A method and system for controlling metal powder injection molding

Abstract

This invention relates to the field of injection control technology, specifically to a method and system for controlling metal powder injection molding. The method includes: using 3D scanning combined with finite element analysis to model the environment of the metal powder injection molding mold and the detection area of ​​the quartz tube sensor, obtaining and storing the mold cavity, the installation position of the quartz tube sensor, and the detection path; sending molding process commands through the molding control system, parsing to obtain injection parameters, molding temperature, and quartz tube sensor detection trigger conditions; planning the injection path and the quartz tube sensor detection path based on an improved genetic algorithm combined with real-time detection feedback rules from the quartz tube sensor; and using the quartz tube sensor to detect the metal powder filling state, melt flow rate, and cavity pressure in real time during the molding process, dynamically correcting the molding parameters and path using a conflict detection mechanism. This invention improves molding accuracy and production efficiency by combining quartz tube sensor detection technology with intelligent path planning and dynamic parameter adjustment.

Description

Technical Field

[0001] This invention relates to the field of injection control technology, specifically to a method and system for controlling metal powder injection molding. Background Technology

[0002] Metal powder injection molding (MIM) is an advanced manufacturing technology that combines powder metallurgy with plastic injection molding. It boasts advantages such as high precision, high complexity, and strong mass production capabilities, and is widely used in aerospace, automotive manufacturing, and electronic equipment industries. However, existing metal powder injection molding processes face numerous technical bottlenecks: Delayed inspection during molding process: Traditional inspection methods are mostly offline inspections after molding, which cannot capture the filling state, flow rate and pressure changes of the molten metal powder in the cavity in real time. As a result, defects such as insufficient filling, bubbles and cracks cannot be detected in time, and the scrap rate is high. Poor adaptability of injection path planning: Existing injection path planning is mostly based on fixed process parameters and does not combine real-time detection data for dynamic adjustment. It is difficult to adapt to changes in different metal powder materials and mold structures, resulting in poor molding uniformity. Insufficient coordination between testing and molding: The installation location and testing range of existing testing equipment lack scientific planning, which can easily conflict with the injection path. Furthermore, the guidance role of testing data in adjusting molding parameters is unclear, making it impossible to form a closed-loop control. Environmental interference affects detection accuracy: The high temperature environment during the molding process can lead to a decrease in the accuracy of the detection equipment, and factors such as mold wear and changes in raw material properties are not incorporated into the model in real time, further reducing the accuracy of molding control.

[0003] Quartz tube sensors have the characteristics of high light transmittance, high temperature resistance, and strong chemical stability, making them suitable as detection carriers in high-temperature molding environments. However, existing technologies have not fully utilized the advantages of quartz tube sensors and have not established a collaborative mechanism between quartz tube sensor detection and injection molding path planning and parameter adjustment, thus failing to effectively solve the aforementioned technical problems. Summary of the Invention

[0004] To address the aforementioned technical shortcomings, this invention provides a metal powder injection molding control method and system. By combining real-time detection technology using quartz tube sensors with improved genetic algorithm path planning and dynamic parameter adjustment, closed-loop control of the molding process is achieved, thereby improving molding accuracy and production efficiency while reducing scrap rate.

[0005] This invention is achieved through the following technical solution: A method for controlling metal powder injection molding is provided, the method comprising the following steps: Step S10: Use three-dimensional laser scanning technology to collect data on the cavity structure of the metal powder injection molding mold, the mounting hole position of the quartz tube sensor, the position of the detection window, and the spatial dimensions of the molding area. Combine this with finite element analysis to establish a mold-quartz tube sensor coupling environment model and store the model information in the database of the molding control system. Step S20: The metal powder injection molding process command is sent through the molding control system. The injection molding equipment receives and parses the command to obtain the control parameters. Step S30: Based on the improved genetic algorithm combined with the quartz tube sensor detection feedback rules, according to the model information in step S10 and the process parameters analyzed in step S20, plan the metal powder injection path and the real-time detection path of the quartz tube sensor. The injection path includes the melt flow trajectory and the segmented injection pressure distribution scheme, and the detection path includes the quartz tube body detection point sequence and the detection angle adjustment scheme. Step S40: During the injection molding process, the filling progress, flow rate, cavity pressure and melt uniformity of the metal powder melt are detected in real time by a quartz tube sensor installed at a preset position in the mold. The detection data and preset thresholds are compared and analyzed to predict defects and detect path conflicts. When the detection data exceeds the threshold or there is a potential conflict, the injection pressure, speed and detection parameters of the quartz tube sensor are dynamically adjusted to correct the injection path and the detection path. In step S10, finite element analysis is used to simulate the temperature and stress field distribution of the mold cavity and determine the optimal installation position and detection angle of the quartz tube sensor to ensure that the detection range covers the key filling area of ​​the cavity. The model information is stored in a three-dimensional array, and the array elements correspond to the coordinates, temperature attributes and detection accessibility identifiers of the cavity mesh nodes. The quartz tube sensor detection uses a high-transmittance, high-temperature resistant quartz tube sensor as the detection carrier to monitor key molding parameters such as the filling progress, flow rate, uniformity and cavity pressure of the metal powder melt inside the mold cavity in real time during the metal powder injection molding process. In step S40, the conflict detection includes conflicts between the injection path and the detection field of the quartz tube sensor, and conflicts between the matching of molding parameter adjustment and detection frequency. When uneven filling of metal powder, abnormal melt flow rate, or sudden change in cavity pressure is detected, the fitness function weight of the improved genetic algorithm is adjusted according to the severity of the defect and the priority of the production task, the path is replanned and the molding parameters are updated.

[0006] Preferably, step S10, which involves using three-dimensional laser scanning technology to acquire data on the cavity structure of the metal powder injection molding die, the mounting holes of the quartz tube sensor, the position of the detection window, and the spatial dimensions of the molding area, includes: Data acquisition: A 3D laser scanner is used to perform a full-size scan of the mold cavity inner wall, quartz tube sensor mounting base, injection channel and vent hole to obtain point cloud data. At the same time, physical parameters such as thermal conductivity coefficient and thermal expansion coefficient of the mold material are also collected. Point cloud processing: The collected point cloud data is denoised, registered and meshed to divide the cavity space into a three-dimensional grid with a side length of 0.01-0.05mm. Each grid node is assigned a unique three-dimensional coordinate identifier (x,y,z). Finite element simulation: Import the meshed model into the finite element analysis software, set the initial temperature and pressure boundary conditions for injection molding, simulate the flow path and temperature distribution of the melt in the cavity, and identify high-risk areas that are prone to defects such as incomplete filling, bubbles and cracks. Quartz tube sensor detection area calibration: Based on the finite element simulation results, mark the installation position of the quartz tube sensor on the mold wall corresponding to the high-risk area, determine the detection angle of each quartz tube sensor, the angle with the cavity wall is 30° to 60°, the detection distance is 5-15mm and the effective detection range, convert the marked model information into a machine-readable three-dimensional array and store it in the molding control system; Model update mechanism: The mold is scanned every 8 hours to update the temperature field and wear status data of the model. When the mold is repaired, the metal powder raw material is replaced, or the molding process is adjusted, an event-driven update is triggered to remodel and calibrate the detection area of ​​the quartz tube sensor.

[0007] Preferably, sending the metal powder injection molding process command through the molding control system in step S20 includes: Basic molding parameter instructions: specify injection pressure, injection speed, molding temperature, holding time, and cooling time, and match initial parameters according to the characteristics of the metal powder material; Quartz tube sensor detection parameter instructions: set the detection frequency, detection accuracy threshold, and upper limit of detection data transmission delay, and clarify the detection area and data acquisition priority of each quartz tube sensor; Defect warning threshold instructions: preset warning thresholds for insufficient filling, air bubbles, and uneven flow, as well as corresponding emergency handling levels; Priority adjustment instruction: Based on the urgency of production orders and the level of product precision requirements, set the priority weights for molding quality and production efficiency. When parameter adjustment conflicts occur, the decision is made according to the priority weights.

[0008] Preferably, step S30, based on an improved genetic algorithm combined with the quartz tube sensor detection feedback rules, includes: Coding method design: Real number coding is adopted, and the segmented pressure and speed parameters of the injection path and the coordinates and detection angles of the quartz tube sensor detection points are used as chromosome genes. Each gene corresponds to the value range of a process parameter or detection parameter. Fitness function construction: Fitness function F = α·F1 + β·F2 + γ·F3, where F1 is the filling uniformity evaluation index, calculated based on melt flow uniformity from finite element simulation, F2 is the detection coverage evaluation index, and F3 is the molding efficiency evaluation index, calculated based on the total injection molding time. F1, F2 and F3 are all percentages, and α, β and γ are weighting coefficients, dynamically adjusted according to the priority instructions in step S20. Genetic operations: The selection operation uses a combination of roulette wheel selection and elite retention strategy, retaining the top 10% of chromosomes in fitness value to directly enter the next generation; the crossover operation uses arithmetic crossover, performing linear combination of corresponding genes on adjacent chromosomes to generate new combinations of process parameters; the mutation operation uses adaptive mutation, adjusting the mutation probability according to the number of generations of population evolution. Quartz tube sensor detection feedback rule setting: When a lag in filling progress is detected, the injection pressure in the corresponding area should be increased first; when the flow rate is detected to be too fast, the local injection speed should be reduced and the detection frequency should be increased; when the field of view is obstructed in the detection area, the detection angle of the quartz tube sensor should be adjusted or a backup detection point should be switched. Path optimization and determination: By improving the genetic algorithm for iterative calculation, the optimal combination of injection path and detection path is obtained. The path is verified to meet the detection feedback rules of the quartz tube sensor. For the parts that do not meet the rules, the parameters are fine-tuned to form the final execution path.

[0009] Preferably, the quartz tube sensor in step S40 includes a quartz tube body, a laser emitting unit, a laser receiving unit, a pressure sensing unit, and a temperature compensation unit. The quartz tube sensor is made of high-transmittance quartz material and is fixed to the mold wall by a sealing seat during installation to ensure that the detection end face is flush with the inner wall of the cavity and to avoid affecting the flow of the melt.

[0010] Preferably, the step of correcting the injection path and the detection path in step S40 includes: Data acquisition: The quartz tube sensor is based on the principle of light reflection and transmission to collect data in real time on the filling height, flow front position, melt refractive index and cavity wall pressure of the molten metal powder inside the cavity. The melt refractive index is used to reflect the uniformity. The data sampling frequency is consistent with the detection frequency set in step S20. Data preprocessing: The collected data is filtered and denoised to remove outliers. The Kalman filter algorithm is used for filtering. The processed data is then matched with the model information from step S10 to determine the potential location of defects. Defect judgment and conflict detection: The pre-processed data is compared with the preset warning threshold. When the filling progress is lower than the threshold, the flow rate fluctuates excessively, or the pressure changes abruptly, it is judged as a potential defect. At the same time, it is detected whether the injection path overlaps with the detection field of the quartz tube sensor and whether parameter adjustment will cause the detection frequency to be mismatched. When the field of view overlaps and the detection frequency is mismatched, it is judged as a conflict. Dynamic correction strategy: When there are minor defects and no conflicts, adjust the injection pressure and speed of the corresponding area, keep the detection parameters unchanged, adjust the fitness function weight, replan the injection path and detection path, and update the detection frequency of the quartz tube sensor. Correction result feedback: The dynamically corrected parameters and paths are fed back to the molding control system in real time, and the model information in the database is updated synchronously to provide a reference for subsequent molding tasks.

[0011] Furthermore, to achieve the above objectives, the present invention also proposes a metal powder injection molding control system, which includes: Mold-quartz tube sensor coupling modeling module: Used to acquire data on the cavity structure of metal powder injection molding mold, the mounting hole position of quartz tube sensor, the position of detection window and the spatial dimensions of the molding area using 3D laser scanning technology, and to establish a mold-quartz tube sensor coupling environment model by combining finite element analysis, and store the model information in the database of the molding control system; Process instruction sending and parsing module: used to send metal powder injection molding process instructions through the molding control system, and the injection molding equipment receives and parses the instructions to obtain control parameters; Path planning module: Based on the improved genetic algorithm combined with the quartz tube sensor detection feedback rules, and according to the model information of the mold-quartz tube sensor coupling modeling module and the process parameters analyzed by the process instruction sending and parsing module, the module plans the metal powder injection path and the real-time detection path of the quartz tube sensor. The injection path includes the melt flow trajectory and the segmented injection pressure distribution scheme, and the detection path includes the quartz tube body detection point sequence and the detection angle adjustment scheme. Real-time detection and dynamic correction module: During the injection molding process, a quartz tube sensor installed at a preset position in the mold is used to detect the filling progress, flow rate, cavity pressure and melt uniformity of the metal powder melt in real time. The detection data is compared and analyzed with preset thresholds to predict defects and detect path conflicts. When the detection data exceeds the threshold or there is a potential conflict, the injection pressure, speed and quartz tube sensor detection parameters are dynamically adjusted to correct the injection path and detection path. In the mold-quartz tube sensor coupled modeling module, finite element analysis is used to simulate the temperature field and stress field distribution of the mold cavity, determine the optimal installation position and detection angle of the quartz tube sensor, and ensure that the detection range covers the key filling area of ​​the cavity. The model information is stored in a three-dimensional array, and the array elements correspond to the coordinates, temperature attributes and detection reachability identifiers of the cavity mesh nodes. In the real-time detection and dynamic correction module, the conflict detection includes conflicts between the injection path and the detection field of the quartz tube sensor, and conflicts between the matching of molding parameter adjustment and detection frequency. When uneven filling of metal powder, abnormal melt flow rate, or sudden change in cavity pressure is detected, the fitness function weight of the improved genetic algorithm is adjusted according to the severity of the defect and the priority of the production task, the path is replanned and the molding parameters are updated.

[0012] Furthermore, to achieve the above objectives, the present invention also proposes a metal powder injection molding control device, the device comprising: a memory, a processor, and a metal powder injection molding control program stored in the memory and executable on the processor, the metal powder injection molding control program comprising the steps of implementing a metal powder injection molding control method as described above.

[0013] In addition, to achieve the above objectives, the present invention also provides a computer program product, which includes programs such as metal powder injection molding control, and when the metal powder injection molding control programs are executed by a processor, they implement a metal powder injection molding control method as described above.

[0014] The advantages and effects of this invention are: This invention proposes a metal powder injection molding control method and system. Utilizing the high transmittance and high-temperature resistance of a quartz tube sensor, it achieves real-time detection of the metal powder melt filling state, flow rate, and pressure during the molding process, solving the problem of lag in traditional offline detection and enabling timely detection and handling of molding defects. An improved genetic algorithm combined with quartz tube sensor detection feedback rules is employed to achieve collaborative optimization of the injection path and detection path. Path planning adapts to different mold structures, metal powder materials, and production priority requirements, improving molding uniformity and detection coverage. Through comparative analysis of detection data and preset thresholds, injection pressure, speed, and quartz tube sensor detection parameters are dynamically adjusted, effectively solving defects such as uneven filling and bubbles, while avoiding conflicts between detection and molding, thus improving process adaptability. The quartz tube sensor has a built-in temperature compensation module to eliminate the impact of high-temperature environments on detection accuracy. The mold-quartz tube sensor coupling model supports timed updates and event-driven updates, adapting to dynamic scenarios such as mold wear and material changes, ensuring the stability of control accuracy. By predicting and dynamically correcting defects in real time, the scrap rate is significantly reduced, while molding efficiency is optimized, production cycle is shortened, and the large-scale production capacity of metal powder injection molding is improved. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a flowchart of a metal powder injection molding control method according to the present invention.

[0017] Figure 2 This is a schematic diagram of a metal powder injection molding control system according to the present invention.

[0018] Figure 3 This is a schematic block diagram of a metal powder injection molding control electronic device according to the present invention. Detailed Implementation

[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] like Figure 1 As shown, in one embodiment of the present invention, a method for controlling metal powder injection molding includes the following steps: Step S10: Use 3D laser scanning technology to collect data on the cavity structure of the metal powder injection molding mold, the mounting hole position of the quartz tube sensor, the position of the detection window, and the spatial dimensions of the molding area. Combine this with finite element analysis to establish a mold-quartz tube sensor coupling environment model. The model information includes the 3D coordinates of the cavity, the effective detection range of the quartz tube sensor, the relative position of the injection port and the cavity, and the temperature field distribution area of ​​the mold. Store the model information in the database of the molding control system.

[0021] Specifically, in step S10, finite element analysis is used to simulate the temperature and stress field distribution of the mold cavity and determine the optimal installation position and detection angle of the quartz tube sensor to ensure that the detection range covers the key filling area of ​​the cavity. The model information is stored in a three-dimensional array, and the array elements correspond to the coordinates, temperature attributes, and detection accessibility identifiers of the cavity mesh nodes. The quartz tube sensor detection uses a high-transmittance, high-temperature resistant quartz tube sensor as the detection carrier to monitor key molding parameters such as the filling progress, flow rate, uniformity, and cavity pressure of the metal powder melt inside the mold cavity in real time during the metal powder injection molding process.

[0022] Specifically, step S10, which involves using three-dimensional laser scanning technology to acquire data on the cavity structure of the metal powder injection molding die, the mounting holes of the quartz tube sensor, the position of the detection window, and the spatial dimensions of the molding area, includes: Data acquisition: A 3D laser scanner with an accuracy of ±0.001mm is used to perform a full-size scan of the mold cavity inner wall, quartz tube sensor mounting base, injection channel and vent hole to obtain point cloud data. At the same time, physical parameters such as thermal conductivity coefficient and thermal expansion coefficient of the mold material are also collected. Point cloud processing: The collected point cloud data is denoised, registered and meshed to divide the cavity space into a three-dimensional grid with a side length of 0.01-0.05mm. Each grid node is assigned a unique three-dimensional coordinate identifier (x,y,z). Finite element simulation: Import the meshed model into the finite element analysis software, set the initial temperature and pressure boundary conditions for injection molding, simulate the flow path and temperature distribution of the melt in the cavity, and identify high-risk areas that are prone to defects such as incomplete filling, bubbles and cracks. Quartz tube sensor detection area calibration: Based on the finite element simulation results, mark the installation position of the quartz tube sensor on the mold wall corresponding to the high-risk area, determine the detection angle of each quartz tube sensor, the angle with the cavity wall is 30° to 60°, the detection distance is 5-15mm and the effective detection range, convert the marked model information into a machine-readable three-dimensional array and store it in the molding control system; Model update mechanism: The mold is scanned every 8 hours to update the temperature field and wear status data of the model. When the mold is repaired, the metal powder raw material is replaced, or the molding process is adjusted, an event-driven update is triggered to remodel and calibrate the detection area of ​​the quartz tube sensor.

[0023] Step S20: The molding control system sends a metal powder injection molding process instruction. The injection molding equipment receives and parses the instruction to obtain control parameters, such as injection pressure, injection speed, molding temperature, holding time, quartz tube sensor detection frequency and detection trigger threshold. The process instruction includes basic molding parameter instruction, quartz tube sensor detection parameter instruction, defect early warning threshold instruction and priority adjustment instruction.

[0024] Specifically, the steps in step S20 where the signal preprocessing unit performs adaptive filtering, baseline correction, and period synchronization processing on the current signal include: Step S20, which involves sending metal powder injection molding process instructions through the molding control system, includes: Basic molding parameter instructions: specify core parameters such as injection pressure 50-200MPa, injection speed 5-50mm / s, molding temperature 150-400℃, holding time 10-60s and cooling time 30-120s, and match initial parameters according to the characteristics of metal powder materials, such as stainless steel powder and titanium alloy powder. Quartz tube sensor detection parameter instructions: Set the detection frequency 100-1000Hz, detection accuracy threshold (filling progress error ±1%, speed error ±0.5mm / s), detection data transmission delay upper limit (≤10ms), and specify the detection area and data acquisition priority of each quartz tube sensor; Defect warning threshold instructions: preset incomplete filling warning threshold, bubble warning threshold and uneven flow warning threshold. The preset incomplete filling warning threshold is 95%, the bubble warning threshold is when the cavity pressure fluctuation exceeds ±5%, the uneven flow warning threshold is when the flow velocity difference between different areas exceeds 3mm / s, and the corresponding emergency handling level. Priority adjustment instruction: Based on the urgency of production orders and the level of product precision requirements, set the priority weights for molding quality and production efficiency. When parameter adjustment conflicts occur, the decision is made according to the priority weights.

[0025] Step S30: Based on the improved genetic algorithm combined with the quartz tube sensor detection feedback rules, and according to the model information in step S10 and the process parameters analyzed in step S20, plan the metal powder injection path and the real-time detection path of the quartz tube sensor. The injection path includes the melt flow trajectory and the segmented injection pressure distribution scheme, and the detection path includes the quartz tube body detection point sequence and the detection angle adjustment scheme.

[0026] Specifically, step S30, based on the improved genetic algorithm combined with the quartz tube sensor detection feedback rules, includes: Coding method design: Real number coding is adopted, and the segmented pressure and speed parameters of the injection path and the coordinates and detection angles of the quartz tube sensor detection points are used as chromosome genes. Each gene corresponds to the value range of a process parameter or detection parameter. Fitness function construction: Fitness function F = α·F1 + β·F2 + γ·F3, where F1 is the filling uniformity evaluation index, calculated based on melt flow uniformity from finite element simulation, F2 is the detection coverage evaluation index, and F3 is the molding efficiency evaluation index, calculated based on the total injection molding time. F1, F2 and F3 are all percentages, and α, β and γ are weighting coefficients, dynamically adjusted according to the priority instructions in step S20. Genetic operations: The selection operation uses a combination of roulette wheel selection and elite retention strategy, retaining the top 10% of chromosomes in fitness value to directly enter the next generation. The crossover operation uses arithmetic crossover, performing linear combination of corresponding genes on adjacent chromosomes to generate new combinations of process parameters. The mutation operation uses adaptive mutation, adjusting the mutation probability according to the number of generations of population evolution. For example, the initial probability is 0.05, and it decreases by 0.005 every 10 generations to avoid local optima. Quartz tube sensor detection feedback rule setting: When a lag in filling progress is detected, the injection pressure in the corresponding area should be increased first; when the flow rate is detected to be too fast, the local injection speed should be reduced and the detection frequency should be increased; when the field of view is obstructed in the detection area, the detection angle of the quartz tube sensor should be adjusted or a backup detection point should be switched. Path optimization determination: By improving the genetic algorithm for iterative calculation, such as 50-100 iterations, the optimal combination of injection path and detection path is obtained. The path is verified to meet the detection feedback rules of the quartz tube sensor. For the parts that do not meet the rules, the parameters are fine-tuned to form the final execution path.

[0027] Step S40: During the injection molding process, the filling progress, flow rate, cavity pressure and melt uniformity of the metal powder melt are detected in real time by a quartz tube sensor installed at a preset position in the mold. The detection data is compared and analyzed with preset thresholds to predict defects and detect path conflicts. When the detection data exceeds the threshold or there is a potential conflict, the injection pressure, speed and detection parameters of the quartz tube sensor are dynamically adjusted to correct the injection path and detection path.

[0028] Specifically, in step S40, conflict detection includes conflicts between the injection path and the detection field of the quartz tube sensor, and conflicts between the matching of molding parameter adjustment and detection frequency. When uneven filling of metal powder, abnormal melt flow rate, or sudden change in cavity pressure is detected, the fitness function weight of the improved genetic algorithm is adjusted according to the severity of the defect and the priority of the production task, the path is replanned and the molding parameters are updated.

[0029] Specifically, the steps in step S40 for correcting the injection path and the detection path include: Data acquisition: The quartz tube sensor is based on the principle of light reflection and transmission to collect data in real time on the filling height, flow front position, melt refractive index and cavity wall pressure of the molten metal powder inside the cavity. The melt refractive index is used to reflect the uniformity. The data sampling frequency is consistent with the detection frequency set in step S20. Data preprocessing: The collected data is filtered and denoised to remove outliers. The Kalman filter algorithm is used for filtering. The processed data is then matched with the model information from step S10 to determine the potential location of defects. Defect judgment and conflict detection: The pre-processed data is compared with the preset warning threshold. When the filling progress is lower than the threshold, the flow rate fluctuates excessively, or the pressure changes abruptly, it is judged as a potential defect. At the same time, it is detected whether the injection path overlaps with the detection field of the quartz tube sensor and whether parameter adjustment will cause the detection frequency to be mismatched. When the field of view overlaps and the detection frequency is mismatched, it is judged as a conflict. Dynamic correction strategy: When there are minor defects and no conflicts, such as slightly low local filling speed, adjust the injection pressure and speed of the corresponding area. The injection pressure adjustment range is ±5MPa, and the speed adjustment range is ±2mm / s, keeping the detection parameters unchanged. When there are serious defects or conflicts, such as insufficient filling exceeding 5%, re-call the improved genetic algorithm, adjust the fitness function weights, re-plan the injection path and detection path, and update the detection frequency of the quartz tube sensor, improving it by 20%-50%. Correction result feedback: The dynamically corrected parameters and paths are fed back to the molding control system in real time, and the model information in the database is updated synchronously to provide a reference for subsequent molding tasks.

[0030] In addition, such as Figure 2 As shown, in one embodiment of the present invention, a metal powder injection molding control system is provided, the system comprising: Mold-quartz tube sensor coupling modeling module: This module uses 3D laser scanning technology to collect data on the cavity structure of metal powder injection molding molds, the mounting holes of quartz tube sensors, the position of the detection window, and the spatial dimensions of the molding area. It then combines this data with finite element analysis to establish a mold-quartz tube sensor coupling environment model. The model information includes the 3D coordinates of the cavity, the effective detection range of the quartz tube sensor, the relative position of the injection port and the cavity, and the temperature field distribution area of ​​the mold. The model information is then stored in the database of the molding control system. Process instruction sending and parsing module: used to send metal powder injection molding process instructions through the molding control system. The injection molding equipment receives and parses the instructions to obtain control parameters, such as injection pressure, injection speed, molding temperature, holding time, quartz tube sensor detection frequency and detection trigger threshold, etc. The process instructions include basic molding parameter instructions, quartz tube sensor detection parameter instructions, defect early warning threshold instructions and priority adjustment instructions. Path planning module: Based on the improved genetic algorithm combined with the quartz tube sensor detection feedback rules, and according to the model information of the mold-quartz tube sensor coupling modeling module and the process parameters analyzed by the process instruction sending and parsing module, the module plans the metal powder injection path and the real-time detection path of the quartz tube sensor. The injection path includes the melt flow trajectory and the segmented injection pressure distribution scheme, and the detection path includes the quartz tube body detection point sequence and the detection angle adjustment scheme. Real-time detection and dynamic correction module: During the injection molding process, a quartz tube sensor installed at a preset position in the mold is used to detect the filling progress, flow rate, cavity pressure and melt uniformity of the metal powder melt in real time. The detection data is compared and analyzed with preset thresholds to predict defects and detect path conflicts. When the detection data exceeds the threshold or there is a potential conflict, the injection pressure, speed and quartz tube sensor detection parameters are dynamically adjusted to correct the injection path and detection path. In the mold-quartz tube sensor coupled modeling module, finite element analysis is used to simulate the temperature field and stress field distribution of the mold cavity, determine the optimal installation position and detection angle of the quartz tube sensor, and ensure that the detection range covers the key filling area of ​​the cavity. The model information is stored in a three-dimensional array, and the array elements correspond to the coordinates, temperature attributes and detection reachability identifiers of the cavity mesh nodes. In the real-time detection and dynamic correction module, the conflict detection includes conflicts between the injection path and the detection field of the quartz tube sensor, and conflicts between the matching of molding parameter adjustment and detection frequency. When uneven filling of metal powder, abnormal melt flow rate, or sudden change in cavity pressure is detected, the fitness function weight of the improved genetic algorithm is adjusted according to the severity of the defect and the priority of the production task, the path is replanned and the molding parameters are updated.

[0031] This application provides a metal powder injection molding control system, employing a metal powder injection molding control method as described in the above embodiments. This system addresses the technical problems of uneven filling, delayed defect detection, and poor adaptability of process parameters in existing metal powder injection molding processes. Compared to the prior art, the beneficial effects of the metal powder injection molding control system provided in this application are the same as those of the metal powder injection molding control method provided in the above embodiments. Furthermore, other technical features of the metal powder injection molding control system are the same as those disclosed in the methods of the above embodiments, and will not be elaborated upon here.

[0032] This application provides a metal powder injection molding control device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, which are executed by the at least one processor to enable the at least one processor to perform a metal powder injection molding control method as described in Embodiment 1 above.

[0033] like Figure 3 As shown in the illustration, in one embodiment of the present invention, a structural schematic diagram of a metal powder injection molding control device suitable for implementing the embodiments of this application is presented. The metal powder injection molding control device in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 3 The metal powder injection molding control device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0034] Figure 3The illustrated metal powder injection molding control device may include a processor 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a machine-readable storage medium (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the metal powder injection molding control device. The processor 1001, the read-only memory 1002, and the machine-readable storage medium 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image quartz tube sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and a communication unit 1009. Communication unit 1009 allows a metal powder injection molding control device to communicate wirelessly or wiredly with other devices to exchange data. Although a metal powder injection molding control device with various systems is shown in the figure, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems may be implemented alternatively.

[0035] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication unit, or installed from storage device 1003, or installed from read-only memory 1002. When the computer program is executed by processor 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0036] This application provides a metal powder injection molding control device that employs a metal powder injection molding control method described in the above embodiments. This method can solve the technical problems of uneven filling, delayed defect detection, and poor adaptability of process parameters in existing metal powder injection molding processes. Compared with the prior art, the beneficial effects of the metal powder injection molding control device provided in this application are the same as those of the metal powder injection molding control method described in the above embodiments. Furthermore, other technical features of this metal powder injection molding control device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0037] The various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0038] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the metal powder injection molding control method described above.

[0039] The computer program product provided in this application can solve the technical problems of uneven filling, delayed defect detection, and poor adaptability of process parameters in existing metal powder injection molding processes. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the metal powder injection molding control method provided in the above embodiments, and will not be repeated here.

[0040] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for controlling metal powder injection molding, characterized in that, The method includes the following steps: Step S10: Use three-dimensional laser scanning technology to collect data on the cavity structure of the metal powder injection molding mold, the mounting hole position of the quartz tube sensor, the position of the detection window, and the spatial dimensions of the molding area. Combine this with finite element analysis to establish a mold-quartz tube sensor coupling environment model and store the model information in the database of the molding control system. Step S20: The metal powder injection molding process command is sent through the molding control system. The injection molding equipment receives and parses the command to obtain the control parameters. Step S30: Based on the improved genetic algorithm combined with the quartz tube sensor detection feedback rules, and according to the model information in step S10 and the process parameters analyzed in step S20, plan the metal powder injection path and the real-time detection path of the quartz tube sensor. Step S40: During the injection molding process, the filling progress, flow rate, cavity pressure and melt uniformity of the metal powder melt are detected in real time by a quartz tube sensor installed at a preset position in the mold. The detection data and preset thresholds are compared and analyzed to predict defects and detect path conflicts, and to correct the injection path and detection path. In step S10, finite element analysis is used to simulate the temperature field and stress field distribution of the mold cavity and determine the optimal installation position and detection angle of the quartz tube sensor. The model information is stored in a three-dimensional array, and the array elements correspond to the coordinates, temperature attributes and detection accessibility identifiers of the cavity mesh nodes. The quartz tube sensor detection uses the quartz tube sensor as the detection carrier to monitor the filling progress, flow rate, uniformity and cavity pressure parameters of the molten metal powder inside the mold cavity in real time during the metal powder injection molding process. The step S20, which involves sending the metal powder injection molding process command through the molding control system, includes: Basic molding parameter instructions: specify injection pressure, injection speed, molding temperature, holding time, and cooling time, and match initial parameters according to the characteristics of the metal powder material; Quartz tube sensor detection parameter instructions: set the detection frequency, detection accuracy threshold, and upper limit of detection data transmission delay, and clarify the detection area and data acquisition priority of each quartz tube sensor; Defect warning threshold instructions: preset warning thresholds for insufficient filling, air bubbles, and uneven flow, as well as corresponding emergency handling levels; Priority adjustment instruction: Based on the urgency of production orders and the level of product precision requirements, set the priority weights for molding quality and production efficiency. When parameter adjustment conflicts occur, the decision is made according to the priority weights. Step S30, based on the improved genetic algorithm combined with the quartz tube sensor detection feedback rules, includes: Coding method design: Real number coding is adopted, and the segmented pressure and speed parameters of the injection path and the coordinates and detection angles of the quartz tube sensor detection points are used as chromosome genes. Each gene corresponds to the value range of a process parameter or detection parameter. Fitness function construction: Fitness function F = α·F1 + β·F2 + γ·F3, where F1 is the filling uniformity evaluation index, calculated based on melt flow uniformity from finite element simulation, F2 is the detection coverage evaluation index, and F3 is the molding efficiency evaluation index, calculated based on the total injection molding time. F1, F2 and F3 are all percentages, and α, β and γ are weighting coefficients, dynamically adjusted according to the priority instructions in step S20. Genetic operations: The selection operation uses a combination of roulette wheel selection and elite retention strategy, retaining the top 10% of chromosomes in fitness value to directly enter the next generation; the crossover operation uses arithmetic crossover, performing linear combination of corresponding genes on adjacent chromosomes to generate new combinations of process parameters; the mutation operation uses adaptive mutation, adjusting the mutation probability according to the number of generations of population evolution. Quartz tube sensor detection feedback rule settings: When a filling progress lag is detected, the injection pressure in the corresponding area is increased; when the flow rate is detected to be greater than the set threshold, the local injection speed is reduced and the detection frequency is increased.

2. The method for controlling metal powder injection molding according to claim 1, characterized in that, The step S10, which involves using three-dimensional laser scanning technology to acquire data on the cavity structure of the metal powder injection molding die, the mounting holes of the quartz tube sensor, the position of the detection window, and the spatial dimensions of the molding area, includes: Data acquisition: A 3D laser scanner is used to perform a full-size scan of the mold cavity inner wall, quartz tube sensor mounting base, injection channel and vent hole to obtain point cloud data. At the same time, the thermal conductivity coefficient and thermal expansion coefficient of the mold material are collected. Point cloud processing: The collected point cloud data is denoised, registered and meshed to divide the cavity space into a three-dimensional mesh, and each mesh node is assigned a unique three-dimensional coordinate identifier. Finite element simulation: Import the meshed model into the finite element analysis software, set the initial temperature and pressure boundary conditions for injection molding, and simulate the flow path and temperature distribution of the melt in the cavity; Quartz tube sensor detection area calibration: Based on the finite element simulation results and installation position, determine the detection angle of each quartz tube sensor, convert the labeled model information into a machine-readable three-dimensional array, and store it in the molding control system; Model update mechanism: The mold is scanned every 8 hours to update the temperature field and wear status data of the model. When the mold is repaired, the metal powder raw material is replaced, or the molding process is adjusted, an event-driven update is triggered to remodel and calibrate the detection area of ​​the quartz tube sensor.

3. The method for controlling metal powder injection molding according to claim 1, characterized in that, In step S40, the quartz tube sensor includes a quartz tube body, a laser emitting unit, a laser receiving unit, a pressure sensing unit, and a temperature compensation unit. During installation, it is fixed to the mold wall through a sealing seat to ensure that the detection end face is flush with the inner wall of the cavity. Conflict detection includes conflicts between the injection path and the detection field of view of the quartz tube sensor, and conflicts between the matching of molding parameter adjustment and detection frequency. When uneven filling of metal powder, abnormal melt flow rate, or sudden change in cavity pressure is detected, the fitness function weight of the improved genetic algorithm is adjusted according to the severity of the defect and the priority of the production task, the path is replanned, and the molding parameters are updated.

4. The method for controlling metal powder injection molding according to claim 1, characterized in that, The step of correcting the injection path and detection path in step S40 includes: Data acquisition: The quartz tube sensor is based on the principle of light reflection and transmission to collect data in real time on the filling height, flow front position, melt refractive index and cavity wall pressure of the molten metal powder inside the cavity. The melt refractive index is used to reflect the uniformity. The data sampling frequency is consistent with the detection frequency set in step S20. Data preprocessing: The collected data is filtered and denoised to remove outliers. The Kalman filter algorithm is used for filtering. The processed data is then matched with the model information from step S10 to determine the potential location of defects. Defect judgment and conflict detection: The pre-processed data is compared with the preset warning threshold. When the filling progress is lower than the threshold, the flow rate fluctuates excessively, or the pressure changes abruptly, it is judged as a potential defect. At the same time, it is detected whether the injection path overlaps with the detection field of the quartz tube sensor and whether parameter adjustment will cause the detection frequency to be mismatched. When the field of view overlaps and the detection frequency is mismatched, it is judged as a conflict. Dynamic correction strategy: When there is a defect and no conflict, adjust the injection pressure and speed of the corresponding area, keep the detection parameters unchanged, adjust the fitness function weight, replan the injection path and detection path, and update the detection frequency of the quartz tube sensor. Correction result feedback: The dynamically corrected parameters and paths are fed back to the molding control system in real time, and the model information in the database is updated synchronously to provide a reference for subsequent molding tasks.

5. A metal powder injection molding control system, characterized in that, The system executes the metal powder injection molding control method according to claim 1, comprising: Mold-quartz tube sensor coupling modeling module: Used to acquire data on the cavity structure of metal powder injection molding mold, the mounting hole position of quartz tube sensor, the position of detection window and the spatial dimensions of the molding area using 3D laser scanning technology, and to establish a mold-quartz tube sensor coupling environment model by combining finite element analysis, and store the model information in the database of the molding control system; Process instruction sending and parsing module: used to send metal powder injection molding process instructions through the molding control system, and the injection molding equipment receives and parses the instructions to obtain control parameters; Path planning module: Based on the improved genetic algorithm combined with the quartz tube sensor detection feedback rules, and according to the model information of the mold-quartz tube sensor coupling modeling module and the process parameters analyzed by the process instruction sending and parsing module, the module plans the metal powder injection path and the real-time detection path of the quartz tube sensor. Real-time detection and dynamic correction module: During the injection molding process, a quartz tube sensor installed at a preset position on the mold is used to detect the filling progress, flow rate, cavity pressure and melt uniformity of the metal powder melt in real time. The detection data is compared and analyzed with preset thresholds to predict defects and detect path conflicts, and to correct the injection path and detection path.

6. A metal powder injection molding control device, characterized in that, include: A memory, a processor, and a metal powder injection molding control program stored in the memory and executable on the processor, wherein the metal powder injection molding control program, when executed by the processor, implements a metal powder injection molding control method as described in any one of claims 1 to 4.

7. A computer program product, characterized in that, The computer program product includes a metal powder injection molding control program, which, when executed by a processor, implements a metal powder injection molding control method as described in any one of claims 1 to 4.

Images