

[0036] The intelligent analysis module obtains the printing parameters of the 3D model by reading the 3D model file output in a layer structure mode by the slicing software in the computer control system of the device, compensates and corrects the relevant process parameters set in step 1, controls the completion of printing, records the printing results and related data, and enters them into the database.

[0037] Furthermore, the self-learning module in step 4 records the printing process parameters according to the molding characteristics, judges the process parameters according to the molding results of this characteristic, and compares the relevant parameters already in the database. If the judgment result is better, the relevant data is updated, and the modification log is recorded, the printing results are evaluated, and self-learning correction files are generated regularly to correct the deviations caused by the long-term use of the printer.

[0038] The beneficial effects of the present invention are:

[0039] First, the present invention loads a self-learning file into the device, inputs the 3D model file into the computer control system, generates printing parameters by selecting an adaptive printing mode or a manually input printing mode, and the intelligent printing module controls the printer to print according to a single layer. The intelligent analysis module simultaneously performs real-time data collection, data analysis and printing effect evaluation on the single-layer printing. By adding supports, slicing, path planning and parameter allocation, the data targets are more specific and accurate than traditional data management. Different parameters corresponding to different feature positions can make the quality of the printed layer uniform and improve the quality of the printing effect. After the single-layer printing quality is judged to be qualified, the next layer is printed, and the single-layer printing process is repeated until the printing is completed. After printing, a complete report of the printing process is output. The intelligent analysis module combines the current printing report with past printing records to perform analysis and self-learning, optimize the printing parameters, and can automatically compare similar cases in the database to evaluate the current printing effect and obtain recommended parameters. At the same time, it performs self-upgrades, enriches the database, outputs parameter correction files, calculates losses while optimizing the process, compensates for the effects of machine wear and aging, optimizes the next printing, and can improve the printing quality.

[0040] Second, the present invention comprehensively monitors the selective laser melting process. The monitoring data is connected to the intelligent analysis module, which can intervene in the printing process. The intelligent analysis classifies defects into three categories according to their impact, and automatically determines and handles them accordingly based on the printing quality. The intelligent analysis module can process real-time monitoring data and analyze the melt pool, spatter, temperature field, molding surface quality, powder spreading quality, etc., including measuring the melt pool size, existence time, keyhole condition, spatter size and flight direction.

[0041] Third, the method of the present invention can control the entire process of laser selective melting manufacturing, from original model analysis, support addition, model slicing, path planning, control of printing production, full printing process monitoring, printing process quality feedback, to final molding quality recording, and the entire process can be completed independently; some content such as modeling, support addition, slicing and path planning, printer control, etc. can be delivered to other computer control systems, and the system of the present invention works as an interface and core analysis and processing unit. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 This is the overall flow chart of the laser selective melting molding quality monitoring and analysis method of the present invention;

[0043] Figure 2 This is a flowchart of generating a print task in step 2 of the present invention;

[0044] Figure 3 This is a flow chart of the intelligent analysis module of the present invention for judging the single-layer printing effect;

[0045] Figure 4This is a simplified structural diagram of a part to be printed according to an embodiment of the present invention;

[0046] Figure 5 is a printing layer division diagram of a part to be printed according to an embodiment of the present invention;

[0047] Figure 6 is a diagram of the division of the printing area of ​​the part to be printed according to an embodiment of the present invention;

[0048] Figure 7 This is a single-layer quality scoring evaluation chart of an embodiment of the present invention. DETAILED DESCRIPTION

[0049] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0050] The present invention provides a method for monitoring and analyzing the quality of selective laser melting (SLM). This method is implemented using SLM equipment, which includes a mechanical system, an optical system, and a computer control system. The mechanical system primarily consists of a frame, a lifting platform, an automatic powder spreading device, a material collection box, and related components. The optical system primarily comprises an indicator, a beam combiner, a reflector, a beam expander, a focusing lens, a scanner, and related components. The computer control system includes an intelligent printing module, an intelligent analysis module, a real-time forming visual monitoring module, a self-learning module, a database, and related module control units.

[0051] The laser selective melting molding quality monitoring and analysis method of the present invention uses a computer control system or multiple computer control systems to control the coordinated work of the mechanical system and the optical system, thereby realizing original model analysis, support addition, model slicing, path planning, control of printing production, full printing process monitoring, printing process quality feedback and molding quality recording, and automatically completing the processing and molding of the workpiece.

[0052] like Figure 1 As shown, the laser selective melting forming quality monitoring and analysis method of the present invention includes:

[0053] Step 1: Start the laser selective melting equipment, initialize the equipment settings, restore the process parameters to the default values, load the self-learning correction file, and correct the default process parameters.

[0054] Step 2: After the process parameters of step 1 are corrected, the 3D model file is input into the computer control system of the equipment. According to the printing mode type and printing requirements, the adaptive printing mode or the manual input printing mode is selected to obtain the model parameters. After rationality verification and compensation correction, the printing task is generated.

[0055] Step 3: Based on the printing task generated in step 2, the intelligent printing module controls the printer to print in a single layer. The intelligent analysis module simultaneously performs real-time data collection, data analysis, and printing effect evaluation on the single-layer printing. After the single-layer printing quality is judged to be qualified, the next layer is printed. The single-layer printing process is repeated until the printing is completed, thereby realizing intelligent printing.

[0056] Step 4: During the overall printing process in step 3, various data during the printing process are recorded in the database. Combined with past printing records, the default printing parameters are adjusted to achieve self-learning of the intelligent analysis module. After the overall printing is completed, the overall printing quality report is output.

[0057] Specifically, the process parameters in step 1 include laser parameters, machine tool operating parameters, molding process parameters, external environment parameters, and result input parameters. Machine tool operating parameters include circulating airflow, internal environment airtightness, and mechanical system operating accuracy. Result input parameters include molding density, surface roughness, defects, and related parameters. Internal environment airtightness includes temperature, humidity, and oxygen content. Mechanical system operating accuracy includes powder spreading smoothness and layer thickness uniformity and stability.

[0058] The contents of the self-learning correction file are based on factory commissioning, aging, and other factors. Each device's factory-set process parameters vary. Compensation parameters are set to match the device's process parameters during factory commissioning. Long-term equipment wear and tear can cause aging. The settings in the self-learning file continuously update the compensation parameters as the device is used, minimizing the impact of these issues on the product and ensuring that processing quality remains within process limits. Actual processing differs from theoretical processing, so process compensation parameters are set in the self-learning file based on experience.

[0059] like Figure 2 As shown, the printing mode type of step 2 includes adaptive printing mode or manual input printing mode, and the two printing modes operate independently. Step 2 generates a printing task specifically including:

[0060] Step 2.1: Select the adaptive printing mode to obtain the basic parameters of the 3D model file, perform intelligent analysis of the model based on the basic parameters, and generate the printing parameters of the adaptive printing mode; select the manual input printing mode to obtain the printing parameters of the 3D model file, and implement default value completion for the printing parameters of the manual input printing mode.

[0061] The basic parameters in the adaptive printing mode are used to meet the parameters required by the forming target, determine the printing efficiency and special effects, and are selectively input into the device according to the printing requirements. The basic parameters include laser power, scanning speed, scanning spacing, layer thickness, substrate temperature and related parameters; the printing parameters in the manually input printing mode are used to determine the printing forming quality. The printing parameters include not only the basic parameters, but also the printing angle, layer rotation angle, volume compensation coefficient and printing layer depth coefficient.

[0062] Intelligent analysis of 3D models in adaptive printing mode includes model feature recognition and classification, model risk assessment, and intelligent support. Feature recognition and classification include supports and solids, with solids including thin-wall, non-thin-wall, exterior surface, transition layer, and interior layer features. Model risk assessment identifies and issues warnings about model problems during printing. Intelligent support adds supports to existing supports or at risk locations to strengthen the structure.

[0063] Step 2.2: The intelligent analysis module performs a rationality check based on the printing parameters generated by the adaptive printing mode in step 2.1 or the printing parameters generated by the manual input printing mode, and performs compensation correction based on the relevant process parameters set in step 1. After the compensation correction is completed, printing is ready.

[0064] The intelligent analysis module reads the 3D model file and automatically analyzes the model features, identifying the process parameters that match the model's different features. Based on the model's material type, it automatically selects matching process parameters from a database for printing. If no matching process parameters are found in the database, the laser selective melting machine prompts for manual intervention. The machine then records the print results and related data, which are then added to the database.

[0065] The intelligent analysis module obtains the printing parameters of the 3D model by reading the 3D model file output in a layer structure mode by the slicing software in the computer control system of the device, compensates and corrects the relevant process parameters set in step 1, controls the completion of printing, records the printing results and related data, and enters them into the database.

[0066] like Figure 3 As shown, step 3 implements intelligent printing and print quality evaluation based on step 2, specifically including:

[0067] Step 3.1: Single-layer printing begins. The intelligent printing module controls the equipment to spread powder. The intelligent analysis module collects data for single-layer printing, collects the melt pool image in real time, obtains information such as the melt pool size, melt pool temperature field, and spatter, collects the image of the formed surface, obtains the forming surface morphology, forming surface temperature field, forming size and related information, and collects the powder-spreading surface image.

[0068] The intelligent analysis module in this invention processes the captured images, identifying and recording melt pool, spatter, and defect information. Melt pool information calculates the melt pool's length and width, measures its maximum temperature, and records its continuous changes. Spatter information calculates the center position of spatter particles and records their flight direction, starting position, and landing location. Defect information identifies the type of printing defect and records its type, location, and size.

[0069] The defect types recorded by the intelligent analysis module include Class I, Class II, and Class III defects. Class I defects require machine downtime to resolve, significantly impacting the build quality and preventing further printing. These defects include interlayer fractures, macro cracks, severe local warping, and related defects. Class II defects moderately impact the mechanical properties, density, and surface quality of the molded part, such as pores, lack of fusion, microcracks, protrusions, and related defects. Class III defects mildly impact the mechanical properties, density, and surface quality of the molded part, including surface powder adhesion, spatter, and related defects.

[0070] Step 3.2: The intelligent analysis module in the computer control system performs real-time analysis on the powder laying quality, melt pool, spatter, temperature field data and molding surface of single-layer printing.

[0071] It should be noted that the powder spreading analysis checks the integrity and uniformity of the powder spreading. If the powder is not fully spread or uneven, the powder will be spread again. If the unevenness is repeated multiple times, the powder spreading defect will be recorded and the next step will be carried out. If it is found that the part is not fully spread due to high warping, and the powder spreading arm sensor data is abnormal, it is judged that the part has Class I defects, and the machine will be stopped and wait for processing.

[0072] The molten pool analysis is to analyze the changes in the molten pool morphology over time based on the changes in the molten pool length, width and maximum temperature, and to judge whether the current molten pool state is qualified based on the molten pool size and temperature.

[0073] Spatter analysis records the flight of spatter particles based on their center position, calculates the number of spatter particles generated per unit time, and distinguishes the type of spatter based on their starting position. Temperature field monitoring assists in determining the impact on molding quality based on the landing position of the spatter particles.

[0074] Temperature field analysis is to analyze the temperature field of the molten pool and the temperature field of the forming surface, qualitatively analyze the residual stress based on the temperature field conditions, and assist in determining the number, size and location of surface defects.

[0075] Molding surface analysis determines whether there are any abnormalities in the temperature field distribution of the molding surface of a single layer, and assists in determining the location of defects. It extracts the molding surface contour and compares it with the model cross-section to analyze the molding dimensional accuracy, and counts the location, size, number and printing surface size of the current layer's printing defects.

[0076] Step 3.2.1: The first step in analyzing the powder spreading quality is to compare the images before and after the powder spreading. Through visual monitoring of the powder spreading, the powder spreading force, acceleration and vibration monitoring, the percentage of powder coverage area is calculated. If the powder spreading is unqualified, the powder is spread again.

[0077] The powder spreading quality analysis of the present invention can simultaneously judge the bonding quality between printed layers. If there is a long-term poor one-sided powder spreading coverage rate resulting in poor interlayer bonding and warping defects caused by poor interlayer bonding, it will be judged as a Class I defect and printing will be terminated.

[0078] Step 3.2.2: After the powder spreading is qualified in step 3.2.1, the intelligent analysis module analyzes and judges the environmental parameters. By monitoring and analyzing the environmental parameters, it determines whether the environmental parameters meet the printing conditions. If it is judged to be unqualified, it waits for the conditions to be met.

[0079] Environmental parameters include ambient temperature and humidity monitoring, air flow monitoring, and substrate temperature.

[0080] Step 3.2.3: After the environmental parameters in step 3.2.2 meet the printing conditions, the printer starts laser scanning and monitors the printing power, forming vision, and forming temperature field in real time. If a Class I defect problem is detected during the printing process, printing is terminated; if the printing process monitoring is normal, the printer continues printing until the current layer is printed.

[0081] It should be noted that in step 3.2, when the intelligent analysis module detects in real time that the printing defect is a Class I defect problem in single-layer printing, it is determined that the printing has failed and the printing is terminated.

[0082] Step 3.3: After the single-layer printing is completed, the laser scanning stops, and the intelligent analysis module evaluates the single-layer printing effect. The printing quality is scored on a 10-point scale based on the number of Class II defects and Class III defects.

[0083] If 10 points > score ≥ 8 points, the current layer printing is completed and the next layer printing is started; if 8 points > score ≥ 4 points, the system handles it automatically; if 4 points > score ≥ 2 points, printing is terminated and an alarm is issued, prompting manual intervention to modify the printing parameters. The process parameters are manually modified according to the printing quality and printing is carried out, and the modified parameters are displayed; if the score is less than 2 points, printing is terminated and an alarm is issued, indicating that a serious defect has occurred and manual processing is required.

[0084] After the problem defects of 8 points > score ≥ 4 points and 2 points > score ≥ 4 points are processed, the intelligent analysis module re-scores the quality of the current layer, and enters the next layer printing if the score is ≥ 8.

[0085] Step 3.4: Repeat steps 3.1 to 3.3. After each layer is judged as qualified, print the next layer until the entire printing is completed.

[0086] The print quality report in step 4 includes various printing parameters, print quality estimation, abnormal conditions such as detected print defects and their locations, printer abnormalities, and printing and maintenance recommendations.

[0087] It should be noted that the various parameters printed in the print quality report include changes during the entire printing process.

[0088] The self-learning module records printing process parameters based on molding features, determines these parameters based on the molding results of these features, and compares them to relevant parameters already in the database. If the judgment result is superior, the relevant data is updated and a modification log is recorded. The module comprehensively evaluates the printing results and regularly generates self-learning correction files to correct deviations caused by long-term wear and tear on the printer.

[0089] The self-learning module includes comparing printing quality when process parameters are the same or similar, and statistically analyzing the factors that cause quality differences; analyzing the feature classification of each part of the current printing task, comparing it with the data in the database, and modifying or supplementing the database after judgment; evaluating the correction effect of the reference and supplementary documents and modifying them; evaluating the analysis effect of the intelligent model, recording and feedback, and modifying the judgment methods of modules such as intelligent features, model risks, and intelligent support.

[0090] The database includes a defect database and other databases. The defect database is a problem database for Class I, Class II, and Class III defects. Other databases include print reports, database modification logs, model features, typical process monitoring data, typical quality assessment data, process parameters such as laser power, scanning speed, scanning spacing, layer thickness, scanning mode, filling mode, circulating air volume, heating temperature, and ambient oxygen content; forming effect data such as melt pool size, actual overlap rate, and temperature; forming quality data such as density, roughness, and defects; and other related data.

[0091] Example:

[0092] like Figure 4 The figure shows a 3D model of the part to be printed, taking the adaptive printing mode as an example.

[0093] Step 1: Start the laser selective melting equipment, initialize the equipment settings, restore the process parameters to the default values, and load the self-learning correction file.

[0094] Step 2: Input the 3D model file into the computer control system of the equipment and select the adaptive printing mode. To quickly obtain the part, choose to use a larger layer thickness for printing in the adaptive printing mode. Obtain the two basic parameters of material 316L and layer thickness 0.05mm.

[0095] The system performs intelligent model analysis on the printed parts based on the parameter requirements input in the self-learning correction file, and recognizes that the part is composed of a bottom structural part, a middle cantilever structural part, two upper structural parts and a support. The bottom structural part, the middle cantilever structural part and the two upper structural parts are divided into areas according to multiple layers and printing paths.

[0096] like Figure 5 As shown, the bottom structure includes a base layer, a transition layer, and an intermediate layer. The central cantilever structure and the two upper structures each include a transition layer, a surface layer, and an intermediate layer. The base layer is the bonding layer between the bottom and the baseplate, the transition layer is the bonding layer between adjacent features and different components, the intermediate layer is the main body of the component, and the surface layer is the layer without bonding between components.

[0097] like Figure 6 As shown, the base layer, transition layer and middle layer are divided into contour area, good heat dissipation area and poor heat dissipation area. It should be noted that the printing path area divisions between different parts are different, and the proportions of each area are different.

[0098] The middle cantilever structural part has a cantilever structure, and the bottom of the cantilever beam has support. The system analyzes the original support structure of the part and determines that the area of ​​the original support structure cannot meet the structural requirements. The part is supplemented with support through the system's intelligent support module.

[0099] After analyzing and dividing the area, the adaptive printing mode slices the part and plans the path, and generates different printing parameters according to different layers and areas. Take the parameters of the areas with good heat dissipation in different layers as an example:

[0100] The parameters of the middle layer's good heat dissipation area are: laser power 160W, scanning speed 900mm / s, scanning spacing 0.08mm; the parameters of the bottom layer's good heat dissipation area are: laser power 180W, scanning speed 850mm / s, scanning spacing 0.09mm; the parameters of the surface layer's poor heat dissipation area are: laser power 150W, scanning speed 875mm / s, scanning spacing 0.08mm.

[0101] Step 3: Based on the printing task generated in step 2, the intelligent printing module controls the printer to print in a single layer. The intelligent analysis module simultaneously performs real-time data collection, data analysis, and printing effect evaluation on the single-layer printing. After the single-layer printing quality is judged to be qualified, the next layer is printed. The single-layer printing process is repeated until the printing is completed, thereby realizing intelligent printing.

[0102] like Figure 7As shown, no powder spreading defects or defects were found in the powder spreading analysis, that is, there were no Class I defects in the powder spreading stage. According to the molten pool analysis, the molten pool temperature had slight fluctuations, and the average deviation from the reference value was 6.1%, which was scored 7 points; the molten pool length and width deviation was 4.7%, which was scored 8 points. According to the spatter analysis, the spatter generation rate was 20 / ms, which was scored 8 points; the number of spatters falling on the surface was 7, which was scored 7 points. According to the forming surface analysis, the outer contour dimension deviation was 3%, which was scored 9 points; the maximum microcrack length was 0.015mm, which was scored 6 points; the maximum spheroidization and protrusion size was 0.01, which was scored 8 points, and the number was 5, which was scored 8 points; the unmelted powder accounted for 0.05% of the area, which was scored 9 points.

[0103] After all the scoring is completed, the comprehensive score is calculated to be 8.6 points. The intelligent printing module determines to enter the next layer of printing. After the printing quality of each layer is judged to be qualified, the next layer is printed until the overall printing is completed.

[0104] Step 4: During the overall printing process in step 3, various data during the printing process are recorded in the database. Combined with past printing records, the default printing parameters are adjusted to achieve self-learning of the intelligent analysis module. After the overall printing is completed, the overall printing quality report is output.

[0105] The results of this print were compared with the data in the database, and a curve was generated based on past print records, which was then used for compensation. The analysis revealed significant variations in the melt pool temperature and length and width, excessive spatter, long surface microcracks, and a low level of unmelted powder. This indicated that the input laser power was too high. Based on past print results, the default print parameters were adjusted: the laser power was lowered from 160W to 157W, and the scanning speed was lowered from 900mm / s to 890mm / s.

[0106] After the entire print was completed, a report was generated. The print parameters for this part were: laser power 160W, scan speed 900mm / s, and scan pitch 0.08mm. The estimated print density was 99.82%. The report indicated a microcrack defect of 0.015mm in length was detected in the i-th layer. The defect was located at (x, y, z) coordinates on the part. The printer had laser power offset, which was corrected through maintenance.

[0107] The above is only an embodiment of the present invention, and common sense such as the specific structure and characteristics of the scheme are not described in detail here. For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic characteristics of the present invention. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the appended claims rather than the above description, and it is intended that all changes that fall within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any figure mark in the claims should not be regarded as limiting the claim involved.

Claims

1. A method for monitoring and analyzing the quality of laser selective melting, characterized in that: The laser selective melting forming quality monitoring and analysis method comprises: Step 1: Start the laser selective melting equipment, initialize the equipment settings, restore the process parameters to the default values, load the self-learning correction file, and correct the default process parameters; Step 2: After the process parameters of step 1 are corrected, the 3D model file is input into the computer control system of the equipment. According to the printing mode type and printing requirements, the adaptive printing mode or the manual input printing mode is selected to obtain the model parameters. After rationality verification and compensation correction, the printing task is generated. Step 3: Based on the print task generated in step 2, the intelligent printing module controls the printer to print a single layer. The intelligent analysis module simultaneously performs real-time data collection, data analysis, and printing effect evaluation on the single layer printing. After the single layer printing quality is evaluated as qualified, the next layer is printed. The single layer printing process is repeated until the printing is completed. The defect types recorded by the intelligent analysis module include Class I defects, Class II defects, and Class III defects; Class I defects require machine downtime to resolve, significantly impacting the build quality and preventing further printing. These defects include interlayer fractures, macro cracks, severe local warping, and related defects. Class II defects are defects that have a moderate impact on the mechanical properties, density, and surface quality of the formed parts, including pores, lack of fusion, microcracks, protrusions, and related defects; Class III defects are defects that have a slight impact on the mechanical properties, density, and surface quality of the formed parts, including surface powder adhesion, spatter, and related defects; The step 3 specifically includes: Step 3.1: Single-layer printing begins. The intelligent printing module controls the equipment to spread powder. The intelligent analysis module collects data for single-layer printing, capturing real-time images of the melt pool to obtain melt pool size, melt pool temperature field, and spatter information. Images of the formed surface are captured to obtain the molded surface morphology, molded surface temperature field, molded dimensions, and related information. Finally, images of the powder-spreading surface are captured. Step 3.2: The intelligent analysis module in the computer control system performs real-time analysis of the powder laying quality, melt pool, spatter, temperature field data, and molding surface of the single-layer printing; The analysis by the intelligent analysis module in step 3.2 specifically includes: Step 3.2.1: First, analyze the powder spreading quality by comparing images before and after spreading. Calculate the percentage of powder coverage area through visual monitoring, spreading force, acceleration, and vibration monitoring. If the spreading is unsatisfactory, re-spread the powder. Step 3.2.2: After the powder coating is tested and qualified in step 3.2.1, the intelligent analysis module analyzes and determines whether the environmental parameters meet the printing conditions by monitoring and analyzing the environmental parameters. If it is judged to be unqualified, it waits for the conditions to be met; Step 3.2.3: After the environmental parameters in step 3.2.2 meet the printing conditions, the printer begins laser scanning and monitors the printing power, forming vision, and forming temperature field in real time. If a Class I defect is detected during the printing process, printing is terminated. If the printing process is monitored normally, the printer continues printing until the current layer is printed. Step 3.3: After the single-layer printing is completed, the laser scanning stops, and the intelligent analysis module evaluates the single-layer printing effect. The printing quality is scored on a 10-point scale based on the number of Class II defects and Class III defects found. The print quality scoring method in step 3.3 specifically includes: If 10 points > score ≥ 8 points, the current layer printing ends and the next layer printing begins; If 8 points > score ≥ 4 points, the system will handle it automatically; If 4 points > score ≥ 2 points, printing will be stopped and an alarm will be issued, prompting manual intervention to modify the printing parameters. The process parameters will be manually modified according to the printing quality and the modified parameters will be displayed; If the score is less than 2 points, printing will be terminated and an alarm will be issued, indicating that a serious defect has occurred and manual processing is required; When the problem defects of 8 points > score ≥ 4 points and 2 points > score ≥ 4 points are processed, the intelligent analysis module re-scores the quality of the current layer, and if the score is ≥ 8, it will proceed to the next layer printing; Step 3.4: Repeat steps 3.1 to 3.3, and print the next layer after each layer is judged to be qualified, until the entire printing is completed; Step 4: During the overall printing process in step 3, various data during the printing process are recorded in the database, and the default printing parameters are adjusted in combination with past printing records to achieve self-learning of the intelligent analysis module. After the overall printing is completed, an overall printing quality report is output.

2. The method for monitoring and analyzing the quality of selective laser melting according to claim 1, characterized in that: Generating a print task in step 2 specifically includes: Step 2.1: Select the adaptive printing mode to obtain the basic parameters of the 3D model file, perform intelligent analysis of the model based on the basic parameters, and generate the printing parameters of the adaptive printing mode; select the manual input printing mode to obtain the printing parameters of the 3D model file, and implement default value completion for the printing parameters of the manual input printing mode; Step 2.2: The intelligent analysis module performs a rationality check based on the printing parameters generated by the adaptive printing mode in step 2.1 or the printing parameters generated by the manual input printing mode, and performs compensation correction based on the relevant process parameters set in step 1. After the compensation correction is completed, printing is ready.

3. The method for monitoring and analyzing the quality of selective laser melting according to claim 2, characterized in that: The basic parameters in the adaptive printing mode of step 2.1 include laser power, scanning speed, scanning spacing, layer thickness, substrate temperature and related parameters; The printing parameters in the manual input printing mode include basic parameters, printing angle, layer rotation angle, volume compensation coefficient and printing layer depth coefficient.

4. The method for monitoring and analyzing the quality of selective laser melting according to claim 2, wherein: The intelligent analysis of the model in step 2.1 includes model feature identification and classification, model risk assessment and intelligent support; Feature recognition classification includes support and solid, solid includes thin wall, non-thin wall, outer surface, transition layer and inner layer features; Model risk assessment identifies locations where problems may occur during the printing process and issues warnings; Smart support adds support to the original support or risk location to strengthen the structure.

5. The method for monitoring and analyzing the quality of selective laser melting according to claim 2, wherein: The rationality check of the printing parameters in step 2.2 is based on the intelligent analysis module reading the 3D model file, automatically analyzing the model features, analyzing the process parameters matching different feature parts of the model, and autonomously selecting the matching process parameters from the database according to the material type of the model for printing; If there are no matching process parameters in the database, the laser selective melting molding equipment will prompt manual intervention, manually input the process parameters used for the relevant features, and record the printing results and related data, and supplement them into the database; The intelligent analysis module obtains the printing parameters of the 3D model by reading the 3D model file output in a layer structure mode by the slicing software in the computer control system of the device, compensates and corrects the relevant process parameters set in step 1, controls the completion of printing, records the printing results and related data, and enters them into the database.

6. The method for monitoring and analyzing the quality of selective laser melting according to claim 1, characterized in that: The self-learning module in step 4 records the printing process parameters according to the molding characteristics, judges the process parameters according to the molding results of this characteristic, and compares the relevant parameters already in the database. If the judgment result is better, the relevant data is updated, and the modification log is recorded, the printing results are evaluated, and self-learning correction files are generated regularly to correct the deviation caused by the long-term use of the printer.

Images