Intelligent setting method for mold clamping force of injection molding machine

Abstract

The invention relates to the field of data processing, in particular to an intelligent setting method for mold clamping force of an injection molding machine, which comprises the following steps: acquiring and preprocessing pressure and temperature data of each region of a mold cavity of a mold, constructing a pressure sequence and a temperature sequence of each region according to the sequence of acquisition time, and forming a feature sequence of the region; dividing the feature sequence into a first time period and a second time period according to the working process of injection molding, and calculating a target similarity between any two regions according to the feature sequence of the same time period and the calculated feature weight of the same time period; calculating according to the target similarity, the second time period pressure sequence and the mold projection area to obtain a mold locking force predicted value; and before the next injection molding production, multiplying the predicted mold clamping force by a preset safety coefficient to obtain an actual mold clamping force, and completing intelligent setting based on the actual mold clamping force. By means of the intelligent setting method, the mold clamping force can be more reasonable, and therefore product defects are reduced.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and more particularly to an intelligent setting method for the clamping force of an injection molding machine. Background Art

[0002] Clamping force refers to the force used by an injection molding machine to tightly lock the two halves of the mold during production, preventing the high pressure generated by the molten plastic during injection from pushing the mold apart. During the injection molding process, the molten plastic generates significant pressure after being injected into the mold cavity. If the clamping force is insufficient, the mold may be pushed apart, resulting in quality issues such as flash and dimensional instability. Therefore, intelligent clamping force setting is necessary to ensure production safety and product quality during injection molding.

[0003] Moldflow is a software used to simulate the plastic injection molding process. It can predict the flow of plastic melt in the mold, including pressure distribution. However, when using Moldflow to predict the clamping force, the existing technology usually uses the global average pressure from the time of holding pressure to the completion of injection molding. This ignores the uneven pressure distribution in different areas of the mold and the complexity of the mold's force structure, resulting in inaccurate predicted clamping force. In turn, there is a deviation in the clamping force applied to the next injection cycle, affecting the stability of injection molding production and product quality. Summary of the Invention

[0004] In order to solve the above-mentioned technical problem of inaccurate predicted clamping force, the present invention provides the following technical solution.

[0005] An intelligent setting method for the clamping force of an injection molding machine, comprising: The mold cavity is divided into multiple regions, and the pressure and temperature data of each region at each time are collected and preprocessed. Based on a single region, a pressure sequence and a temperature sequence of the region are constructed according to the order of collection time. The pressure sequence and temperature sequence constitute the characteristic sequence of the region; The feature sequence is divided into a first period and a second period according to the injection molding process. The target similarity between any two regions is calculated based on the feature sequence of the same period and the calculated feature weight of the same period. The target similarity is used to evaluate the similarity of feature distribution of the two regions during the entire injection molding process. The clamping force prediction value is calculated based on the target similarity, the pressure sequence in the second period, and the mold projection area; Before the next injection molding production, the predicted clamping force is multiplied by the preset safety factor to obtain the actual clamping force, and intelligent setting is completed based on the actual clamping force.

[0006] Preferably, collecting the pressure and temperature data of each area at each time includes: The mold is divided into equal areas according to the area of the mold parting surface, and a pressure sensor is set at the center of each divided area to collect the pressure data in the mold cavity; Infrared sensors are used synchronously to collect temperature data on the mold surface. For an area, at a certain moment, the temperature values of all positions in the area are averaged to obtain the temperature value of the area at that moment.

[0007] Preferably, the first period is from injection filling to the start of pressure holding, and the second period is from pressure holding to the end of filling.

[0008] Preferably, the process of acquiring the feature weights includes: For a period, the discrimination of the pressure series and the discrimination of the temperature series in the corresponding period are calculated based on the Manhattan distance between the characteristic sequences of all regions in the same period. According to the discrimination degree of the pressure sequence and the discrimination degree of the temperature sequence, the characteristic weight of the pressure sequence and the characteristic weight of the temperature sequence in the corresponding time period are obtained.

[0009] Preferably, the calculating the target similarity between any two regions includes: For any two regions, the time period similarity of the two regions in the same time period is calculated based on the feature sequence and the weight of the feature sequence; Then, the time period similarity of the first time period and the similarity of the second time period are added and normalized to obtain the target similarity between any two regions.

[0010] Preferably, the Manhattan distances of the pressure sequences of any two regions in the first period are calculated, and the length of the first period is obtained; the Manhattan distances of the pressure sequences of all any two regions in the first period are added together and then divided by the length of the first period to obtain the discrimination of the pressure sequences in the first period; The discrimination degree of the temperature sequence in the first period, as well as the discrimination degree of the pressure sequence and the discrimination degree of the temperature sequence in the second period can be calculated based on the discrimination degree of the pressure sequence in the first period.

[0011] Preferably, the process of obtaining the time period similarity of the first time period is: For the pressure sequence of the first period, the difference between the two regions on the feature, i.e., the absolute value difference, is calculated. The calculated difference is divided by the global maximum value of the feature, and all the differences are summed and multiplied by the weight of the feature to obtain the weighted difference sum of the pressure sequence; The weighted difference sum of the temperature sequence in the first period is calculated according to the calculation method of the weighted difference sum of the pressure sequence, and the weighted difference sum of the pressure sequence and the weighted difference sum of the temperature sequence are added together to obtain the period similarity of the two regions in the first period.

[0012] Preferably, the process of obtaining the predicted value of the clamping force includes: The attention weight of each region is calculated based on the target similarity ratio between each region and the regions belonging to its most remote and nearest sensors; The predicted clamping force value is obtained by multiplying the attention weight of each region, the average value of the pressure sequence in the second period, and the projected area of the region, and then summing the values for all regions.

[0013] The beneficial effects of the present invention are: The present invention first divides the mold cavity into multiple areas, collects pressure and temperature data for each area, and constructs a feature sequence. This can more carefully reflect the actual state of the mold during the injection molding process and avoid errors caused by single data points or overall average values. Secondly, the feature sequence is divided into the first period (from injection filling to the start of pressure holding) and the second period (from pressure holding to the end of filling), and feature weights and target similarities are calculated for each period, fully accounting for the dynamic changes in the injection molding process. The pressure and temperature distribution patterns within the mold vary at different stages, and this method allows for targeted analysis based on the characteristics of each stage, leading to more accurate prediction of clamping force. When calculating the predicted clamping force, multiple factors are comprehensively considered, including target similarity, the second-period pressure sequence, and the mold projected area. Target similarity reflects the similarity of characteristic distributions between different regions, the second-period pressure sequence reflects the pressure state during the holding phase, and the mold projected area is directly related to the clamping force. By organically combining these factors, a more comprehensive assessment of clamping force requirements can be achieved, avoiding inaccurate settings caused by ignoring certain key factors. This ensures that the actual clamping force meets production requirements, safeguarding the safety and stability of the injection molding process, and improving product quality and production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 This is a method flow chart of steps S1 to S4 in an intelligent setting method for the clamping force of an injection molding machine according to an embodiment of the present invention. DETAILED DESCRIPTION

[0015] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, but not all of the embodiments.

[0016] Reference Figure 1 A method for intelligently setting the clamping force of an injection molding machine includes steps S1 to S4, specifically as follows: S1: Divide the mold cavity into multiple areas, collect and preprocess the pressure and temperature data of each area at each time, and construct the pressure sequence and temperature sequence of a single area according to the order of collection time. The pressure sequence and temperature sequence constitute the characteristic sequence of the area.

[0017] In one embodiment, the mold cavity is first divided into multiple areas of equal area based on the area of the mold parting surface. The parting surface is a plane in the mold used to divide the mold into two parts to remove the molded product. The areas are divided based on the area of the parting surface so that the divided areas are evenly distributed and representative in the mold cavity.

[0018] A pressure sensor is then placed in the mold cavity corresponding to the center of each zone to collect real-time pressure data for that zone. Simultaneously, an infrared temperature sensor is used to collect temperature data on the mold cavity surface. For a zone, at a specific moment, the average temperature value of all locations within the zone is taken to obtain the average temperature value for that zone at that moment. This allows the generation of a temperature sequence for that zone over time.

[0019] The collected pressure and temperature data are further denoised using wavelet transform.

[0020] Finally, the pressure sequence and temperature sequence of each region are obtained by sorting them according to the acquisition time, and the pressure sequence and temperature sequence of each region are combined together to form the characteristic sequence of the region.

[0021] It's important to note that the projection of the parting surface of an injection mold is often an irregular shape. To optimally position sensors on these irregular shapes, we first find the smallest rectangle that can accommodate the projection of the parting surface. If the center of the region is not on the projection, the sensor is positioned at the edge of the projection closest to the center. This ensures that the sensor can effectively collect data while avoiding inaccurate data collection due to improper sensor placement.

[0022] S2: Divide the feature sequence into a first period and a second period according to the injection molding process. Calculate the target similarity of any two regions in the same period based on the feature sequence and the calculated feature weight of the same period. The target similarity is used to evaluate the similarity of feature distribution of the two regions in the entire injection molding process.

[0023] Injection molding machines involve multiple stages, and pressure distribution varies across different regions. Analyzing flash-prone and flash-resistant areas and predicting clamping force based solely on the instantaneous pressure distribution within the mold after injection is complete is flawed. Ignoring the influence of temperature at different stages can lead to incorrect region identification. For example, the high-pressure, high-temperature edge areas and the high-pressure center of the injection point at different stages can be mistakenly identified as flash-resistant areas, resulting in flash in the mold. Therefore, it is necessary to comprehensively consider pressure and temperature characteristics and calculate target similarity to assess the similarity of the characteristic distribution of the two regions throughout the injection process, thereby determining the likelihood of regional anomalies (such as flash).

[0024] In one embodiment, the injection molding process is divided into two periods: the first period is from filling to the start of holding pressure, and the second period is from holding pressure to the end of filling. Then, for the characteristic sequence of each area, the characteristic sequence of the first period and the second period can be obtained.

[0025] As mentioned above, during the filling phase, the edge areas may experience high pressure due to the faster plastic flow rate. However, during the holding phase, the temperature in these areas may be lower, causing the plastic to cool faster. Meanwhile, the center area may experience lower pressure during the filling phase, but during the holding phase, the temperature may be higher due to concentrated heat. Therefore, by dividing the injection molding process into the first and second phases, the pressure and temperature changes during these phases can be more comprehensively analyzed, allowing for more accurate identification and assessment of the characteristic distribution of each region. This approach not only considers the dual-dimensional characteristics of pressure and temperature, but also eliminates the impact of characteristic changes between phases through time-phase analysis, improving the accuracy of identifying abnormal areas (such as flash).

[0026] In order to measure the degree of difference in characteristics of different regions in a specific time period, in one embodiment, the discrimination of the pressure sequence and the discrimination of the temperature sequence in the same time period are calculated using the Manhattan distance. Based on the discrimination of the pressure sequence and the discrimination of the temperature sequence, the characteristics of different regions can be more accurately identified and distinguished.

[0027] For example, taking the pressure sequence of the first period as an example, the discrimination of the pressure sequence satisfies the following relationship: Where, is the discrimination of the pressure sequence in the first period, Indicates area and region The Manhattan distance of the pressure series in the first period, is the length of the first period (i.e., the number of time points), which is used to eliminate the impact of the length differences of different periods on the Manhattan distance. is the total number of regions.

[0028] Based on the discrimination of the pressure sequence in the first period, the discrimination of the temperature sequence in the first period, and the discrimination of the pressure sequence and the discrimination of the temperature sequence in the second period are calculated in the same way.

[0029] Furthermore, the importance of features may vary across time periods. For example, certain features may have strong explanatory power for the target in one time period but become less important in another. By comparing the discriminability of a feature with that of other features and calculating weights, we can quantify the relative importance of each feature within a specific time period. For example, if the pressure series has high discriminability in the first time period, while the temperature series has low discriminability, the pressure series will have a higher weight in that time period, indicating that it contributes more to the target in that time period.

[0030] For example, the ratio of the discrimination of the pressure sequence for the first period to the sum of the discrimination of the pressure sequence for the first period and the discrimination of the temperature sequence for the first period is used as the characteristic weight of the pressure sequence for the first period. Similarly, the characteristic weight of the temperature sequence for the first period, as well as the characteristic weight of the pressure sequence and the characteristic weight of the temperature sequence for the second period, can be calculated.

[0031] Furthermore, the time period similarity between regions in a certain time period is calculated. The specific calculation process is as follows: For the pressure sequence of the first period, the difference between the two regions in this feature, that is, the absolute value difference, is calculated. The calculated difference is divided by the global maximum value of the feature, and all the differences are summed and multiplied by the weight of the feature to obtain the weighted difference sum of the pressure sequence. Similarly, the weighted difference sum of the temperature sequence of the first period is also calculated. The weighted difference sum of the pressure sequence and the weighted difference sum of the temperature sequence are added together to obtain the time period similarity of the two regions in the first period. Similarly, the time period similarity of the two regions in the second period can be obtained.

[0032] The above fusion of temperature and pressure dimensions can more comprehensively and accurately identify differences between regions, improve the accuracy of identifying abnormal areas, and avoid misjudgments or omissions caused by single-dimensional analysis.

[0033] Furthermore, considering that the first time period typically focuses on local or short-term behavior—that is, during the injection molding process, the first time period may only consider the instantaneous pressure changes or filling conditions when the melt first enters the mold—the similarity of this time period can reflect whether the region's behavior is consistent in the initial stage, but may not capture subsequent long-term behavior. However, the second time period focuses more on overall or long-term behavior. The similarity of this time period can reflect whether the region's overall behavior is consistent throughout the entire injection molding process, but may not capture local differences in the initial stage. Furthermore, during the injection molding process, the distance from the injection point to different areas of the mold varies, and the injection speed also affects regional behavior. For example, areas farther from the injection point may respond more slowly in the initial stage, but if only the similarity of the first time period is considered, it may be misjudged as an anomaly. By incorporating the similarity of the second time period, the influence of this single factor can be eliminated.

[0034] By calculating the similarity between two areas in the first period and the second period, and then further calculating the target similarity, the main purpose is to comprehensively consider the information at different time scales, so as to more comprehensively and accurately reflect the behavioral characteristics and abnormal situations between areas.

[0035] By region and region For example, the target similarity of these two regions satisfies the relationship: Where, Indicates area and region The target similarity, For the region and region The time period similarity in the first period, For the region and region The time period similarity in the second period, Indicates normalization processing.

[0036] Then, the target similarity of any two other regions is obtained according to the above calculation method.

[0037] If the target similarity between two regions is low (close to 0), it means that the behaviors of the two regions in the two time periods are quite different, and there may be anomalies. If the target similarity is high (close to 1), it means that the behaviors of the two regions in the two time periods are relatively consistent, which is normal.

[0038] S3: The clamping force prediction value is calculated based on the target similarity, the pressure sequence in the second period, and the mold projection area.

[0039] Due to the different thicknesses of different locations on the injection mold (such as smooth areas, ribs, pins, etc.), uneven pressure distribution on the mold surface during injection molding can easily occur. The existing technology Moldflow usually takes the average value of the pressure field over the entire projected area, ignoring the complex structure within the mold cavity. As a result, local high pressure at non-injection points or edge areas is smoothed out by the remaining areas, resulting in misjudgment of flash areas, insufficient clamping force support in local high-pressure areas, resulting in flash, or excessive clamping force and high energy consumption.

[0040] By calculating attention weights, we can identify areas with unusual distribution characteristics. Because the melt flows in all directions during injection molding, the characteristic distributions of areas close to the injection point should be similar. The greater the difference between an area and its neighbors, and the smaller the difference from remote areas, the greater the likelihood of unusual distribution characteristics in that area, and the more attention should be paid to avoid problems such as flash. Using attention weights and the second-period pressure sequence for clamping force prediction can more accurately account for the pressure distribution in different areas of the mold, thereby improving the accuracy of clamping force predictions, reducing the occurrence of flash, and lowering energy consumption.

[0041] Specifically, the Euclidean distance between each sensor and the injection point is calculated to identify the sensor closest to the injection point (the nearest sensor) and the sensor farthest from the injection point (the most remote sensor). If multiple sensors meet the criteria, further screening is performed based on the distance between them. It should be noted that during the product design phase, engineers determine the optimal plastic filling inlet location based on the product's shape, size, and functional requirements. This location is the injection point.

[0042] Then, based on the area to which each sensor belongs, the target similarity of each area with the area to which its most adjacent and most remote sensors belong is determined (calculated based on the target similarity in S2 above).

[0043] Next, the attention weight of each region is calculated based on the target similarity ratio between each region and the regions of its most remote and nearest sensors. That is, the following relationship is satisfied: Where, For the region The attention weight, For the region Similarity to targets in the area of its most remote sensor, Indicates area The target similarity with the area of its nearest neighboring sensor, Represents an exponential function with the natural constant e as its base.

[0044] when When >1, it indicates the area The similarity of the characteristic distribution of its neighboring areas is less than that of the characteristic distribution of remote areas, which means that the probability of local anomalies in this area is higher and more attention is needed. Since the melt flows from the injection point to the surrounding areas during injection molding, the characteristic distribution of areas close to the injection point should be more similar. If a region is very different from the neighboring areas but not from the remote areas, it means that the region may have abnormal distribution characteristics and flash should be avoided. Exponential function Amplify differences and strengthen attention to abnormal areas.

[0045] Furthermore, the predicted clamping force value is calculated by using the attention weight of each area and the average value of the pressure sequence in the second period, combined with the mold projection area of each area. The predicted clamping force value satisfies the following relationship: Where, is the predicted value of clamping force, For the region The attention weight, Indicates area The average value of the pressure series in the second period, Indicates area The mold projection area (the projection area along the clamping direction determines the range of pressure action. This parameter is obtained through existing technologies such as CAD models or actual measurements). is the total number of regions.

[0046] Among them, by introducing the attention mechanism, the importance of each area in the clamping force calculation can be more accurately reflected; since the injection molding process is a dynamic process, the pressure will change over time. By considering the average value of the pressure sequence, the pressure distribution in the actual injection molding process can be more comprehensively reflected. Secondly, the second period mentioned above usually corresponds to the mid-stage of plastic filling the mold. At this time, the plastic has partially filled the mold, and the pressure sequence may be more stable and better represent the average pressure level of the entire injection molding process.

[0047] When calculating clamping force, it is important to consider the projected area because the clamping force is not only related to the pressure, but also to the area over which the pressure acts. If an area has a larger projected area, then even if the pressure is the same, the clamping force in that area will be greater. Therefore, by multiplying the projected area of each area by the average pressure in that area and the attention weight, the contribution of that area to the total clamping force can be more accurately calculated.

[0048] S4: Before the next injection molding production, the predicted clamping force is multiplied by the preset safety factor to obtain the actual clamping force, and intelligent setting is completed based on the actual clamping force.

[0049] In injection molding production, intelligent setting by predicting the clamping force and combining it with a safety factor can effectively balance production efficiency and equipment safety.

[0050] Specifically, first, determine the safety factor. By considering factors such as fluctuations in material properties, mold wear, and precision errors of the injection molding machine during the production process, the safety factor can usually be set based on experience and actual needs, such as 1.2 or 1.3.

[0051] Then, the predicted clamping force value calculated by S3 is multiplied by the safety factor to obtain an actual clamping force.

[0052] Finally, the calculated actual clamping force is set in the injection molding machine's control system. For example, assuming a predicted clamping force of 500 tons and a safety factor of 1.2, the actual clamping force is 600 tons. Then, in the injection molding machine's control interface, the clamping force is set to 600 tons, saved, and a trial run is performed.

[0053] It should be noted that those skilled in the art may make various modifications and improvements without departing from the scope of the present invention, and these modifications and improvements fall within the scope of protection of the present invention. Therefore, the scope of protection of the patent for this invention shall be based on the appended claims.

Claims

1. An intelligent setting method for the clamping force of an injection molding machine, characterized in that: include: The mold cavity is divided into multiple regions, and the pressure and temperature data of each region at each time are collected and preprocessed. Based on a single region, a pressure sequence and a temperature sequence of the region are constructed according to the order of collection time. The pressure sequence and temperature sequence constitute the characteristic sequence of the region; The feature sequence is divided into a first period and a second period according to the injection molding process. The target similarity between any two regions is calculated based on the feature sequence of the same period and the calculated feature weight of the same period. The target similarity is used to evaluate the similarity of feature distribution of the two regions during the entire injection molding process. The clamping force prediction value is calculated based on the target similarity, the pressure sequence in the second period, and the mold projection area; Before the next injection molding production, the predicted clamping force is multiplied by the preset safety factor to obtain the actual clamping force, and intelligent setting is completed based on the actual clamping force.

2. The intelligent setting method of the clamping force of an injection molding machine according to claim 1, characterized in that: The collecting of pressure and temperature data of each region at each time includes: The mold is divided into equal areas according to the area of the mold parting surface, and a pressure sensor is set at the center of each divided area to collect the pressure data in the mold cavity; Infrared sensors are used synchronously to collect temperature data on the mold surface. For an area, at a certain moment, the temperature values of all positions in the area are averaged to obtain the temperature value of the area at that moment.

3. The intelligent setting method of the clamping force of an injection molding machine according to claim 2, characterized in that: The first period is from injection filling to the start of pressure holding, and the second period is from pressure holding to the end of filling.

4. The intelligent setting method of the clamping force of an injection molding machine according to claim 3, characterized in that: The process of obtaining the feature weights includes: For a period, the discrimination of the pressure series and the discrimination of the temperature series in the corresponding period are calculated based on the Manhattan distance between the characteristic sequences of all regions in the same period. According to the discrimination degree of the pressure sequence and the discrimination degree of the temperature sequence, the characteristic weight of the pressure sequence and the characteristic weight of the temperature sequence in the corresponding time period are obtained.

5. The intelligent setting method of the clamping force of an injection molding machine according to claim 4, characterized in that: Calculating the target similarity between any two regions includes: For any two regions, the time period similarity of the two regions in the same time period is calculated based on the feature sequence and the weight of the feature sequence; Then, the time period similarity of the first time period and the similarity of the second time period are added and normalized to obtain the target similarity between any two regions.

6. The intelligent setting method of the clamping force of an injection molding machine according to claim 5, characterized in that: Calculate the Manhattan distance of the pressure sequence of any two regions in the first period and obtain the length of the first period; add the Manhattan distances of the pressure sequence of any two regions in the first period and then divide it by the length of the first period to obtain the discrimination of the pressure sequence in the first period; The discrimination degree of the temperature sequence in the first period, as well as the discrimination degree of the pressure sequence and the discrimination degree of the temperature sequence in the second period can be calculated based on the discrimination degree of the pressure sequence in the first period.

7. The intelligent setting method of the clamping force of an injection molding machine according to claim 6, characterized in that: The process of obtaining the time period similarity of the first time period is as follows: For the pressure sequence of the first period, the difference between the two regions on the feature, i.e., the absolute value difference, is calculated. The calculated difference is divided by the global maximum value of the feature, and all the differences are summed and multiplied by the weight of the feature to obtain the weighted difference sum of the pressure sequence; The weighted difference sum of the temperature sequence in the first period is calculated according to the calculation method of the weighted difference sum of the pressure sequence, and the weighted difference sum of the pressure sequence and the weighted difference sum of the temperature sequence are added together to obtain the period similarity of the two regions in the first period.

8. The intelligent setting method of the clamping force of an injection molding machine according to claim 7, characterized in that: The process of obtaining the predicted value of the clamping force includes: The attention weight of each area is calculated based on the target similarity ratio of each area to the areas to which its most remote and nearest sensors belong; the attention weight of each area, the average value of the pressure sequence in the second period and the projected area of the area are multiplied, and then the sum of all areas is used to obtain the clamping force prediction value.

Images