Injection molding control method and system for automobile plastic parts

Abstract

The invention discloses an injection molding control method and system for automobile plastic parts, and relates to the technical field of automobile parts. Historical data and process parameters of structural parts are collected, a mapping relation is established, temperature and pressure data are collected, a process suggestion model is matched, an optimal injection molding strategy is output, a mold filling state matrix is constructed, and a control signal is output. According to the method, the mapping relation between the structure identification code and the injection molding strategy is established, accurate matching of the structural part and the technological parameters is achieved, temperature and pressure data of the mold filling stage and the pressure filling stage are collected, the mold filling state matrix is constructed in real time, and the pressure filling synchronization time point is recognized, so that the pressure filling precision is improved. And a pressure supplementing path network diagram is constructed in combination with three-dimensional structure modeling data, path efficiency and filling states are analyzed, the main branch pressure supplementing proportion is dynamically adjusted, the intelligent regulation and control capacity in the injection molding process is effectively improved, forming defects are reduced, and the consistency and forming quality of complex structural parts are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of automotive parts, and particularly to an injection molding control method and system for automotive plastic parts. Background Art

[0002] With the development trend of automotive lightweight and complex styling, plastic parts are increasingly widely used in automotive structures, and their injection molding quality has a direct impact on the overall vehicle appearance, assembly accuracy, and functional stability. To improve production efficiency and product consistency, existing injection molding processes are gradually evolving from single-cavity to multi-cavity and multi-region collaborative control directions. Especially in the manufacturing of large-sized or irregular parts such as instrument panels, center console decorative parts, and lamp housing assemblies, multi-cavity injection molding has become the mainstream solution.

[0003] Currently, the Chinese invention patent with the application number CN202410507491.2 discloses a forming optimization method for vehicle decorative parts and a vehicle decorative part. The forming optimization method is used to injection mold a texture layer with a texture effect on the outer surface of the vehicle decorative part. The method includes raising the injection temperature of the injection melt to a preset injection temperature, raising the temperature of the injection mold to a preset mold temperature, and the injection mold has a texture layer; controlling the flow rate of the injection melt at the gate to be below 10%, where 10% represents the percentage of the actual injection speed of the injection molding machine to the maximum injection speed of the injection molding machine; controlling the filling speed of the injection melt in the large surface cavity of the injection mold to be below 20%, where 20% represents the percentage of the actual injection speed of the injection molding machine to the maximum injection speed of the injection molding machine.

[0004] The above technology is difficult to achieve intelligent matching of process strategies based on structural geometric features and real-time adaptive regulation of the compensation pressure path during the injection molding process of multi-cavity complex structural parts, and it is difficult to effectively solve the coexistence problems of uneven mold filling, pressure accumulation, and molding defects. Summary of the Invention

[0005] The technical problem solved by the present invention is that the above technology is difficult to achieve intelligent matching of process strategies based on structural geometric features and real-time adaptive regulation of the compensation pressure path during the injection molding process of multi-cavity complex structural parts, and it is difficult to effectively solve the coexistence problems of uneven mold filling, pressure accumulation, and molding defects.

[0006] To solve the above technical problem, the present invention provides the following technical solutions: An injection molding control method for automotive plastic parts, including the following steps: Step S1, collecting historical data of structural parts and process parameters, and establishing a mapping relationship between structural identification codes and injection molding strategies; Step S2, collecting temperature and pressure data during the mold filling and compensation pressure stages and storing them in a database; Step S3, identify the current structure and match the process recommendation model, and output the optimal injection molding strategy; Step S4, construct a mold filling state matrix, determine the time point of pressure compensation synchronization and output a control signal; Step S5, construct a pressure compensation path network diagram, analyze the path efficiency and filling state, and output the pressure compensation path and flow rate adjustment instructions.

[0007] Preferably, the step S1 includes the following sub-steps: Step S101, collect historical data of structural parts and historical injection molding process parameters. The historical data of structural parts includes external dimension data, wall thickness distribution data, weld line position data, and typical molding defect data. The historical injection molding process parameters include mold filling speed, pressure compensation time, pressure compensation pressure, and cooling time, and label the historical data of structural parts; Step S102, extract the historical structural geometric features from the historical data of structural parts, and based on decision tree regression, analyze the coupling law between the historical structural geometric features and the historical injection molding process parameters, and output it as a process recommendation model. The input data of the process recommendation model is the structural set feature, and the output data is the injection molding strategy; Step S103, construct a structural feature coding rule according to the wall thickness fluctuation value, rib density, geometric symmetry, number of mold cavities, and typical runner layout form in the historical structural geometric features, discretize and encode the features in the historical structural geometric features and combine them into a structural identification code; Step S104, establish a mapping relationship between the structural identification code and the injection molding strategy, and output it as an injection molding strategy mapping library.

[0008] Preferably, the step S2 includes the following sub-steps: Step S201, collect temperature and pressure data, including position data and corresponding mold filling stage temperature data, mold filling stage pressure data, mold filling stage melt front advancement rate, pressure compensation stage temperature data, pressure compensation stage pressure data, and pressure compensation stage melt front advancement rate; Step S202, archive the temperature and pressure data according to the time stamp and store it in the injection molding database.

[0009] Preferably, the step S3 includes the following sub-steps: Step S301, according to step S1, identify the current structural geometric features of the current product and call the corresponding process recommendation model; Step S302, compare the similarity between the temperature and pressure data and the process parameters in the process recommendation model, obtain the optimal mold filling path, pressure compensation area distribution, and temperature control strategy, and output the optimal mold filling path, pressure compensation area distribution, and temperature control strategy as the matching result; Step S303, convert the matching result into an instruction set and transmit it to the control end of the injection molding equipment.

[0010] Preferably, step S4 includes the following sub-steps: Step S401: Obtain the current cavity position, the number of gating ports, and the structural symmetry difference. According to the injection molding strategy associated with the structure identification code, calculate the filling sequence and the expected filling time period for each cavity, and set a differential gating timing, which is input to the control terminal of the injection molding equipment.

[0011] Preferably, step S4 further includes the following sub-steps: Step S402: Collect the temperature data, pressure data, melt front advancement rate, and filling completion index during the filling stage corresponding to the current cavity position, and construct a multi-cavity filling state matrix; The multi-cavity filling state matrix is a two-dimensional matrix, and the mathematical expression of the multi-cavity filling state matrix is: ; Wherein, is an element in the cavity filling state matrix, is the number of cavities, is the monitoring index dimension, and the monitoring indexes include the temperature data, pressure data, melt front advancement rate, and filling completion index during the filling stage corresponding to the current cavity position; Judge the cavity consistency, and the logic for judging the cavity consistency is: Set the threshold vector of the monitoring indexes , , and , the is the threshold vector of the temperature data during the filling stage, the is the threshold vector of the pressure data during the filling stage, the is the threshold vector of the melt front advancement rate during the filling stage, the is the threshold vector of the filling completion index. If the following consistency conditions are met: , , ; Wherein, is the real-time state value of the th cavity at the th item of the process index at the th moment in the multi-cavity filling state matrix, and the real-time state value includes temperature data, pressure data, melt front advancement rate, and filling completion index, is the average value of all cavities of the th process index at the th moment; It is determined that the consistency threshold is reached. When the consistency condition is continuously satisfied for a time longer than the preset shortest determination period, the current time point is obtained and output as the optimal synchronization point; Step S403, set the optimal synchronization point as the pressure boosting action signal output time point, and the optimal synchronization point is used to control the opening synchronization and pressure output rate of multiple pressure boosting channels.

[0012] Preferably, the step S5 includes the following sub-steps: Step S501, based on the three-dimensional cavity structure modeling data, extract the main filling channels, rib position extension areas, and closed corner areas of the three-dimensional cavity structure modeling data and mark them as path control nodes. Collect the real-time mold temperature map and real-time pressure data. Define several logical pressure boosting conduction paths in the three-dimensional cavity structure modeling data, connect the three-dimensional cavity structure modeling data, and form a pressure boosting path network diagram; The nodes of the pressure boosting path network diagram represent the key points of pressure action, and the edges represent the pressure boosting path segments; The pressure boosting path network diagram is constructed as a directed weighted graph model. The edge weight of the directed weighted graph model is the conduction efficiency of the pressure boosting path segment. The initial weight value of the conduction efficiency is calculated by weighting according to the path segment length, the mold temperature state of the path segment, and the current pressure gradient in the area where the path is located. The mathematical expression of the conduction efficiency is: ; Among them, is the conduction efficiency of the pressure boosting path segment to the pressure boosting path segment , is the path segment length of the pressure boosting path segment to the pressure boosting path segment , is the normalized temperature value of the pressure boosting path segment to the pressure boosting path segment , is the current pressure gradient value at both ends of the pressure boosting path segment to the pressure boosting path segment , is the preset empirical adjustment coefficient.

[0013] Preferably, the step S5 further includes the following sub-steps: Step S502, perform conduction efficiency analysis on the logical pressure boosting conduction paths according to the pressure boosting path network diagram, calculate the filling rate of the target area based on the historical filling integrity data, and count the flow resistance index of the path branches. Construct a dynamic sorting algorithm to sort the logical pressure boosting conduction paths by priority, and output the preferred pressure boosting path for the current cycle; The preferred pressure compensation path is the optimal path in the pressure compensation path network diagram. The optimal path is sorted by path priority through a weighted path score function, and the weighted path score function includes the path segment conduction weight and the target filling area integrity data; Step S503: Based on the joint analysis of the real-time pressure data and the actual filling trend of the target area, extract the real-time pressure difference between the path start point and the end point, the real-time filling rate and filling rate of the area corresponding to the path end, the mold temperature of the path segment, and the historical flow resistance score, construct a path conduction efficiency score model, and output the score result. The mathematical expression of the path conduction efficiency score model is: ; Among them, is the path segment score from the pressure compensation path segment to the pressure compensation path segment ; is the real-time filling rate of the end area of the pressure compensation path segment to the pressure compensation path segment ; is the filling rate of the pressure compensation path segment to the pressure compensation path segment ; is the historical flow resistance score of the pressure compensation path segment to the pressure compensation path segment ; , and are the preset ideal real-time filling rate, ideal filling rate, and ideal historical flow resistance score respectively; Update the edge weights in the pressure compensation path network diagram according to the score result. The mathematical expression of the edge weight update rule is: ; Among them, is the updated edge weight at the time of the pressure compensation path segment from to the pressure compensation path segment ; is the edge weight at the time of the pressure compensation path segment from to the pressure compensation path segment ; is the preset weight adjustment factor; is the path segment score at the time of the pressure compensation path segment from to the pressure compensation path segment ; is the average path segment score value of all path segment scores; Identify the path segments with bias pressure or material flow accumulation, and output the pressure compensation flow ratio adjustment signal of the main branch path.

[0014] Preferably, the pressure compensation preferred path is a self-learning dynamic graph structure.

[0015] An injection molding control system for automotive plastic parts, which is applied to the injection molding control method of the above-mentioned automotive plastic parts, includes a strategy establishment module, a data acquisition module, a model recognition module, a control signal module, and an adjustment setting module; The strategy establishment module is used to collect historical data of structural parts and process parameters, and establish a mapping relationship between structural identification codes and injection molding strategies; The data acquisition module is used to collect temperature and pressure data in the mold filling and pressure compensation stages and store them in a database; The model recognition module is used to identify the current structure and match the process recommendation model, and output the optimal injection molding strategy; The control signal module is used to construct a mold filling state matrix, determine the pressure compensation synchronization time point and output a control signal; The adjustment setting module is used to construct a pressure compensation path network diagram, analyze the path efficiency and filling state, and output a pressure compensation path and flow rate adjustment instruction.

[0016] Advantages of the present invention: By establishing a mapping relationship between structural identification codes and injection molding strategies, the present invention realizes the precise matching of structural parts and process parameters. By collecting temperature and pressure data in the mold filling and pressure compensation stages, a mold filling state matrix is constructed in real time, the pressure compensation synchronization time point is identified, and a pressure compensation path network diagram is constructed in combination with three-dimensional structure modeling data. The path efficiency and filling state are analyzed, and the pressure compensation ratio of the main branch is dynamically adjusted, effectively improving the intelligent control ability of the injection molding process, reducing molding defects, and improving the consistency and molding quality of complex structural parts. Description of the Drawings

[0017] Figure 1 It is a step flow chart of an injection molding control method for automotive plastic parts provided by an embodiment of the present invention; Figure 2 It is a basic process schematic diagram of an injection molding control system for automotive plastic parts provided by an embodiment of the present invention. Detailed Embodiments

[0018] In order to make the above objects, features, and advantages of the present invention more obvious and understandable, the following detailed description of the specific embodiments of the present invention is made in conjunction with the drawings of the specification. Obviously, the described embodiments are some embodiments of the present invention, rather than all embodiments.

[0019] Embodiment 1, referring to Figure 1 , provides an injection molding control method for automotive plastic parts, including the following steps: Step S1: Collect historical data of structural components and process parameters, and establish a mapping relationship between structure identification codes and injection strategies.

[0020] Step S2: Collect temperature and pressure data during the mold filling and pressure compensation stages and store them in the database.

[0021] Step S3: Identify the current structure and match the process recommendation model, and output the optimal injection strategy.

[0022] Step S4: Construct a mold filling state matrix, determine the pressure compensation synchronization time point and output a control signal.

[0023] Step S5: Construct a pressure compensation path network diagram, analyze the path efficiency and filling state, and output the pressure compensation path and flow rate adjustment instructions.

[0024] Step S1 includes the following sub-steps: Step S101: Collect historical data of structural components and historical injection process parameters. The historical data of structural components includes external dimension data, wall thickness distribution data, weld line position data, and typical molding defect data. The historical injection process parameters include mold filling speed, pressure compensation time, pressure compensation pressure, and cooling time. Tag the historical data of structural components.

[0025] Through collecting historical data of structural components including external dimensions, wall thickness distribution, weld line position, and typical molding defects, and supporting the collection of historical process parameters, and combining with the tagging method, Step S101 standardizes the structural features, providing data guarantee for subsequent structural feature modeling.

[0026] Step S102: Extract historical structural geometric features from the historical data of structural components, and based on decision tree regression, analyze the coupling law between historical structural geometric features and historical injection process parameters, and output it as a process recommendation model. The input data of the process recommendation model is the structural set feature, and the output data is the injection strategy.

[0027] Based on the tagged historical structural data, Step S102 extracts structural geometric features, and uses the decision tree regression algorithm to establish a coupling model between them and process parameters, and outputs a process recommendation model, enabling the system to predict the appropriate injection strategy based on the structural input and realizing effective reasoning from structure to process.

[0028] Step S103: Based on the wall thickness fluctuation value, rib density, geometric symmetry, number of mold cavities, and typical runner layout form in the historical structural geometric features, construct a structural feature coding rule, discretize and encode the features in the historical structural geometric features and combine them into a structure identification code.

[0029] Step S103 discretizes the wall thickness fluctuation value, rib density, geometric symmetry, number of mold cavities, and typical runner layout forms, constructs a structural feature coding rule, and combines them to form a structure identification code, realizing the digital expression of structural differences for quick indexing and matching.

[0030] In step S104, a mapping relationship is established between the structure identification code and the injection molding strategy, and the output is the injection molding strategy mapping library.

[0031] Step S104 maps the structure identification code one by one with the injection molding strategies output by the process recommendation model, establishes an injection molding strategy mapping library, provides a basis for automatically recommending matching injection molding process parameters for different structure types, and improves the intelligence and versatility of the injection molding control system.

[0032] In step S1, historical data of structural parts and injection molding process parameters are collected, structural geometric features are extracted, a structure identification code is constructed, and a mapping relationship is established between it and the injection molding strategy, forming a structure identification code - injection molding strategy mapping library, realizing the precise matching between different structure types and molding strategies, and providing a data basis and decision-making basis for subsequent process parameter recommendation and intelligent control.

[0033] Step S2 includes the following sub-steps: In step S201, temperature and pressure data are collected. The temperature and pressure data include position data and corresponding temperature data in the filling stage, pressure data in the filling stage, melt front advancement rate in the filling stage, temperature data in the pressure holding stage, pressure data in the pressure holding stage, and melt front advancement rate in the pressure holding stage.

[0034] In step S201, temperature and pressure data including position data, temperature data in the filling stage, pressure data in the filling stage, melt front advancement rate in the filling stage, temperature data in the pressure holding stage, pressure data in the pressure holding stage, and melt front advancement rate in the pressure holding stage are collected in real time at each key position in the mold cavity, comprehensively recording the characteristics of melt flow and thermal changes during the molding process, and realizing the real-time acquisition of multi-dimensional process data.

[0035] In step S202, the temperature and pressure data are archived according to the time stamp and stored in the injection molding database.

[0036] In step S202, the collected temperature and pressure data are archived according to the time stamp and stored in the injection molding database to ensure that each data item has time relevance, constructing a complete and traceable time-series temperature and pressure data set, and providing high-precision basic data for subsequent state matrix construction, path adjustment calculation, and process optimization decision-making.

[0037] Step S2 constructs a multi-dimensional dynamic process dataset by collecting temperature and pressure data during the mold filling and packing stages, archiving them according to timestamps, and storing them in the injection molding database, realizing real-time working condition monitoring and accurate recording of key stages in the injection molding process, providing data support for subsequent process matching analysis, mold filling state judgment, and path optimization.

[0038] Step S3 includes the following sub-steps: Step S301, based on the current structural geometric features of the current product identified in Step S1, calls the corresponding process recommendation model.

[0039] Step S301 realizes rapid matching between the structure and the process by identifying the structural geometric features of the current product and calling the process recommendation model established in Step S1, ensuring a high degree of adaptation between the injection molding control strategy and the structural characteristics.

[0040] Step S302 compares the temperature and pressure data with the process parameters in the process recommendation model to obtain the optimal mold filling path, packing area distribution, and temperature control strategy, and outputs the optimal mold filling path, packing area distribution, and temperature control strategy as the matching result.

[0041] Step S302 compares the real-time collected temperature and pressure data with the historical injection molding parameters in the process recommendation model, comprehensively judges the current molding state, outputs the optimal mold filling path, packing area distribution, and temperature control strategy, and realizes intelligent injection molding process matching and adjustment based on the current working conditions.

[0042] Step S303 converts the matching result into an instruction set and transmits it to the control end of the injection molding equipment.

[0043] Step S303 formats the optimal mold filling path, packing area distribution, and temperature control strategy in the matching result, converts them into a data instruction set adapted to the injection molding equipment, and sends it to the control end to realize the automatic regulation of the injection molding equipment, improving the accuracy and response efficiency of the injection molding process execution.

[0044] Step S3 realizes structure-driven personalized process matching and intelligent injection molding process control by identifying the current structural geometric features, calling the process recommendation model, comparing the real-time temperature and pressure data with the historical process parameters, obtaining the optimal injection molding control strategy, and converting it into a control instruction and outputting it to the injection molding equipment.

[0045] Step S4 includes the following sub-steps: Step S401 obtains the current cavity position, the number of gating points, and the structural symmetry difference, calculates the filling sequence and expected filling time period of each cavity according to the injection molding strategy associated with the structure identification code, and sets the differential gating timing, and inputs it to the control end of the injection molding equipment.

[0046] Step S401 calculates the filling sequence and expected filling time period for each cavity by obtaining information such as the current cavity position, the number of injection gates, and the structural symmetry difference, and combines the injection molding strategy associated with the structure identification code. It sets a differential injection timing to achieve orderly control of the filling process of each cavity, and inputs the control strategy into the injection molding equipment to ensure the asynchronous filling accuracy and execution efficiency.

[0047] In step S402, the temperature data, pressure data, melt front advancement rate, and filling completion index corresponding to the current cavity position during the filling stage are collected to construct a multi-cavity filling state matrix.

[0048] The multi-cavity filling state matrix is a two-dimensional matrix, and its mathematical expression is: ; where is an element in the cavity filling state matrix, is the number of cavities, is the monitoring index dimension, and the monitoring indexes include the temperature data, pressure data, melt front advancement rate, and filling completion index corresponding to the current cavity position.

[0049] Judge the cavity consistency. The logic for judging the cavity consistency is as follows: Set the threshold vector , , and , is the threshold vector of the temperature data during the filling stage, is the threshold vector of the pressure data during the filling stage, is the threshold vector of the melt front advancement rate during the filling stage, is the threshold vector of the filling completion index. If the following consistency conditions are met: , , ; where is the real-time state value of the th cavity at the th time under the th process index in the multi-cavity filling state matrix. The real-time state value includes temperature data, pressure data, melt front advancement rate, and filling completion index, is the average value of all cavities of the th process index at the th time.

[0050] It is determined that the consistency threshold is reached. When the consistency condition is continuously satisfied for a time longer than the preset shortest determination period, the current time point is obtained and output as the optimal synchronization point.

[0051] In step S402, by collecting the temperature data, pressure data, melt front advancement rate, and filling completion index corresponding to the current cavity position, a multi-cavity filling state matrix is constructed. The system determines the filling synchronization state of each cavity based on whether each index reaches the set consistency threshold, thereby accurately determining whether the pressure compensation start condition is met, and ensuring that each cavity is in the optimal synchronization state when the pressure compensation starts.

[0052] In step S403, the optimal synchronization point is set as the output time point of the pressure compensation action signal. The optimal synchronization point is used to control the opening synchronization and pressure output rate of multiple pressure compensation channels.

[0053] Step S403 uses the optimal synchronization point identified in step S402 as the control trigger signal for the pressure compensation action, controls the simultaneous opening of multiple pressure compensation channels and the coordination of the pressure output rate, enables each cavity to enter the pressure compensation stage at the same moment, improves the synchronization and molding balance of the pressure holding process, and reduces warping, air marks, or dimensional deviation caused by pressure differences.

[0054] In step S4, by determining the filling sequence and gate timing based on the structure identification code and cavity characteristics, collecting the cavity filling state data in real time and constructing a filling state matrix, identifying the optimal synchronization time point when the pressure compensation preparation is completed, and outputting a pressure compensation control signal, the coordinated control of multi-cavity asynchronous filling and synchronous pressure compensation is realized, effectively improving the filling uniformity and molding accuracy.

[0055] Step S5 includes the following sub-steps: In step S501, based on the 3D structure modeling data of the cavity, the main filling channels, rib extension areas, and closed corner areas of the 3D structure modeling data of the cavity are extracted and marked as path control nodes. The real-time mold temperature map and real-time pressure data are collected, and several logical pressure compensation conduction paths are defined in the 3D structure modeling data of the cavity, and the 3D structure modeling data of the cavity is connected to form a pressure compensation path network diagram.

[0056] The pressure compensation path network diagram is constructed as a directed weighted graph model. The edge weight of the directed weighted graph model is the conduction efficiency of the pressure compensation path segment. The initial weight value of the conduction efficiency is calculated by weighting according to the path segment length, the mold temperature state of the path segment, and the current pressure gradient in the area where the path is located. The mathematical expression of the conduction efficiency is: ; Among them, is the conduction efficiency of the pressure compensation path segment to the pressure compensation path segment , is the pressure compensation path segment to the pressure compensation path segment the path segment length is the pressure compensation path segment to the pressure compensation path segment the normalized temperature value is the pressure compensation path segment to the pressure compensation path segment the current pressure gradient values at both ends is the preset empirical adjustment coefficient

[0057] The nodes of the pressure compensation path network diagram represent the key points of pressure action, and the edges represent the pressure compensation path segments

[0058] In step S501, by analyzing the three-dimensional structure modeling data of the mold cavity, the main filling channels, rib position extension areas, and closed corner areas are extracted as path control nodes. Combining the real-time mold temperature diagram and real-time pressure data, several logical pressure compensation conduction paths are established in the geometric structure, and a pressure compensation path network diagram with nodes representing pressure key points and edges representing pressure compensation path segments is constructed, providing a structural basis for subsequent pressure compensation path optimization and dynamic adjustment

[0059] Step S502. In step S502, the conduction efficiency of the logical pressure compensation conduction paths is analyzed according to the pressure compensation path network diagram. Based on the historical filling integrity data, the filling rate of the target area is calculated, and the flow resistance indexes of the path branches are statistically analyzed. A dynamic sorting algorithm is constructed to sort the priorities of the logical pressure compensation conduction paths, and the optimal pressure compensation path for the current cycle is output

[0060] The optimal pressure compensation path is the optimal path in the pressure compensation path network diagram. The optimal path is sorted by the weighted path score function, and the weighted path score function includes the path segment conduction weight and the integrity data of the target filling area

[0061] In step S502, the conduction efficiency of each logical path in the pressure compensation path network diagram is evaluated. Weighted calculations are performed in combination with the path segment length, mold temperature state, and local pressure gradient. At the same time, the filling rate of the target area is calculated according to the historical filling integrity data, and the flow resistance indexes are statistically analyzed. The dynamic sorting algorithm is used to sort the path priorities, and the optimal pressure compensation path for the current cycle is output, improving the accuracy and responsiveness of path selection

[0062] Step S503. Based on the joint analysis of the real-time pressure data and the actual filling trend of the target area, the real-time pressure difference between the start and end points of the path, the real-time filling rate and filling rate of the area corresponding to the end of the path, the mold temperature of the path segment, and the historical flow resistance score are extracted to construct a path conduction efficiency score model and output the score result. The mathematical expression of the path conduction efficiency score model is ; Where is the supplementary pressure path segment to the supplementary pressure path segment of the path segment score is the supplementary pressure path segment to the supplementary pressure path segment of the real-time filling rate of the end region is the supplementary pressure path segment to the supplementary pressure path segment of the filling rate is the supplementary pressure path segment to the supplementary pressure path segment of the historical flow resistance score , and are respectively the preset ideal real-time filling rate, ideal filling rate and ideal historical flow resistance score

[0063] Update the edge weights in the supplementary pressure path network diagram according to the score results. The mathematical expression of the edge weight update rule is ; where is the updated edge weight at the time of the supplementary pressure path segment to the supplementary pressure path segment is the edge weight at the time of the supplementary pressure path segment to the supplementary pressure path segment is the preset weight adjustment factor is the supplementary pressure path segment to the supplementary pressure path segment is the average path segment score value of all path segment scores

[0064] In the mathematical expression of the edge weight update rule represents the deviation degree of the current path compared with the average level. It is a relative deviation ratio. Here, the reason for multiplying by is that the conduction efficiency of the injection molding supplementary pressure path, that is, the edge weight, is itself a relative concept. Using multiplication can make the weight increase or decay exponentially, which is suitable for simulating the inertia or flow resistance effect in continuous path flow. Multiplication keeps the weight positive, and in the path selection algorithm, multiplication more naturally expresses the change of the path quality makes the weight dynamically adjusted according to the actual performance, that is when, the weight rises, indicating that the supplementary pressure path segment is more important when, the weight drops, indicating that the supplementary pressure path segment is less likely to be selected​​​​ When there is no change in the weight, this update formula fine-tunes the edge weight periodically by multiplying the relative deviation ratio by the adjustment amplitude, achieving dynamic adaptive control of the path priority. Multiplication is used because it is more stable, physically reasonable, always positive in sign, and suitable for describing the enhancement or suppression process of the path channel efficiency in injection molding.

[0065] Identify the path segments where bias voltage or material flow accumulation occurs, and output the proportional adjustment signal of the compensation pressure flow rate for the main branch path.

[0066] The preferred compensation pressure path is a self-learning dynamic graph structure.

[0067] Step S503, based on the real-time pressure data and the actual filling trend of the target area, jointly extracts the pressure difference between the start and end points of the path, the filling rate and filling speed at the end of the path, the mold temperature of the path segment and the historical flow resistance score, constructs a path conduction efficiency score model, and dynamically updates the weights of each edge in the network graph according to the model score results, identifies the path segments where bias voltage or accumulation occurs, outputs the proportional adjustment signal of the compensation pressure flow rate for the main branch path, realizes the adaptive adjustment and closed-loop control of the compensation pressure process, and improves the intelligence and stability of the system.

[0068] Step S5 constructs a compensation pressure path network graph based on the three-dimensional structure modeling data of the mold cavity, combines the real-time mold temperature graph and pressure data, analyzes the conduction efficiency of the compensation pressure path and the regional filling state, dynamically outputs the preferred compensation pressure path, and adjusts the weights of the edges in the path network based on real-time feedback, realizing intelligent flow distribution and path adaptive control in the compensation pressure stage, and significantly improving the filling integrity and pressure balance of complex structural parts.

[0069] Example 2, referring to Figure 2 , provides an injection molding control system for automotive plastic parts, including a strategy establishment module, a data acquisition module, a model recognition module, a control signal module, and an adjustment setting module.

[0070] The strategy establishment module is used to collect the historical data and process parameters of the structural parts, and establish the mapping relationship between the structure identification code and the injection molding strategy.

[0071] The data acquisition module is used to collect the temperature and pressure data in the mold filling and compensation pressure stages and store them in the database.

[0072] The model recognition module is used to identify the current structure and match the process recommendation model, and output the optimal injection molding strategy.

[0073] The control signal module is used to construct a mold filling state matrix, determine the compensation pressure synchronization time point and output a control signal.

[0074] The adjustment setting module is used to construct a compensation pressure path network graph, analyze the path efficiency and filling state, and output the compensation pressure path and flow rate adjustment instructions.

[0075] By collecting the historical data of structural components and injection molding process parameters, a coupling relationship between structural geometric features and injection molding strategies is established based on decision tree regression, forming a mapping library of structural identification codes and injection molding strategies, achieving precise process recommendation for different structural features, significantly reducing the number of mold adjustments and the manual trial-and-error process. By collecting multi-dimensional temperature and pressure data in the filling and pressure compensation stages, a multi-cavity filling state matrix is constructed, which can monitor the filling state of each area and the melt propulsion characteristics in real time, realizing the dynamic tracking of the entire molding process. Based on the temperature and pressure data and the melt front propagation rate collected in the filling stage, the optimal time point for multiple cavities to enter the pressure compensation stage simultaneously is accurately judged to ensure the synchronous release of pressure and prevent structural stress concentration and warpage defects caused by inconsistent pressure between cavities. By constructing a pressure compensation path network diagram based on the three-dimensional structural modeling data and real-time temperature and pressure data of the mold cavity, and conducting weighted analysis on the conduction efficiency of path segments, combining the filling rate and flow resistance score to calculate the path priority, the optimal deployment of multi-path pressure compensation control for complex structural parts is realized. By dynamically updating the edge weights of the pressure compensation path network diagram through the path conduction efficiency score model, identifying the biased pressure or accumulation areas, and outputting the main branch path flow adjustment signal, the closed-loop adjustment and adaptive flow control in the pressure compensation stage are realized. By precisely controlling the filling sequence, synchronous pressure compensation rhythm and path adjustment ratio, problems caused by uneven flow, pressure imbalance or inconsistent cooling are effectively suppressed, and the molding quality and dimensional stability of products are improved. The constructed structural identification code - injection molding strategy mapping library and self-learning pressure compensation path network have the ability of continuous expansion and adaptability, are suitable for intelligent injection molding control of various types and complex-structured plastic parts, and are convenient to be integrated into industrial control to realize intelligent manufacturing.

[0076] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code. Among them, the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. These computer program instructions can also be stored in a computer-readable memory capable of guiding a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured article including an instruction device, and the instruction device implements the functions specified in Figure 1 one process or a plurality of processes and / or Figure 1 boxes or a plurality of boxes.

[0077] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

Claims

1. An injection molding control method for automotive plastic parts, characterized in that, It includes the following steps: Step S1: Collect historical data of structural parts and process parameters, and establish a mapping relationship between structural identification codes and injection molding strategies; Step S2: Collect temperature and pressure data during the mold filling and pressure compensation stages and store them in a database; Step S3: Identify the current structure and match the process recommendation model, and output the optimal injection molding strategy; Step S4: Construct a mold filling state matrix, determine the pressure compensation synchronization time point and output a control signal; Step S5: Construct a pressure compensation path network diagram, analyze the path efficiency and filling state, and output the pressure compensation path and flow rate adjustment instructions.

2. The injection molding control method for an automotive plastic part as claimed in claim 1, wherein The said Step S1 includes the following sub-steps: Step S101: Collect historical data of structural parts and historical injection molding process parameters. The historical data of structural parts includes external dimension data, wall thickness distribution data, weld line position data and typical molding defect data. The historical injection molding process parameters include mold filling speed, pressure compensation time, pressure compensation pressure and cooling time, and perform tagging and marking on the historical data of structural parts; Step S102: Extract the historical structural geometric features from the historical data of structural parts, and based on decision tree regression, analyze the coupling law between the historical structural geometric features and the historical injection molding process parameters, and output it as a process recommendation model. The input data of the process recommendation model is the structural set features, and the output data is the injection molding strategy; Step S103: Construct a structural feature coding rule according to the wall thickness fluctuation value, rib density, geometric symmetry, number of mold cavities and typical runner layout form in the historical structural geometric features, discretize and encode the features in the historical structural geometric features and combine them into a structural identification code; Step S104: Establish a mapping relationship between the structural identification code and the injection molding strategy, and output it as an injection molding strategy mapping library.

3. The injection molding control method for an automotive plastic part as described in claim 2, characterized in that, The said Step S2 includes the following sub-steps: Step S201: Collect temperature and pressure data. The temperature and pressure data includes position data and corresponding mold filling stage temperature data, mold filling stage pressure data, mold filling stage melt front advance rate, pressure compensation stage temperature data, pressure compensation stage pressure data and pressure compensation stage melt front advance rate; Step S202: Archive the temperature and pressure data according to the time stamp and store it in the injection molding database.

4. The injection molding control method for an automotive plastic part according to claim 3, wherein The said Step S3 includes the following sub-steps: Step S301: According to Step S1, identify the current structural geometric features of the current product and call the corresponding process recommendation model; Step S302: Compare the similarity between the temperature and pressure data and the process parameters in the process recommendation model, obtain the optimal mold filling path, pressure compensation area distribution and temperature control strategy, and output the optimal mold filling path, pressure compensation area distribution and temperature control strategy as the matching result; Step S303: Convert the matching result into an instruction set and transmit it to the control end of the injection molding equipment.

5. The injection molding control method for an automotive plastic part according to claim 4, characterized in that, The said Step S4 includes the following sub-steps: Step S401: Obtain the current mold cavity position, number of gate openings and structural symmetry difference, calculate the filling sequence and expected filling time period of each cavity according to the injection molding strategy associated with the structural identification code, and set a differentiated gate opening timing sequence, and input it to the control end of the injection molding equipment.

6. The injection molding control method for an automotive plastic part as described in claim 5, characterized in that, The said Step S4 also includes the following sub-steps: Step S402: Collect the temperature data, pressure data, melt front advancement rate, and filling completion index corresponding to the current cavity position during the filling stage, and construct a multi-cavity filling state matrix. The multi-cavity filling state matrix is a two-dimensional matrix, and the mathematical expression of the multi-cavity filling state matrix is: ； Among them, is an element in the cavity filling state matrix, is the number of mold cavities, is the monitoring index dimension, and the monitoring indexes include the temperature data at the filling stage corresponding to the current mold cavity position, the pressure data at the filling stage, the melt front advancing rate at the filling stage, and the filling completion index; Judge the cavity consistency. The logic for judging the cavity consistency is: Set the threshold vector of the monitoring index , , and , where the is the threshold vector of the temperature data in the mold filling stage, the is the threshold vector of the pressure data in the mold filling stage, the is the threshold vector of the melt front advancement rate in the mold filling stage, and the is the threshold vector of the mold filling completion index. If the following consistency conditions are met: ， ， ； Among them, is the real-time status value of the th cavity at the th moment under the th process index. The real-time status value includes temperature data, pressure data, melt front advancement rate, and mold filling completion index. is the th moment of the average value of all mold cavities of the th process index; If it is determined to reach the consistency threshold, when the consistency condition is continuously satisfied for a time greater than the preset shortest judgment period, obtain the current time point and output it as the optimal synchronization point. Step S403: Set the optimal synchronization point as the output time point of the pressure compensation action signal. The optimal synchronization point is used to control the opening synchronization and pressure output rate of multiple pressure compensation channels.

7. The injection molding control method for an automotive plastic part according to claim 6, wherein, The step S5 includes the following sub-steps: Step S501: Based on the 3D cavity structure modeling data, extract the main filling channels, rib extension areas, and closed corner areas of the 3D cavity structure modeling data and mark them as path control nodes. Collect the real-time mold temperature map and real-time pressure data. Define several logical pressure compensation conduction paths in the 3D cavity structure modeling data, connect the 3D cavity structure modeling data, and form a pressure compensation path network diagram. The nodes of the pressure compensation path network diagram represent the key points of pressure action, and the edges represent the pressure compensation path segments. The pressure compensation path network diagram is constructed as a directed weighted graph model. The edge weight of the directed weighted graph model is the conduction efficiency of the pressure compensation path segment. The initial weight value of the conduction efficiency is calculated by weighting according to the path segment length, the mold temperature state of the path segment, and the current pressure gradient in the area where the path is located. The mathematical expression of the conduction efficiency is: ； Among them, is the conduction efficiency of the pressure compensation path segment to the pressure compensation path segment ; is the path segment length of the pressure compensation path segment to the pressure compensation path segment ; is the normalized temperature value of the pressure compensation path segment to the pressure compensation path segment ; is the current pressure gradient value at both ends of the pressure compensation path segment to the pressure compensation path segment ; is a preset empirical adjustment coefficient.

8. The injection molding control method for an automotive plastic part according to claim 7, characterized in that The step S5 also includes the following sub-steps: Step S502: Analyze the conduction efficiency of the logical pressure compensation conduction paths according to the pressure compensation path network diagram. Calculate the filling rate of the target area based on the historical filling integrity data, and count the flow resistance index of the path branches. Construct a dynamic sorting algorithm to sort the logical pressure compensation conduction paths by priority, and output the pressure compensation preferred path for the current cycle. The pressure compensation preferred path is the optimal path in the pressure compensation path network diagram. The optimal path is sorted by path priority through a weighted path score function. The weighted path score function includes the conduction weight of the path segment and the integrity data of the target filling area. Step S503: Conduct a joint analysis based on the real-time pressure data and the actual filling trend of the target area. Extract the real-time pressure difference between the start and end points of the path, the real-time filling rate and filling rate of the area corresponding to the end of the path, the mold temperature of the path segment, and the historical flow resistance score. Construct a path conduction efficiency score model and output the score result. The mathematical expression of the path conduction efficiency score model is: ； Among them, is the path segment score of the pressure compensation path segment to the pressure compensation path segment ; is the real-time filling rate of the end area of the pressure compensation path segment to the pressure compensation path segment ; is the filling rate of the pressure compensation path segment to the pressure compensation path segment ; is the historical flow resistance score of the pressure compensation path segment to the pressure compensation path segment ; , and are respectively the preset ideal real-time filling rate, ideal filling rate and ideal historical flow resistance score; Update the edge weight in the pressure compensation path network diagram according to the score result. The mathematical expression of the edge weight update rule is: ； Among them, is the supplementary pressure path segment to the supplementary pressure path segment at the time to update the subsequent weight, is the supplementary pressure path segment to the supplementary pressure path segment at the time of the edge weight, is the preset weight adjustment factor, is the supplementary pressure path segment to the supplementary pressure path segment at the time of the path segment score, is the average path segment score value of all path segment scores; Identify the path segments with bias pressure or material flow accumulation, and output the pressure compensation flow ratio adjustment signal for the main branch path.

9. The injection molding control method for an automotive plastic part according to claim 8, wherein The pressure compensation preferred path is a self-learning dynamic graph structure.

10. An injection molding control system for automotive plastic parts, which is applied to an injection molding control method for an automotive plastic part as described in any one of claims 1-9, characterized in that, It includes a strategy establishment module, a data collection module, a model identification module, a control signal module, and an adjustment setting module. The strategy establishment module is used to collect the historical data of structural parts and process parameters, and establish the mapping relationship between the structure identification code and the injection molding strategy; The data acquisition module is used to collect the temperature and pressure data in the mold filling and pressure compensation stages and store them in the database; The model identification module is used to identify the current structure and match the process suggestion model, and output the optimal injection molding strategy; The control signal module is used to construct a mold filling state matrix, determine the pressure compensation synchronization time point and output a control signal; The adjustment setting module is used to construct a pressure compensation path network diagram, analyze the path efficiency and filling state, and output the pressure compensation path and flow rate adjustment instructions.

Images