A method and system for surface treatment of injection mold for polymer materials

Abstract

This invention relates to the field of surface treatment technology, specifically a method and system for surface treatment of injection molds for polymer materials. The method includes: constructing a precise multi-dimensional digital model of the mold using a multimodal scanner; intelligently generating laser command sequences, preheating temperatures, and predicted molten pool information using an AI analysis model and the multi-dimensional digital model; performing a trial remelting operation on the mold based on the laser command sequence; adjusting the laser command sequence based on the results of the trial remelting to form a closed-loop structure; scanning again after the first remelting operation to construct a second multi-dimensional digital model; remelting again based on the second multi-dimensional digital model to further repair defects and refine the surface; and finally, annealing to eliminate mold stress and obtain the finished mold. This invention improves the intelligence level, diagnostic accuracy, and finished product quality of surface treatment.

Description

Technical Field

[0001] This invention relates to the field of surface treatment technology, and in particular to a method and system for surface treatment of injection molds for polymer materials. Background Technology

[0002] Injection molds are core equipment in the molding and processing of polymer materials. The surface finish, hardness, wear resistance, and corrosion resistance of injection molds directly determine the precision, appearance, quality, and service life of the final polymer products. Therefore, high-quality, high-precision surface treatment and repair of injection molds are of paramount importance for enhancing product competitiveness, reducing production costs, and extending the service life of expensive molds.

[0003] Traditional surface treatment mainly relies on manual experience and the expertise and subjective judgment of operators. However, this method suffers from low efficiency, incomplete diagnosis, and low product quality. Therefore, the level of intelligence, diagnostic accuracy, and product quality of this method need to be improved. Summary of the Invention

[0004] This invention provides a surface treatment method and system for injection molds of polymer materials, the main purpose of which is to improve the intelligence level, diagnostic accuracy and finished product quality of surface treatment.

[0005] To achieve the above objectives, the present invention provides a surface treatment method for injection molds of polymer materials, comprising:

[0006] Acquire information on injection molds, cleaning equipment, multimodal scanners, mold materials, polymer materials, AI analysis models, laser instruments, and annealing equipment;

[0007] The injection mold is pre-cleaned using a cleaning device to obtain a clean mold;

[0008] A multimodal scanner was used to scan the cleaning mold to obtain a multidimensional digital model;

[0009] Preheating temperature, laser command sequence, and predicted molten pool information are obtained based on mold material information, polymer material information, multi-dimensional digital model, and AI analysis model.

[0010] The injection mold is preheated based on the preheating temperature to obtain a preheated mold.

[0011] Based on the laser instrument and laser command sequence, a trial remelting operation is performed on the preheated mold to obtain a trial remelting pool. A pre-constructed pool monitor is used to monitor the trial remelting pool to obtain pool information.

[0012] Based on the molten pool information and the predicted molten pool information, the molten pool gap is obtained. If the molten pool gap is not within the preset allowable molten pool gap range, the laser command sequence is adjusted based on the molten pool gap and the AI ​​analysis model to obtain a new laser command sequence. The new laser command sequence is used as the laser command sequence, and the step of performing a trial remelting operation on the preheated mold is returned. Otherwise, the preheated mold is remelted to obtain the first remelted mold.

[0013] A multimodal scanner is used to scan the first remelting mold to obtain a second multidimensional digital model. Based on the second multidimensional digital model and the AI ​​analysis model, a second laser command sequence is obtained. Based on the laser instrument and the second laser command sequence, the first remelting mold is remelted to obtain the second remelting mold.

[0014] The stress distribution model of the second remelting mold was obtained using a pre-constructed non-destructive stress testing instrument;

[0015] Based on the second multidimensional digital model, mold material information, stress distribution model and AI analysis model, stress-relief annealing parameters are obtained. Based on the annealing equipment and stress-relief annealing parameters, stress release operation is performed on the second remelting mold to obtain the finished mold.

[0016] Optionally, the pre-cleaning operation of the injection mold using a cleaning device to obtain a clean mold includes:

[0017] Based on the mold material information, a cleaning agent is obtained. Based on the cleaning agent and a pre-constructed ultrasonic cleaner, an ultrasonic cleaning operation is performed on the injection mold to obtain the first clean mold.

[0018] Using a pre-built high-pressure flushing device, the first cleaning mold is subjected to high-pressure flushing to obtain the second cleaning mold;

[0019] The second cleaning mold is dried using a pre-built dryer to obtain a clean mold.

[0020] Optionally, the step of scanning the cleaning mold using a multimodal scanner to obtain a multidimensional digital model includes:

[0021] The surface of the cleaning mold is scanned using a pre-built laser scanning unit in a multimodal scanner to obtain a mold surface model.

[0022] The mold surface model is divided to obtain a subsurface detection region set, which includes multiple subsurface detection regions.

[0023] Ultrasonic pulse signals are generated using a pre-built ultrasonic scanning unit in a multimodal scanner. The ultrasonic scanning unit includes an ultrasonic transducer and a subsurface detection probe.

[0024] Obtain standard defect samples, and based on the standard defect samples, obtain an amplitude-defect volume curve atlas, wherein the amplitude-defect volume curve atlas includes multiple amplitude-defect volume curves;

[0025] For each subsurface detection region in the subsurface detection region set, perform the following operations:

[0026] Using ultrasonic pulse signals, an ultrasonic transducer, and a subsurface detection probe, an ultrasonic scanning operation is performed on the subsurface detection area to obtain an echo waveform.

[0027] Obtain the thickness of the subsurface detection area, and based on the thickness of the subsurface detection area and the preset ultrasonic reference velocity, obtain the echo reference time;

[0028] Based on the echo waveform diagram, echo reference time, and preset defect judgment conditions, the defect judgment result is obtained;

[0029] If the defect judgment result is that there is no defect as preset, then the subsurface detection area is confirmed as the preset defect-free area.

[0030] If the defect judgment result is that a defect exists as preset, the subsurface detection area is confirmed as the preset defect area, and the defect transit time is obtained according to the echo waveform. Based on the defect transit time and the ultrasonic reference velocity, the defect depth is obtained.

[0031] Defect volume is obtained based on the defect depth and amplitude-defect volume curve atlas;

[0032] By summarizing the defect depth and defect volume, information about a single defect can be obtained.

[0033] Summarize the defect-free areas to obtain a defect-free area information set;

[0034] By summarizing the information of individual defects, a defect area information set is obtained. Based on the defect-free area information set and the defect area information set, a mold subsurface model is constructed.

[0035] Based on the mold surface model and the mold sub-surface model, a fusion operation is performed in a pre-constructed spatial coordinate system to obtain a multi-dimensional digital model.

[0036] Optionally, the acquisition of preheating temperature, laser command sequence, and predicted molten pool information based on mold material information, polymer material information, multidimensional digital model, and AI analysis model includes:

[0037] Obtaining target performance of molds based on polymer material information;

[0038] The preheating temperature is obtained based on mold material information and AI analysis models.

[0039] Based on the target performance of the mold, the information set of the defect area, the mold material information, the preheating temperature, and the AI ​​analysis model, the laser command sequence for defect processing is obtained;

[0040] Based on the target performance of the mold, the information set of defect-free areas, the mold material information, the preheating temperature, and the AI ​​analysis model, the laser command sequence for roughness treatment is obtained;

[0041] By summarizing the laser command sequences for defect processing and roughness processing, a laser command sequence is obtained.

[0042] Based on the laser command sequence, mold material information, preheating temperature, and AI analysis model, the predicted molten pool information is obtained.

[0043] Optionally, the process of performing a trial remelting operation on the preheated mold based on a laser instrument and laser command sequence to obtain a trial remelting pool, and then using a pre-constructed pool monitor to monitor the trial remelting pool and obtain pool information, including:

[0044] Based on the preset test remelting area, defect test remelting area and roughness test remelting area are selected from the defect area information set and the non-defect area information set, respectively.

[0045] Based on the laser instrument and laser command sequence, a trial remelting operation is performed on the defect trial remelting area and the roughness trial remelting area to obtain the trial remelting pool.

[0046] The molten pool is monitored using a molten pool monitor to obtain molten pool information, including molten pool temperature and molten pool width.

[0047] Optionally, the step of obtaining the molten pool gap based on the molten pool information and the predicted molten pool information, and if the molten pool gap is not within the preset allowable molten pool gap range, adjusting the laser command sequence based on the molten pool gap and the AI ​​analysis model to obtain a new laser command sequence, includes:

[0048] The difference in molten pool temperature is obtained by comparing the molten pool temperature with the preset predicted molten pool temperature in the predicted molten pool information.

[0049] The difference in molten pool width is obtained by comparing the molten pool width with the preset predicted molten pool width in the predicted molten pool information.

[0050] The molten pool difference is obtained by summing the differences in molten pool temperature and molten pool width.

[0051] If the temperature difference of the molten pool is not within the preset allowable temperature difference range of the molten pool, or the width difference of the molten pool is not within the preset allowable width difference range of the molten pool, then it is confirmed that the molten pool difference is not within the allowable molten pool difference range.

[0052] Using an AI analysis model, the molten pool gap is analyzed in reverse to obtain laser adjustment commands;

[0053] By using laser adjustment commands, the laser command sequence is adjusted to obtain a new laser command sequence.

[0054] Optionally, obtaining the stress distribution model of the second remelting mold using a pre-constructed non-destructive stress testing instrument includes:

[0055] The second multidimensional digital model is subjected to stress detection and division operation to obtain a stress detection region set, which includes multiple stress detection regions.

[0056] Using a non-destructive stress testing instrument, stress testing is performed on each stress testing area to obtain a stress information set, in which the stress testing area corresponds one-to-one with the stress information.

[0057] A stress distribution model is constructed based on the stress information set and the second multidimensional digital model.

[0058] Optionally, the step of using a non-destructive stress testing instrument to perform stress testing on each stress testing area to obtain a stress information set includes:

[0059] Perform the following operations for each stress testing area:

[0060] Using a pre-built stress detection probe in a non-destructive stress testing instrument, a longitudinal wave emission operation is performed into the stress detection area, and the time of the longitudinal wave emission operation is recorded to obtain the emission time.

[0061] The reflected longitudinal wave was acquired using a stress detection probe, and the acquisition time was recorded.

[0062] The thickness of the stress detection area is obtained, and the longitudinal wave velocity is obtained based on the emission time, acquisition time, and the thickness of the stress detection area.

[0063] Stress information is obtained based on the longitudinal wave velocity, the pre-constructed acoustoelastic coefficient, and the pre-constructed longitudinal wave reference velocity;

[0064] By summarizing the stress information, a stress information set is obtained.

[0065] Optionally, the step of performing a stress-relieving operation on the second remelting mold based on the annealing equipment and stress-relief annealing parameters to obtain the finished mold includes:

[0066] Extract the pre-constructed heating rate and target temperature from the stress-relief annealing parameters. Based on the annealing equipment, heating rate, and target temperature, perform a heating operation on the second remelting mold to obtain the first-stage mold.

[0067] Extract the pre-constructed holding time from the stress-relief annealing parameters, and perform a holding operation on the first-stage mold based on the annealing equipment and holding time to obtain the second-stage mold;

[0068] Extract the pre-constructed cooling rate and second target temperature from the stress-relief annealing parameters. Based on the annealing equipment, cooling rate, and second target temperature, perform a cooling operation on the second-stage mold to obtain the finished mold.

[0069] To achieve the above objectives, the present invention also provides a surface treatment system for injection molds of polymer materials, comprising:

[0070] The basics and modeling module is used to acquire information on injection molds, cleaning equipment, multimodal scanners, mold materials, polymer materials, AI analysis models, laser instruments, and annealing equipment. The cleaning equipment is used to pre-clean the injection mold to obtain a clean mold, and the multimodal scanner is used to scan the clean mold to obtain a multidimensional digital model.

[0071] The intelligent planning and monitoring module is used to obtain preheating temperature, laser command sequence and predicted melt pool information based on mold material information, polymer material information, multi-dimensional digital model and AI analysis model. Based on the preheating temperature, the injection mold is preheated to obtain a preheated mold. Based on the laser instrument and laser command sequence, the preheated mold is remelted to obtain a remelted melt pool. The remelted melt pool is monitored using a pre-built melt pool monitor to obtain melt pool information.

[0072] The remelting operation module is used to obtain the molten pool gap based on the molten pool information and the predicted molten pool information. If the molten pool gap is not within the preset allowable molten pool gap range, the laser command sequence is adjusted based on the molten pool gap and the AI ​​analysis model to obtain a new laser command sequence. The new laser command sequence is used as the laser command sequence, and the step of performing a trial remelting operation on the preheated mold is returned. Otherwise, the preheated mold is remelted to obtain a first remelting mold. The first remelting mold is scanned using a multimodal scanner to obtain a second multidimensional digital model. Based on the second multidimensional digital model and the AI ​​analysis model, a second laser command sequence is obtained. Based on the laser instrument and the second laser command sequence, the first remelting mold is remelted to obtain a second remelting mold.

[0073] The stress treatment module is used to obtain the stress distribution model of the second remelting mold using a pre-built non-destructive stress detector. Based on the second multi-dimensional digital model, mold material information, stress distribution model and AI analysis model, stress relief annealing parameters are obtained. Based on the annealing equipment and stress relief annealing parameters, stress release operation is performed on the second remelting mold to obtain the finished mold.

[0074] To address the above problems, the present invention also provides an electronic device, the electronic device comprising:

[0075] Memory, storing at least one instruction;

[0076] The processor executes the instructions stored in the memory to implement the surface treatment method for injection molds of polymer materials described above.

[0077] To address the aforementioned problems, the present invention also provides a computer-readable storage medium storing at least one instruction, which is executed by a processor in an electronic device to implement the above-described surface treatment method for injection molds of polymer materials.

[0078] To address the problems described in the background section, this invention provides an injection mold, a cleaning device, a multimodal scanner, mold material information, polymer material information, an AI analysis model, a laser instrument, and annealing equipment. This invention provides all the necessary physical equipment and data, offering a complete foundation for subsequent automated and intelligent processing, ensuring the systematic nature and integrity of the process. The cleaning device pre-cleans the injection mold, resulting in a clean mold. This invention removes oil, mold release agent residue, and impurities from the mold surface, preventing contaminants from interfering with subsequent scanning and laser processing. The multimodal scanner scans the clean mold to obtain a multidimensional digital model, creating a precise model that includes both surface and subsurface information. The digital model provides a comprehensive and quantitative data foundation for AI analysis, improving the accuracy of diagnosis. Based on mold material information, polymer material information, multi-dimensional digital models, and AI analysis models, preheating temperature, laser command sequences, and predicted molten pool information are obtained. This invention can utilize artificial intelligence technology to generate a highly customized and theoretically optimal initial processing scheme, significantly improving the intelligence level of the process. Preheating the injection mold based on the preheating temperature yields a preheated mold. This invention effectively reduces thermal shock and prevents new cracks by preheating the mold, contributing to a stable molten pool. Based on the laser instrument and laser command sequence, a trial remelting operation is performed on the preheated mold to obtain a trial remelted molten pool. The constructed molten pool monitor monitors the molten pool during the trial remelting process, obtaining molten pool information. This invention demonstrates the ability to validate AI-generated schemes on a small scale, acquiring real-world processing conditions with minimal cost and risk, providing a basis for subsequent closed-loop adjustments. Based on the molten pool information and predicted molten pool information, the molten pool gap is obtained. If the gap is outside the preset allowable range, the laser command sequence is adjusted based on the gap and the AI ​​analysis model to obtain a new laser command sequence. Using this new sequence, the process returns to the step of performing a trial remelting operation on the preheated mold. Otherwise, the preheated mold is remelted to obtain the first remelted mold. This invention thus constructs a feedback and correction closed-loop structure. This invention eliminates the discrepancy between theoretical calculations and actual processing, ensuring that the final laser commands used are the optimal solutions proven in practice. This improves the success rate and reliability of formal processing. A multimodal scanner is used to scan the first remelting mold to obtain a second multidimensional digital model. Based on the second multidimensional digital model and an AI analysis model, a second laser command sequence is obtained. Using the laser instrument and the second laser command sequence, the first remelting mold is remelted to obtain the second remelting mold. Thus, this invention refines the surface through secondary scanning and secondary remelting, further improving surface smoothness, uniformity, and other properties, thereby enhancing the surface quality of the mold. A pre-constructed non-destructive stress detector is used to obtain the stress distribution model of the second remelting mold.It is evident that this invention can detect residual stress generated inside the mold after laser processing, providing accurate information for subsequent stress relief. Based on a second multi-dimensional digital model, mold material information, stress distribution model, and AI analysis model, stress-relief annealing parameters are obtained. Using the annealing equipment and these parameters, a stress-relief annealing operation is performed on the second remelting mold to obtain the finished mold. Thus, this invention eliminates stress in the mold through annealing, improving the quality of the finished mold. Therefore, this invention can improve the intelligence level, diagnostic accuracy, and finished product quality of surface treatment. Attached Figure Description

[0079] Figure 1 This is a schematic flowchart of a surface treatment method for injection molds of polymer materials according to an embodiment of the present invention;

[0080] Figure 2 This is a functional block diagram of a surface treatment system for injection molds of polymer materials provided in an embodiment of the present invention;

[0081] Figure 3 This is a schematic diagram of the structure of an electronic device for implementing the surface treatment method for injection molds of polymer materials, according to an embodiment of the present invention.

[0082] Explanation of reference numerals in the attached figures:

[0083] 10. Electronic device; 11. Processor; 12. Memory; 13. Bus.

[0084] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0085] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0086] This application provides a method for surface treatment of injection molds for polymer materials. The execution entity of this method includes, but is not limited to, at least one of the following electronic devices that can be assigned to execute the method provided in this application: a server, a terminal, etc. In other words, the method for surface treatment of injection molds for polymer materials can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster.

[0087] Reference Figure 1The diagram shown is a schematic flow chart of a surface treatment method for injection molds used for polymer materials according to an embodiment of the present invention. In this embodiment, the surface treatment method for injection molds used for polymer materials includes:

[0088] S1. Obtain information on injection molds, cleaning equipment, multimodal scanners, mold materials, polymer materials, AI analysis models, laser instruments, and annealing equipment.

[0089] Understandably, the injection mold refers to the mold required in injection molding production to impart a specific shape and size to molten plastic. The cleaning device refers to equipment used to remove oil, residue, and other contaminants from the mold surface, including ultrasonic cleaners and high-pressure flushing devices. The multimodal scanner refers to a precision instrument integrating multiple scanning technologies to acquire comprehensive three-dimensional data of the object's surface and interior, including laser scanning units and ultrasonic scanning units. The mold material information refers to the specific composition, physical properties, and thermodynamic characteristics of the material used in the injection mold. The polymer material information refers to the type, melting point, flowability, and other characteristics of the plastic raw material used in injection molding production. The AI ​​analysis model refers to a computational model based on artificial intelligence algorithms, which can be divided into a remelting analysis unit and a stress analysis unit. The remelting analysis unit can be used to obtain various parameters of the remelting operation, and the stress analysis unit can be used to obtain various parameters of the stress release operation. The laser device refers to equipment that uses a high-energy laser beam to locally heat and melt the material surface. The annealing equipment refers to equipment capable of precisely heating, holding, and slowly cooling metal workpieces to eliminate stress in the metal workpieces.

[0090] S2. Use a cleaning device to pre-clean the injection mold to obtain a clean mold.

[0091] As is clear, the pre-cleaning operation refers to the preparatory steps taken before performing core processes such as scanning and laser repair. These steps involve removing oil and impurities from the mold surface through methods such as ultrasonic cleaning, high-pressure rinsing, and drying. The purpose is to prevent contaminants on the injection mold surface from affecting scanning accuracy and remelting results. The cleaned mold refers to the mold with a clean surface after the pre-cleaning operation.

[0092] Furthermore, the pre-cleaning operation of the injection mold using a cleaning device to obtain a clean mold includes:

[0093] Based on the mold material information, a cleaning agent is obtained. Based on the cleaning agent and a pre-constructed ultrasonic cleaner, an ultrasonic cleaning operation is performed on the injection mold to obtain the first clean mold.

[0094] Using a pre-built high-pressure flushing device, the first cleaning mold is subjected to high-pressure flushing to obtain the second cleaning mold;

[0095] The second cleaning mold is dried using a pre-built dryer to obtain a clean mold.

[0096] Explained, the cleaning agent refers to a chemical solvent selected based on the mold material information, which will not damage the injection mold and can dissolve contaminants on the injection mold surface. The ultrasonic cleaner refers to a device in the cleaning system that utilizes the cavitation effect generated by ultrasound in a liquid for precision cleaning, aiming to efficiently remove surface contaminants without damaging the injection mold. The ultrasonic cleaning operation refers to the operation of cleaning the injection mold using an ultrasonic cleaner and a cleaning agent. The first cleaned mold refers to the injection mold that has undergone ultrasonic cleaning. The high-pressure flushing device refers to a device in the cleaning system that uses high-pressure water jets to clean the mold surface. The high-pressure flushing operation refers to the operation of cleaning the injection mold using a high-pressure flushing device, aiming to remove any residual cleaning agent from the injection mold surface. The second cleaned mold refers to the injection mold that has undergone high-pressure flushing. The drying device refers to a device in the cleaning system that uses high-pressure gas or other methods to dry the injection mold surface. The drying operation refers to the operation of drying the injection mold using a drying device.

[0097] S3. Use a multimodal scanner to scan the cleaning mold to obtain a multidimensional digital model.

[0098] It should be explained that the scanning operation refers to scanning the surface and subsurface of the injection mold to obtain the required information. The multidimensional digital model refers to a high-precision model that includes the three-dimensional topography and subsurface structure information of the mold surface.

[0099] Furthermore, the step of using a multimodal scanner to scan the cleaning mold to obtain a multidimensional digital model includes:

[0100] The surface of the cleaning mold is scanned using a pre-built laser scanning unit in a multimodal scanner to obtain a mold surface model.

[0101] The mold surface model is divided to obtain a subsurface detection region set, which includes multiple subsurface detection regions.

[0102] Ultrasonic pulse signals are generated using a pre-built ultrasonic scanning unit in a multimodal scanner. The ultrasonic scanning unit includes an ultrasonic transducer and a subsurface detection probe.

[0103] Obtain standard defect samples, and based on the standard defect samples, obtain an amplitude-defect volume curve atlas, wherein the amplitude-defect volume curve atlas includes multiple amplitude-defect volume curves;

[0104] For each subsurface detection region in the subsurface detection region set, perform the following operations:

[0105] Using ultrasonic pulse signals, an ultrasonic transducer, and a subsurface detection probe, an ultrasonic scanning operation is performed on the subsurface detection area to obtain an echo waveform.

[0106] Obtain the thickness of the subsurface detection area, and based on the thickness of the subsurface detection area and the preset ultrasonic reference velocity, obtain the echo reference time;

[0107] Based on the echo waveform diagram, echo reference time, and preset defect judgment conditions, the defect judgment result is obtained;

[0108] If the defect judgment result is that there is no defect as preset, then the subsurface detection area is confirmed as the preset defect-free area.

[0109] If the defect judgment result is that a defect exists as preset, the subsurface detection area is confirmed as the preset defect area, and the defect transit time is obtained according to the echo waveform. Based on the defect transit time and the ultrasonic reference velocity, the defect depth is obtained.

[0110] Defect volume is obtained based on the defect depth and amplitude-defect volume curve atlas;

[0111] By summarizing the defect depth and defect volume, information about a single defect can be obtained.

[0112] Summarize the defect-free areas to obtain a defect-free area information set;

[0113] By summarizing the information of individual defects, a defect area information set is obtained. Based on the defect-free area information set and the defect area information set, a mold subsurface model is constructed.

[0114] Based on the mold surface model and the mold sub-surface model, a fusion operation is performed in a pre-constructed spatial coordinate system to obtain a multi-dimensional digital model.

[0115] Specifically, the laser scanning unit refers to a device in a multimodal scanner that uses a laser to scan the surface of an injection mold. The surface scanning operation refers to the operation of using the laser scanning unit to scan the surface of the injection mold and output a three-dimensional model. The mold surface model refers to a high-precision digital model containing the three-dimensional features of the injection mold surface. The partitioning operation refers to the operation of dividing the mold surface into multiple sub-regions (i.e., subsurface detection regions) based on the mold surface model, in order to scan the subsurface. The subsurface detection region set refers to the collection of multiple subsurface detection regions obtained from the partitioning operation. The subsurface detection region refers to the region obtained from the partitioning operation used for subsurface detection. The ultrasonic scanning unit refers to a device in a multimodal scanner that uses ultrasonic waves to detect the subsurface structure of the injection mold. The ultrasonic pulse signal refers to the electrical signal used to detect the ultrasonic waves on the subsurface of the injection mold. The ultrasonic transducer refers to a device that converts the electrical signal (ultrasonic pulse signal) into ultrasonic waves. The subsurface detection probe refers to a probe that directly contacts the injection mold and is used to emit and receive ultrasonic waves. The standard defect sample refers to a man-made standard block made of the same material as the injection mold, containing defects of different known depths and sizes, used to obtain the relationship between defect volume and echo amplitude under different depth conditions. The amplitude-defect volume curve set refers to a collection of curves showing the correspondence between echo amplitude and defect volume under different depth conditions. The amplitude-defect volume curve graph refers to a curve showing the correspondence between echo amplitude and defect volume at a specific depth. The ultrasonic scanning operation involves emitting a beam of ultrasonic waves perpendicular to the subsurface detection area into the injection mold, and simultaneously recording the waveform over a subsequent period, which is the echo waveform graph. The subsurface detection area thickness refers to the thickness of the subsurface detection area being detected within the injection mold.

[0116] Furthermore, the ultrasonic reference velocity is the standard speed at which ultrasonic waves propagate in the mold material. The echo reference time refers to the time required for ultrasonic waves to travel from emission to reception of the bottom echo in a defect-free area, calculated based on the thickness of the subsurface detection area and the ultrasonic reference velocity. The defect judgment condition refers to the condition for determining the existence of a defect based on the received echo time and the echo reference time shown in the echo waveform diagram. If the difference between the received echo time and the echo reference time is greater than a reasonable error ratio, it indicates the presence of a defect.

[0117] For example, a reasonable error ratio is 2%, which means that if the ratio of the difference between the received echo time and the echo reference time to the echo reference time is greater than 2%, then there is a defect.

[0118] It is understood that the defect judgment result refers to the conclusion given based on the echo waveform, echo reference time, and defect judgment conditions regarding whether a defect exists in the subsurface detection area. "No defect" means the judgment result that the subsurface detection area is considered to be free of defects. "Defect-free area" refers to a subsurface detection area that is judged to be without defects. "Defect present" means the judgment result that the subsurface detection area is considered to have defects. "Defective area" refers to a subsurface detection area that is judged to have defects.

[0119] Furthermore, the defect transit time refers to the total time it takes for the ultrasonic wave emitted from the mold surface to reach the internal defect point and reflect back to the surface. It is obtained by extracting the time corresponding to the peak value of the first echo in the echo waveform. The defect depth refers to the depth of the defect from the mold surface calculated based on the defect transit time and the ultrasonic reference velocity. Its calculation method is as follows:

[0120]

[0121] in, Indicates the depth of the defect. Indicates the ultrasonic reference velocity. Indicates the time it takes for a defect to pass through.

[0122] Understandably, the defect volume refers to the size of the defect obtained based on the amplitude of the echo signal and referring to the amplitude-defect volume curve. The individual defect information refers to the set of defect depth and defect volume for a single defect. The defect-free region information set refers to the set of information for all subsurface detection regions considered defect-free. The defect region information set refers to the set of information for all individual defects. The mold subsurface model refers to a high-precision 3D model that records the defect-free and defect-free regions of the injection mold subsurface. The spatial coordinate system refers to a three-dimensional Cartesian coordinate system. The fusion operation refers to the operation of fusing the mold surface model and the mold subsurface model in 3D space based on precise coordinate positions. Its purpose is to reflect the information of the mold surface and the mold subsurface in the same 3D model for subsequent processing.

[0123] S4. Based on mold material information, polymer material information, multi-dimensional digital model and AI analysis model, obtain preheating temperature, laser command sequence and predicted molten pool information.

[0124] Understandably, the laser command sequence refers to a series of command codes that control the laser's movement path, power, and speed parameters. The preheating temperature refers to the specific temperature to which the entire mold needs to be heated before laser treatment. This is to prevent excessive temperature differences between the laser's point of action and surrounding areas, reducing the risk of cracking due to excessive temperature differences. The predicted molten pool information refers to the temperature and width of the molten area that will form on the mold surface during laser treatment, predicted by the AI ​​analysis model based on various parameters.

[0125] Furthermore, the acquisition of preheating temperature, laser command sequence, and predicted molten pool information based on mold material information, polymer material information, multidimensional digital model, and AI analysis model includes:

[0126] Obtaining target performance of molds based on polymer material information;

[0127] Based on mold material information and AI analysis models, the preheating temperature is obtained;

[0128] Based on the target performance of the mold, the information set of the defect area, the mold material information, the preheating temperature, and the AI ​​analysis model, the laser command sequence for defect processing is obtained;

[0129] Based on the target performance of the mold, the information set of defect-free areas, the mold material information, the preheating temperature, and the AI ​​analysis model, the laser command sequence for roughness treatment is obtained;

[0130] By summarizing the laser command sequences for defect processing and roughness processing, a laser command sequence is obtained.

[0131] Based on the laser command sequence, mold material information, preheating temperature, and AI analysis model, the predicted molten pool information is obtained.

[0132] Explained, obtaining the preheating temperature based on mold material information and an AI analysis model means using the AI ​​analysis model to determine a suitable preheating temperature based on the material of the injection mold. Typically, the selection of the preheating temperature requires comprehensive consideration of the material's carbon content, alloy element content, austenite formation temperature, and martensite formation temperature. Obtaining predicted molten pool information based on the laser command sequence, mold material information, preheating temperature, and AI analysis model means inputting the laser power, scanning speed, mold melting point, thermal conductivity, and preheating temperature into the AI ​​analysis model to calculate the molten pool temperature and width that will be reached during the remelting operation.

[0133] Understandably, the target performance of the mold refers to the surface finish, hardness, and other properties required for the mold based on the characteristics of the polymer material to be injection molded (e.g., high gloss). The defect handling laser command sequence refers to a series of laser control codes calculated by the AI ​​analysis model for each detected defect, used to precisely melt, fill, and eliminate these defects. The roughness handling laser command sequence refers to a series of laser control codes generated by the AI ​​analysis model for defect-free areas on the mold, aiming to uniformly adjust the surface micro-roughness through shallow remelting to meet the target performance of the mold.

[0134] S5. Preheat the injection mold based on the preheating temperature to obtain a preheated mold.

[0135] It should be explained that the preheating operation refers to heating the injection mold to a preheating temperature and maintaining that temperature for an extended period. The preheated mold refers to a mold that has completed the preheating operation and reached the specified temperature.

[0136] S6. Based on the laser instrument and laser command sequence, perform a trial remelting operation on the preheated mold to obtain a trial remelting pool. Use a pre-built pool monitor to monitor the trial remelting pool and obtain pool information.

[0137] It is clear that the trial remelting operation refers to a small-scale experimental remelting operation used to verify and calibrate laser parameters. The trial remelting pool refers to the actual molten area generated during the trial remelting operation. The pool monitor is a sensor used to monitor the state of the pool (pool temperature and pool width) during laser remelting, where the pool width refers to the width of the pool in the direction perpendicular to the laser path. The monitoring operation refers to the operation of monitoring the state of the pool using the pool monitor. The pool information refers to the state information about the pool collected by the pool monitor, including the pool temperature and width of the defective trial remelting area and the pool temperature and width of the roughness trial remelting area.

[0138] Furthermore, based on the laser instrument and laser command sequence, a trial remelting operation is performed on the preheated mold to obtain a trial remelted molten pool. A pre-constructed molten pool monitor is then used to monitor the trial remelted molten pool to obtain molten pool information, including:

[0139] Based on the preset test remelting area, defect test remelting area and roughness test remelting area are selected from the defect area information set and the non-defect area information set, respectively.

[0140] Based on the laser instrument and laser command sequence, a trial remelting operation is performed on the defect trial remelting area and the roughness trial remelting area to obtain the trial remelting pool.

[0141] The molten pool is monitored using a molten pool monitor to obtain molten pool information, including molten pool temperature and molten pool width.

[0142] Understandably, the test remelting area refers to the pre-defined area that needs to be remelted during the test remelting. The defect test remelting area refers to the area selected for test remelting in the area where defects exist. The roughness test remelting area refers to the area selected for test remelting in the area without defects. The molten pool temperature refers to the average temperature of the test remelted molten pool monitored by the molten pool monitor. The molten pool width refers to the average width of the test remelted molten pool monitored by the molten pool monitor.

[0143] S7. Based on the molten pool information and the predicted molten pool information, obtain the molten pool gap. If the molten pool gap is not within the preset allowable molten pool gap range, adjust the laser command sequence based on the molten pool gap and the AI ​​analysis model to obtain a new laser command sequence. Use the new laser command sequence as the laser command sequence and return to the step of performing a trial remelting operation on the preheated mold. Otherwise, perform a remelting operation on the preheated mold to obtain the first remelted mold.

[0144] It should be explained that the melt pool gap refers to the difference between the actual monitored melt pool information and the predicted melt pool information, expressed as a ratio, i.e., the ratio of the difference between the actual monitored melt pool information and the predicted melt pool information to the predicted melt pool information. The allowable melt pool gap range refers to a pre-set, acceptable error range between the actual and predicted melt pool parameters that does not affect mold performance. The new laser command sequence refers to the laser command sequence after command adjustment. The remelting operation refers to the operation of remelting the injection mold according to the laser command sequence and the laser instrument. The first remelted mold refers to the mold that has completed the first laser remelting treatment.

[0145] Furthermore, based on the molten pool information and predicted molten pool information, the molten pool gap is obtained. If the molten pool gap is not within the preset allowable molten pool gap range, the laser command sequence is adjusted based on the molten pool gap and the AI ​​analysis model to obtain a new laser command sequence, including:

[0146] The difference in molten pool temperature is obtained by comparing the molten pool temperature with the preset predicted molten pool temperature in the predicted molten pool information.

[0147] The difference in molten pool width is obtained by comparing the molten pool width with the preset predicted molten pool width in the predicted molten pool information.

[0148] The molten pool difference is obtained by summing the differences in molten pool temperature and molten pool width.

[0149] If the temperature difference of the molten pool is not within the preset allowable temperature difference range of the molten pool, or the width difference of the molten pool is not within the preset allowable width difference range of the molten pool, then it is confirmed that the molten pool difference is not within the allowable molten pool difference range.

[0150] Using an AI analysis model, the molten pool gap is analyzed in reverse to obtain laser adjustment commands;

[0151] By using laser adjustment commands, the laser command sequence is adjusted to obtain a new laser command sequence.

[0152] It is clear that the molten pool temperature difference refers to the difference between the actual monitored average molten pool temperature and the predicted molten pool temperature. The molten pool width difference refers to the difference between the actual monitored average molten pool width and the predicted molten pool width, where the actual monitored average molten pool width refers to the average width of the actual monitored molten pool in the direction perpendicular to the laser path. The allowable molten pool temperature difference range refers to a pre-set, acceptable error range between the actual and predicted molten pool temperatures that does not affect mold performance. For example, an allowable molten pool temperature difference range of 3% means that the ratio of the difference between the actual and predicted temperatures to the predicted temperature is greater than 3%, indicating that the molten pool temperature difference is too large, which may affect the surface performance of the mold or even lead to new defects, thus requiring adjustment of the laser command sequence. The allowable molten pool width difference range is similar to the allowable molten pool temperature difference range and will not be elaborated further here. The reverse analysis operation refers to the operation in which the AI ​​analysis model, based on the molten pool difference, reverse-calculates which parameters in the laser parameters need to be adjusted and calculates the specific amount of adjustment required. The laser adjustment command refers to the code instructions analyzed by the AI ​​analysis model used to adjust the parameters in the laser command sequence. The command adjustment operation refers to the operation of adjusting the laser command sequence using the laser adjustment command.

[0153] S8. Use a multimodal scanner to scan the first remelting mold to obtain a second multidimensional digital model. Based on the second multidimensional digital model and the AI ​​analysis model, obtain a second laser command sequence. Based on the laser instrument and the second laser command sequence, perform a remelting operation on the first remelting mold to obtain a second remelting mold.

[0154] It is clear that the second multidimensional digital model refers to the digital model generated after scanning the first remelting mold. The second laser command sequence refers to the laser parameter commands generated for the second remelting operation based on the analysis of the second multidimensional digital model. The method of obtaining the second laser command sequence is similar to that of obtaining the laser command sequence, and will not be repeated here. The remelting operation refers to the operation of remelting the injection mold a second time according to the second laser command sequence and the laser instrument. Its purpose is to eliminate any incompletely eliminated defects that may exist in the first remelting mold and further improve the surface performance of the mold to obtain a mold that fully meets the target performance. The second remelting mold refers to the mold that has undergone the second laser remelting process.

[0155] S9. Obtain the stress distribution model of the second remelting mold using a pre-built non-destructive stress testing instrument.

[0156] Understandably, due to the laser remelting process, numerous intense and uneven thermal expansions and contractions occur within the injection mold, leaving behind a significant amount of residual stress. If this residual stress is not addressed, it can easily lead to problems such as mold deformation, cracking, corrosion, and shortened lifespan. Therefore, it is necessary to detect the stress level of the injection mold and perform annealing to eliminate this stress. The non-destructive stress testing instrument refers to an ultrasonic residual stress testing instrument capable of measuring the magnitude and distribution of internal stress without damaging the injection mold. The stress distribution model refers to a model constructed based on the detected stress data, displaying the stress distribution within the mold.

[0157] Furthermore, the step of obtaining the stress distribution model of the second remelting mold using a pre-constructed non-destructive stress testing instrument includes:

[0158] The second multidimensional digital model is subjected to stress detection and division operation to obtain a stress detection region set, which includes multiple stress detection regions.

[0159] Using a non-destructive stress testing instrument, stress testing is performed on each stress testing area to obtain a stress information set, in which the stress testing area corresponds one-to-one with the stress information.

[0160] A stress distribution model is constructed based on the stress information set and the second multidimensional digital model.

[0161] Explained, the stress detection partitioning operation refers to dividing the mold surface into multiple sub-regions (i.e., subsurface detection regions) based on the second multi-dimensional digital model to perform stress detection on the mold. The stress detection region set refers to the collection of multiple stress detection regions obtained from the stress detection partitioning operation. The stress detection region refers to the area used for stress detection obtained from the stress detection partitioning operation. The stress detection operation refers to the operation of detecting the stress inside the injection mold using a non-destructive stress testing instrument. The stress information set refers to the collection of stress information from all detected regions.

[0162] Furthermore, the non-destructive stress testing instrument is used to perform stress testing on each stress testing area to obtain a stress information set, including:

[0163] Perform the following operations for each stress testing area:

[0164] Using a pre-built stress detection probe in a non-destructive stress testing instrument, a longitudinal wave emission operation is performed into the stress detection area, and the time of the longitudinal wave emission operation is recorded to obtain the emission time.

[0165] The reflected longitudinal wave was acquired using a stress detection probe, and the acquisition time was recorded.

[0166] The thickness of the stress detection area is obtained, and the longitudinal wave velocity is obtained based on the emission time, acquisition time, and the thickness of the stress detection area.

[0167] Stress information is obtained based on the longitudinal wave velocity, the pre-constructed acoustoelastic coefficient, and the pre-constructed longitudinal wave reference velocity;

[0168] By summarizing the stress information, a stress information set is obtained.

[0169] As is clear, the stress detection probe refers to an instrument used for emitting and receiving longitudinal waves. The longitudinal wave emission operation refers to the operation of using the stress detection probe to emit a longitudinal wave whose vibration direction and propagation direction are in a straight line towards the stress detection area. The emission time refers to the precise time of longitudinal wave emission. The reflected longitudinal wave acquisition operation refers to the operation of using the stress detection probe to acquire the reflected longitudinal wave. The acquisition time refers to the time it takes for the stress detection probe to acquire the reflected longitudinal wave. The thickness of the stress detection area refers to the thickness of the injection mold corresponding to the stress detection area where stress detection is being performed. The longitudinal wave velocity refers to the actual speed at which the longitudinal wave propagates in the stress detection area, calculated based on the emission time, acquisition time, and the thickness of the detection area, and is obtained as follows:

[0170]

[0171] in, Indicates the longitudinal wave velocity. Indicates the thickness of the stress detection area. Indicates the collection time. Indicates the launch time.

[0172] It is clear that when a material is under mechanical stress, the speed of sound waves propagating within it undergoes a small but predictable change, and this change exhibits a linear relationship. Therefore, the stress in the material can be calculated by observing the change in sound speed. The acoustoelastic coefficient is a numerical value describing the linear relationship between the stress on the material and the speed of sound wave propagation within it. The stress information refers to the value representing the magnitude of the stress within a region, calculated using the acoustoelastic coefficient based on the difference between the longitudinal wave velocity and the longitudinal wave reference velocity. Its acquisition method is as follows:

[0173]

[0174] in, Represents stress information, Represents the acoustic elastic coefficient. Indicates the longitudinal wave velocity. This indicates the reference velocity of the longitudinal wave.

[0175] S10. Based on the second multi-dimensional digital model, mold material information, stress distribution model and AI analysis model, obtain stress-relief annealing parameters. Based on the annealing equipment and stress-relief annealing parameters, perform stress relief operation on the second remelting mold to obtain the finished mold.

[0176] Explained, the stress-relief annealing parameters refer to the specific parameters of the annealing process set to eliminate stress in the injection mold, including the heating rate, target temperature, holding time, cooling rate, and second target temperature. The stress relief operation refers to the operation of eliminating stress in the injection mold. The finished mold refers to the final output injection mold that has completed operations such as remelting and annealing.

[0177] Furthermore, the stress-relieving operation on the second remelting mold based on the annealing equipment and stress-relief annealing parameters to obtain the finished mold includes:

[0178] Extract the pre-constructed heating rate and target temperature from the stress-relief annealing parameters. Based on the annealing equipment, heating rate, and target temperature, perform a heating operation on the second remelting mold to obtain the first-stage mold.

[0179] Extract the pre-constructed holding time from the stress-relief annealing parameters, and perform a holding operation on the first-stage mold based on the annealing equipment and holding time to obtain the second-stage mold;

[0180] Extract the pre-constructed cooling rate and second target temperature from the stress-relief annealing parameters. Based on the annealing equipment, cooling rate, and second target temperature, perform a cooling operation on the second-stage mold to obtain the finished mold.

[0181] Understandably, the heating rate refers to the specific value by which the annealing equipment raises the mold temperature per unit time (e.g., every ten minutes) during the heating stage of annealing, aiming to ensure uniform heating of the injection mold. The target temperature refers to the highest temperature to be achieved during the heating stage, aiming to allow the injection mold to obtain sufficient energy at the atomic level to rearrange and eliminate stress. The first-stage mold refers to the mold that has completed the heating operation and whose overall temperature has reached the target temperature. The holding time refers to the time the injection mold needs to be held at the target temperature, aiming to give the atoms sufficient time to complete the rearrangement process for stress release. The second-stage mold refers to the injection mold that has completed heating and sufficient holding, where the stress has been largely eliminated and is ready to enter the cooling stage. The cooling rate refers to the specific value by which the annealing equipment lowers the mold temperature per unit time during the cooling stage of annealing, aiming to prevent the generation of new stress due to excessively rapid cooling. The second target temperature refers to the temperature at the end of the annealing cooling process, marking the completion of the entire stress release operation.

[0182] To address the problems described in the background section, this invention provides an injection mold, a cleaning device, a multimodal scanner, mold material information, polymer material information, an AI analysis model, a laser instrument, and annealing equipment. This invention provides all the necessary physical equipment and data, offering a complete foundation for subsequent automated and intelligent processing, ensuring the systematic nature and integrity of the process. The cleaning device pre-cleans the injection mold, resulting in a clean mold. This invention removes oil, mold release agent residue, and impurities from the mold surface, preventing contaminants from interfering with subsequent scanning and laser processing. The multimodal scanner scans the clean mold to obtain a multidimensional digital model, creating a precise model that includes both surface and subsurface information. The digital model provides a comprehensive and quantitative data foundation for AI analysis, improving the accuracy of diagnosis. Based on mold material information, polymer material information, multi-dimensional digital models, and AI analysis models, preheating temperature, laser command sequences, and predicted molten pool information are obtained. This invention can utilize artificial intelligence technology to generate a highly customized and theoretically optimal initial processing scheme, significantly improving the intelligence level of the process. Preheating the injection mold based on the preheating temperature yields a preheated mold. This invention effectively reduces thermal shock and prevents new cracks by preheating the mold, contributing to a stable molten pool. Based on the laser instrument and laser command sequence, a trial remelting operation is performed on the preheated mold to obtain a trial remelted molten pool. The constructed molten pool monitor monitors the molten pool during the trial remelting process, obtaining molten pool information. This invention demonstrates the ability to validate AI-generated schemes on a small scale, acquiring real-world processing conditions with minimal cost and risk, providing a basis for subsequent closed-loop adjustments. Based on the molten pool information and predicted molten pool information, the molten pool gap is obtained. If the gap is outside the preset allowable range, the laser command sequence is adjusted based on the gap and the AI ​​analysis model to obtain a new laser command sequence. Using this new sequence, the process returns to the step of performing a trial remelting operation on the preheated mold. Otherwise, the preheated mold is remelted to obtain the first remelted mold. This invention thus constructs a feedback and correction closed-loop structure. This invention eliminates the discrepancy between theoretical calculations and actual processing, ensuring that the final laser commands used are the optimal solutions proven in practice. This improves the success rate and reliability of formal processing. A multimodal scanner is used to scan the first remelting mold to obtain a second multidimensional digital model. Based on the second multidimensional digital model and an AI analysis model, a second laser command sequence is obtained. Using the laser instrument and the second laser command sequence, the first remelting mold is remelted to obtain the second remelting mold. Thus, this invention refines the surface through secondary scanning and secondary remelting, further improving surface smoothness, uniformity, and other properties, thereby enhancing the surface quality of the mold. A pre-constructed non-destructive stress detector is used to obtain the stress distribution model of the second remelting mold.It is evident that this invention can detect residual stress generated inside the mold after laser processing, providing accurate information for subsequent stress relief. Based on a second multi-dimensional digital model, mold material information, stress distribution model, and AI analysis model, stress-relief annealing parameters are obtained. Using the annealing equipment and these parameters, a stress-relief annealing operation is performed on the second remelting mold to obtain the finished mold. Thus, this invention eliminates mold stress through annealing, improving the quality of the finished mold. Therefore, this invention can improve the intelligence level, diagnostic accuracy, and finished product quality of surface treatment.

[0183] like Figure 2 The diagram shown is a functional block diagram of a surface treatment system for injection molds of polymer materials provided in an embodiment of the present invention.

[0184] The surface treatment system 100 for injection molds of polymer materials described in this invention can be installed in an electronic device. Depending on the functions implemented, the surface treatment system 100 for injection molds of polymer materials may include a basic modeling module 101, an intelligent planning and monitoring module 102, a remelting operation module 103, and a stress treatment module 104. The module described in this invention can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and which are stored in the memory of the electronic device.

[0185] The basic and modeling module 101 is used to acquire information on injection molds, cleaning equipment, multimodal scanners, mold materials, polymer materials, AI analysis models, laser instruments, and annealing equipment. The cleaning equipment is used to perform pre-cleaning operations on the injection mold to obtain a clean mold. The multimodal scanner is used to scan the clean mold to obtain a multidimensional digital model.

[0186] The intelligent planning and monitoring module 102 is used to obtain preheating temperature, laser command sequence and predicted melt pool information based on mold material information, polymer material information, multi-dimensional digital model and AI analysis model; to preheat the injection mold based on the preheating temperature to obtain a preheated mold; to perform a trial remelting operation on the preheated mold based on the laser instrument and laser command sequence to obtain a trial remelting melt pool; and to monitor the trial remelting melt pool using a pre-constructed melt pool monitor to obtain melt pool information.

[0187] The remelting operation module 103 is used to obtain the molten pool gap based on the molten pool information and the predicted molten pool information. If the molten pool gap is not within the preset allowable molten pool gap range, the laser command sequence is adjusted based on the molten pool gap and the AI ​​analysis model to obtain a new laser command sequence. The new laser command sequence is used as the laser command sequence, and the step of performing a trial remelting operation on the preheated mold is returned. Otherwise, the preheated mold is remelted to obtain a first remelting mold. The first remelting mold is scanned using a multimodal scanner to obtain a second multidimensional digital model. Based on the second multidimensional digital model and the AI ​​analysis model, a second laser command sequence is obtained. Based on the laser instrument and the second laser command sequence, the first remelting mold is remelted to obtain a second remelting mold.

[0188] The stress processing module 104 is used to obtain the stress distribution model of the second remelting mold using a pre-constructed non-destructive stress detector, obtain stress relief annealing parameters based on the second multi-dimensional digital model, mold material information, stress distribution model and AI analysis model, and perform stress relief operation on the second remelting mold based on the annealing equipment and stress relief annealing parameters to obtain the finished mold.

[0189] In detail, the modules in the surface treatment system 100 for injection molds of polymer materials described in this embodiment of the invention employ the same methods as described above during use. Figure 1 The surface treatment method for injection molds of polymer materials described herein is the same as the technical means and can produce the same technical effect, so it will not be repeated here.

[0190] like Figure 3 The diagram shown is a schematic representation of an electronic device for implementing a surface treatment method for injection molds of polymer materials, according to an embodiment of the present invention.

[0191] The electronic device 1 may include a processor 10, a memory 11 and a bus 12, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as a surface treatment method program for injection molds of polymer materials.

[0192] The memory 11 includes at least one type of readable storage medium, such as flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 1, such as a portable hard drive. In other embodiments, the memory 11 can be an external storage device of the electronic device 1, such as a plug-in portable hard drive, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the electronic device 1. Furthermore, the memory 11 includes both internal storage units and external storage devices of the electronic device 1. The memory 11 can be used not only to store application software and various types of data installed on the electronic device 1, such as code for a surface treatment method program for injection molds of polymer materials, but also to temporarily store data that has been output or will be output.

[0193] In some embodiments, the processor 10 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the electronic device, connecting various components of the entire electronic device through various interfaces and lines. It executes programs or modules stored in the memory 11 (e.g., a surface treatment method program for injection molds of polymer materials) and calls data stored in the memory 11 to perform various functions of the electronic device 1 and process data.

[0194] The bus 12 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 can be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to realize the connection and communication between the memory 11 and at least one processor 10, etc.

[0195] Figure 3 Only electronic devices with components are shown; it will be understood by those skilled in the art that... Figure 3The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0196] For example, although not shown, the electronic device 1 may also include a power supply (such as a battery) to power the various components. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management system, thereby enabling functions such as charging management, discharging management, and power consumption management through the power management system. The power supply may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 1 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0197] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, a Bluetooth interface, etc.), which is typically used to establish communication connections between the electronic device 1 and other electronic devices.

[0198] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), and optionally, a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the electronic device 1 and to display a visual user interface.

[0199] The surface treatment method program for injection molds of polymer materials stored in the memory 11 of the electronic device 1 is a combination of multiple instructions, which, when run in the processor 10, can achieve the following:

[0200] Acquire information on injection molds, cleaning equipment, multimodal scanners, mold materials, polymer materials, AI analysis models, laser instruments, and annealing equipment;

[0201] The injection mold is pre-cleaned using a cleaning device to obtain a clean mold;

[0202] A multimodal scanner was used to scan the cleaning mold to obtain a multidimensional digital model;

[0203] Preheating temperature, laser command sequence, and predicted molten pool information are obtained based on mold material information, polymer material information, multi-dimensional digital model, and AI analysis model.

[0204] The injection mold is preheated based on the preheating temperature to obtain a preheated mold.

[0205] Based on the laser instrument and laser command sequence, a trial remelting operation is performed on the preheated mold to obtain a trial remelting pool. A pre-constructed pool monitor is used to monitor the trial remelting pool to obtain pool information.

[0206] Based on the molten pool information and the predicted molten pool information, the molten pool gap is obtained. If the molten pool gap is not within the preset allowable molten pool gap range, the laser command sequence is adjusted based on the molten pool gap and the AI ​​analysis model to obtain a new laser command sequence. The new laser command sequence is used as the laser command sequence, and the step of performing a trial remelting operation on the preheated mold is returned. Otherwise, the preheated mold is remelted to obtain the first remelted mold.

[0207] A multimodal scanner is used to scan the first remelting mold to obtain a second multidimensional digital model. Based on the second multidimensional digital model and the AI ​​analysis model, a second laser command sequence is obtained. Based on the laser instrument and the second laser command sequence, the first remelting mold is remelted to obtain the second remelting mold.

[0208] The stress distribution model of the second remelting mold was obtained using a pre-constructed non-destructive stress testing instrument;

[0209] Based on the second multidimensional digital model, mold material information, stress distribution model and AI analysis model, stress-relief annealing parameters are obtained. Based on the annealing equipment and stress-relief annealing parameters, stress release operation is performed on the second remelting mold to obtain the finished mold.

[0210] Specifically, the processor 10's implementation method for the above instructions can be found in [reference needed]. Figures 1 to 3 The descriptions of the relevant steps in the corresponding embodiments are not repeated here.

[0211] Furthermore, if the modules / units integrated in the electronic device 1 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or system capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0212] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor of an electronic device, can perform the following:

[0213] Acquire information on injection molds, cleaning equipment, multimodal scanners, mold materials, polymer materials, AI analysis models, laser instruments, and annealing equipment;

[0214] The injection mold is pre-cleaned using a cleaning device to obtain a clean mold;

[0215] A multimodal scanner was used to scan the cleaning mold to obtain a multidimensional digital model;

[0216] Preheating temperature, laser command sequence, and predicted molten pool information are obtained based on mold material information, polymer material information, multi-dimensional digital model, and AI analysis model.

[0217] The injection mold is preheated based on the preheating temperature to obtain a preheated mold.

[0218] Based on the laser instrument and laser command sequence, a trial remelting operation is performed on the preheated mold to obtain a trial remelting pool. A pre-constructed pool monitor is used to monitor the trial remelting pool to obtain pool information.

[0219] Based on the molten pool information and the predicted molten pool information, the molten pool gap is obtained. If the molten pool gap is not within the preset allowable molten pool gap range, the laser command sequence is adjusted based on the molten pool gap and the AI ​​analysis model to obtain a new laser command sequence. The new laser command sequence is used as the laser command sequence, and the step of performing a trial remelting operation on the preheated mold is returned. Otherwise, the preheated mold is remelted to obtain the first remelted mold.

[0220] A multimodal scanner is used to scan the first remelting mold to obtain a second multidimensional digital model. Based on the second multidimensional digital model and the AI ​​analysis model, a second laser command sequence is obtained. Based on the laser instrument and the second laser command sequence, the first remelting mold is remelted to obtain the second remelting mold.

[0221] The stress distribution model of the second remelting mold was obtained using a pre-constructed non-destructive stress testing instrument;

[0222] Based on the second multidimensional digital model, mold material information, stress distribution model and AI analysis model, stress-relief annealing parameters are obtained. Based on the annealing equipment and stress-relief annealing parameters, stress release operation is performed on the second remelting mold to obtain the finished mold.

[0223] In the embodiments provided by this invention, it should be understood that the disclosed devices, systems, and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative, and actual implementations may have other classification methods.

[0224] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0225] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0226] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0227] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A surface treatment method for injection molds of polymer materials, characterized in that, The method includes: Acquire information on injection molds, cleaning equipment, multimodal scanners, mold materials, polymer materials, AI analysis models, laser instruments, and annealing equipment; The injection mold is pre-cleaned using a cleaning device to obtain a clean mold; A multimodal scanner was used to scan the cleaning mold to obtain a multidimensional digital model; Preheating temperature, laser command sequence, and predicted molten pool information are obtained based on mold material information, polymer material information, multi-dimensional digital model, and AI analysis model. The injection mold is preheated based on the preheating temperature to obtain a preheated mold. Based on the laser instrument and laser command sequence, a trial remelting operation is performed on the preheated mold to obtain a trial remelting pool. A pre-constructed pool monitor is used to monitor the trial remelting pool to obtain pool information. Based on the molten pool information and the predicted molten pool information, the molten pool gap is obtained. If the molten pool gap is not within the preset allowable molten pool gap range, the laser command sequence is adjusted based on the molten pool gap and the AI ​​analysis model to obtain a new laser command sequence. The new laser command sequence is used as the laser command sequence, and the step of performing a trial remelting operation on the preheated mold is returned. Otherwise, the preheated mold is remelted to obtain the first remelted mold. A multimodal scanner is used to scan the first remelting mold to obtain a second multidimensional digital model. Based on the second multidimensional digital model and the AI ​​analysis model, a second laser command sequence is obtained. Based on the laser instrument and the second laser command sequence, the first remelting mold is remelted to obtain the second remelting mold. The stress distribution model of the second remelting mold was obtained using a pre-constructed non-destructive stress testing instrument; Based on the second multidimensional digital model, mold material information, stress distribution model and AI analysis model, stress-relief annealing parameters are obtained. Based on the annealing equipment and stress-relief annealing parameters, stress release operation is performed on the second remelting mold to obtain the finished mold.

2. The surface treatment method for injection molds of polymer materials as described in claim 1, characterized in that, The process of pre-cleaning the injection mold using a cleaning device to obtain a clean mold includes: Based on the mold material information, a cleaning agent is obtained. Based on the cleaning agent and a pre-constructed ultrasonic cleaner, an ultrasonic cleaning operation is performed on the injection mold to obtain the first clean mold. Using a pre-built high-pressure flushing device, the first cleaning mold is subjected to high-pressure flushing to obtain the second cleaning mold; The second cleaning mold is dried using a pre-built dryer to obtain a clean mold.

3. The surface treatment method for injection molds of polymer materials as described in claim 2, characterized in that, The process of scanning the cleaning mold using a multimodal scanner to obtain a multidimensional digital model includes: The surface of the cleaning mold is scanned using a pre-built laser scanning unit in a multimodal scanner to obtain a mold surface model. The mold surface model is divided to obtain a subsurface detection region set, which includes multiple subsurface detection regions. Ultrasonic pulse signals are generated using a pre-built ultrasonic scanning unit in a multimodal scanner. The ultrasonic scanning unit includes an ultrasonic transducer and a subsurface detection probe. Obtain standard defect samples, and based on the standard defect samples, obtain an amplitude-defect volume curve atlas, wherein the amplitude-defect volume curve atlas includes multiple amplitude-defect volume curves; For each subsurface detection region in the subsurface detection region set, perform the following operations: Using ultrasonic pulse signals, an ultrasonic transducer, and a subsurface detection probe, an ultrasonic scanning operation is performed on the subsurface detection area to obtain an echo waveform. Obtain the thickness of the subsurface detection area, and based on the thickness of the subsurface detection area and the preset ultrasonic reference velocity, obtain the echo reference time; Based on the echo waveform diagram, echo reference time, and preset defect judgment conditions, the defect judgment result is obtained; If the defect judgment result is that there is no defect as preset, then the subsurface detection area is confirmed as the preset defect-free area. If the defect judgment result is that a defect exists as preset, the subsurface detection area is confirmed as the preset defect area, and the defect transit time is obtained according to the echo waveform. Based on the defect transit time and the ultrasonic reference velocity, the defect depth is obtained. Defect volume is obtained based on the defect depth and amplitude-defect volume curve atlas; By summarizing the defect depth and defect volume, information about a single defect can be obtained. Summarize the defect-free areas to obtain a defect-free area information set; By summarizing the information of individual defects, a defect area information set is obtained. Based on the defect-free area information set and the defect area information set, a mold subsurface model is constructed. Based on the mold surface model and the mold sub-surface model, a fusion operation is performed in a pre-constructed spatial coordinate system to obtain a multi-dimensional digital model.

4. The surface treatment method for injection molds of polymer materials as described in claim 3, characterized in that, The process of obtaining preheating temperature, laser command sequence, and predicted molten pool information based on mold material information, polymer material information, multidimensional digital models, and AI analysis models includes: Obtaining target performance of molds based on polymer material information; Based on mold material information and AI analysis models, the preheating temperature is obtained; Based on the target performance of the mold, the information set of the defect area, the mold material information, the preheating temperature, and the AI ​​analysis model, the laser command sequence for defect processing is obtained; Based on the target performance of the mold, the information set of defect-free areas, the mold material information, the preheating temperature, and the AI ​​analysis model, the laser command sequence for roughness treatment is obtained; By summarizing the laser command sequences for defect processing and roughness processing, a laser command sequence is obtained. Based on the laser command sequence, mold material information, preheating temperature, and AI analysis model, the predicted molten pool information is obtained.

5. The surface treatment method for injection molds of polymer materials as described in claim 4, characterized in that, The process involves performing a trial remelting operation on a preheated mold based on a laser instrument and laser command sequence to obtain a trial remelted molten pool. A pre-constructed molten pool monitor is then used to monitor the molten pool and obtain molten pool information, including: Based on the preset test remelting area, defect test remelting areas and roughness test remelting areas are selected from the defect area information set and the non-defect area information set, respectively. Based on the laser instrument and laser command sequence, a trial remelting operation is performed on the defect trial remelting area and the roughness trial remelting area to obtain the trial remelting pool. The molten pool is monitored using a molten pool monitor to obtain molten pool information, including molten pool temperature and molten pool width.

6. The surface treatment method for injection molds of polymer materials as described in claim 5, characterized in that, The process involves obtaining the molten pool gap based on molten pool information and predicted molten pool information. If the molten pool gap is not within a preset allowable molten pool gap range, the laser command sequence is adjusted based on the molten pool gap and the AI ​​analysis model to obtain a new laser command sequence, including: The difference in molten pool temperature is obtained by comparing the molten pool temperature with the preset predicted molten pool temperature in the predicted molten pool information. The difference in molten pool width is obtained by comparing the molten pool width with the preset predicted molten pool width in the predicted molten pool information. The molten pool difference is obtained by summing the differences in molten pool temperature and molten pool width. If the temperature difference of the molten pool is not within the preset allowable temperature difference range of the molten pool, or the width difference of the molten pool is not within the preset allowable width difference range of the molten pool, then it is confirmed that the molten pool difference is not within the allowable molten pool difference range. Using an AI analysis model, the molten pool gap is analyzed in reverse to obtain laser adjustment commands; By using laser adjustment commands, the laser command sequence is adjusted to obtain a new laser command sequence.

7. The surface treatment method for injection molds of polymer materials as described in claim 6, characterized in that, The process of obtaining the stress distribution model of the second remelting mold using a pre-constructed non-destructive stress testing instrument includes: The second multidimensional digital model is subjected to stress detection and division operation to obtain a stress detection region set, which includes multiple stress detection regions. Using a non-destructive stress testing instrument, stress testing is performed on each stress testing area to obtain a stress information set, in which the stress testing area corresponds one-to-one with the stress information. A stress distribution model is constructed based on the stress information set and the second multidimensional digital model.

8. The surface treatment method for injection molds of polymer materials as described in claim 7, characterized in that, The method involves using a non-destructive stress testing instrument to perform stress testing on each stress testing area, thereby obtaining a stress information set, including: Perform the following operations for each stress testing area: Using a pre-built stress detection probe in a non-destructive stress testing instrument, a longitudinal wave emission operation is performed into the stress detection area, and the time of the longitudinal wave emission operation is recorded to obtain the emission time. The reflected longitudinal wave was acquired using a stress detection probe, and the acquisition time was recorded. The thickness of the stress detection area is obtained, and the longitudinal wave velocity is obtained based on the emission time, acquisition time, and the thickness of the stress detection area. Stress information is obtained based on the longitudinal wave velocity, the pre-constructed acoustoelastic coefficient, and the pre-constructed longitudinal wave reference velocity; By summarizing the stress information, a stress information set is obtained.

9. The surface treatment method for injection molds of polymer materials as described in claim 8, characterized in that, The process of performing stress-relieving operation on the second remelting mold based on the annealing equipment and stress-relief annealing parameters to obtain the finished mold includes: Extract the pre-constructed heating rate and target temperature from the stress-relief annealing parameters. Based on the annealing equipment, heating rate, and target temperature, perform a heating operation on the second remelting mold to obtain the first-stage mold. Extract the pre-constructed holding time from the stress-relief annealing parameters, and perform a holding operation on the first-stage mold based on the annealing equipment and holding time to obtain the second-stage mold; Extract the pre-constructed cooling rate and second target temperature from the stress-relief annealing parameters. Based on the annealing equipment, cooling rate, and second target temperature, perform a cooling operation on the second-stage mold to obtain the finished mold.

10. A surface treatment system for injection molds of polymer materials, characterized in that, The system includes: The basics and modeling module is used to acquire information on injection molds, cleaning equipment, multimodal scanners, mold materials, polymer materials, AI analysis models, laser instruments, and annealing equipment. The cleaning equipment is used to pre-clean the injection mold to obtain a clean mold, and the multimodal scanner is used to scan the clean mold to obtain a multidimensional digital model. The intelligent planning and monitoring module is used to obtain preheating temperature, laser command sequence and predicted melt pool information based on mold material information, polymer material information, multi-dimensional digital model and AI analysis model. Based on the preheating temperature, the injection mold is preheated to obtain a preheated mold. Based on the laser instrument and laser command sequence, the preheated mold is remelted to obtain a remelted melt pool. The remelted melt pool is monitored using a pre-built melt pool monitor to obtain melt pool information. The remelting operation module is used to obtain the molten pool gap based on the molten pool information and the predicted molten pool information. If the molten pool gap is not within the preset allowable molten pool gap range, the laser command sequence is adjusted based on the molten pool gap and the AI ​​analysis model to obtain a new laser command sequence. The new laser command sequence is used as the laser command sequence, and the step of performing a trial remelting operation on the preheated mold is returned. Otherwise, the preheated mold is remelted to obtain a first remelting mold. The first remelting mold is scanned using a multimodal scanner to obtain a second multidimensional digital model. Based on the second multidimensional digital model and the AI ​​analysis model, a second laser command sequence is obtained. Based on the laser instrument and the second laser command sequence, the first remelting mold is remelted to obtain a second remelting mold. The stress treatment module is used to obtain the stress distribution model of the second remelting mold using a pre-built non-destructive stress detector. Based on the second multi-dimensional digital model, mold material information, stress distribution model and AI analysis model, stress relief annealing parameters are obtained. Based on the annealing equipment and stress relief annealing parameters, stress release operation is performed on the second remelting mold to obtain the finished mold.

Images