An intelligent injection temperature adjusting system and method for an injection mold

Abstract

This invention discloses an intelligent temperature control system and method for injection molds. The method includes: anchoring N mold region nodes on the injection mold; constructing N thermal behavior coefficient sequences corresponding to the N mold region nodes; calculating J thermal behavior correlations; calculating the thermal behavior distance between any two sequences based on the thermal behavior correlations; performing hierarchical clustering based on the thermal behavior distance to generate K thermal behavior sequence clusters; extracting P node indices corresponding to each of the P thermal behavior coefficient sequences within each cluster; defining the P key regions corresponding to the P node indices as thermal response homogeneous regions, and configuring temperature control strategies with the same rules for each thermal response homogeneous region. This invention can configure the same mold temperature control parameters for each thermal response homogeneous region, effectively suppressing molding defects caused by the injection mold to the product.

Description

Technical Field

[0001] This invention relates to the field of injection molding temperature control, specifically to an intelligent method for controlling the injection temperature of injection molds. Background Technology

[0002] In injection molding, temperature variations in different areas of the mold directly affect melt flow, cooling rate, and product quality. To improve temperature control, existing technologies typically divide the mold into several zones and set temperature control parameters for each zone. However, these zoning methods often rely on engineers' experience or pre-defined mold structural features (such as gate location and cooling channel layout), failing to fully consider the dynamic characteristics of temperature evolution over time in actual production. For example, areas physically far apart may exhibit similar temperature fluctuation patterns due to similar wall thickness or cooling conditions, yet they are assigned to different temperature control groups; conversely, adjacent areas with significantly different thermal responses may be forced to adopt the same temperature control strategy. Furthermore, while configuring an independent temperature control actuator for each temperature measurement point can improve local adjustment capabilities, it leads to increased system complexity and cost, and is prone to causing unnecessary temperature gradients due to parameter inconsistencies, which can exacerbate product warping or internal stress concentration. Summary of the Invention

[0003] To address the shortcomings of existing technologies, this invention provides an intelligent method for adjusting the injection temperature of injection molds, which solves the technical problems mentioned in the background art by introducing a homogeneous thermal response region on the injection mold.

[0004] To achieve the above objectives, the present invention provides the following technical solution: In a first aspect, the present invention discloses an intelligent method for regulating the injection temperature of an injection mold, comprising the following steps: S1, anchoring N mold area nodes on the injection mold; S2. Construct N thermal behavior coefficient sequences corresponding to N mold region nodes; S3. Calculate the thermal behavior correlation between any two sequences in the N thermal behavior coefficient sequences to obtain J thermal behavior correlations; where J = N(N-1) / 2; S4. Calculate the thermal behavior distance between any two sequences based on the thermal behavior correlation. S5. Perform hierarchical clustering on N thermal behavior coefficient sequences based on thermal behavior distance to generate K thermal behavior sequence clusters; S6. For any cluster of thermal behavior sequences, extract the P node indices corresponding to each of the P thermal behavior coefficient sequences within the cluster. S7. Define the P key regions corresponding to the P node numbers as homogeneous thermal response regions, and configure temperature regulation strategies with the same rules for the homogeneous thermal response regions.

[0005] In some specific embodiments, N thermal behavior coefficient sequences corresponding to N mold region nodes are constructed, including: S2-1. Among N mold area nodes, obtain the total variation of injection temperature for any target area node within a time window M; S2-2. Normalize the total variation of injection temperature within M time windows to generate thermal behavior coefficients of the target region nodes within M time windows. S2-3. Sort the M thermal behavior coefficients sequentially by time window to generate a sequence of thermal behavior coefficients for the target region nodes; S2-4. Traverse N mold region nodes and repeat the generation of thermal behavior coefficient sequences for each target region node until N thermal behavior coefficient sequences are obtained.

[0006] In some specific embodiments, obtaining the total variation of injection molding temperature for any target region node within a time window M includes: S2-1-1, Assign predefined node numbers to N mold area nodes; S2-1-2. Based on the sorting direction of N node numbers, anchor the target region node in the mold region node one by one; S2-1-3. Obtain the G instantaneous injection temperatures of the target region nodes within the time window; wherein the sampling period between the G instantaneous injection temperatures is constant; S2-1-4. Based on G instantaneous injection temperatures, calculate the total variation of injection temperature of the target region nodes within the time window; S2-1-5. Slide the time window continuously M times with a standard step size on the time axis to collect the total variation of injection temperature of the target area node in each of the M time windows.

[0007] In some specific embodiments, the calculation of the total variation in injection temperature of the target region node within a time window includes: S2-1-4-1, Anchoring G sampling timestamps corresponding to G instantaneous injection temperatures; S2-1-4-2. Based on the order of sampling timestamps, assign monotonically increasing sampling numbers to the G instantaneous injection temperatures; S2-1-4-3. Arrange the G instantaneous injection temperatures in ascending order according to the sampling sequence number to generate an instantaneous injection temperature sequence; S2-1-4-4 Calculate the G-1 absolute temperature differences between adjacent instantaneous injection temperatures in the instantaneous injection temperature sequence; S2-1-4-5. Sum the G-1 absolute temperature differences to generate the total variation of injection temperature within the time window.

[0008] In some specific embodiments, generating the thermal behavior coefficients of the target region nodes over M time windows includes: S2-2-1. Select the maximum and minimum total variations among the M total variations in injection molding temperature; S2-2-2. The difference between the maximum and minimum total variation is taken to obtain the range of total variation. S2-2-3. Select the current total variation from the M total variations in injection temperature; S2-2-4. Calculate the difference between the current total variation and the minimum total variation to obtain the current total variation offset; S2-2-5. Calculate the ratio between the total variation range and the current total variation offset to generate the thermal behavior coefficient corresponding to the current total variation. S2-2-6. Iterate through M total injection temperature variations until the thermal behavior coefficients of the target region nodes in M ​​time windows are obtained.

[0009] In some specific embodiments, the thermal behavior correlation between any two sequences of N thermal behavior coefficient sequences is calculated, including: S3-1. Select any two sequences from the N thermal behavior coefficient sequences and label them as the first coefficient sequence and the second coefficient sequence. S3-2. Calculate the mean of the first coefficient and the mean of the second coefficient in the first coefficient sequence and the second coefficient sequence; S3-3. Based on the mean of the first coefficient and the mean of the second coefficient, calculate the covariance term between the first coefficient sequence and the second coefficient sequence, as well as the first standard deviation and the second standard deviation of the first coefficient sequence and the second coefficient sequence, respectively. S3-4. If both the first and second standard deviations are positive, calculate the correlation of thermal behavior between the two sequences. S3-5. If the first standard deviation or the second standard deviation is equal to zero, then the correlation of thermal behavior is set to 1. S3-6. Traverse the non-repeating sequence pairs in the N thermal behavior coefficient sequences and repeatedly calculate the thermal behavior correlation until J thermal behavior correlations are obtained.

[0010] In some specific embodiments, hierarchical clustering is performed on N sequences of thermal behavior coefficients based on thermal behavior distance, including: S5-1. Take the N thermal behavior coefficient sequences as N initial clusters, and initialize the N initial clusters as the current cluster set; S5-2. In the current cluster set, identify any two clusters that have the minimum thermal behavior distance and merge the cluster pair into a new cluster. S5-3. Remove the cluster pair from the current cluster set and add the new cluster, then update the current cluster set; S5-4. Repeat the update of the current cluster set until the current cluster set contains only a single cluster; S5-5. During each merge operation, record the merged cluster pairs and their corresponding thermal behavior distances to generate a merge record; S5-6. Construct a hierarchical clustering tree representing the evolutionary relationship of thermal behavior patterns based on merged records; S5-7. Based on the hierarchical clustering tree, extract K hot behavior sequence clusters at the corresponding level.

[0011] In some specific embodiments, K clusters of thermal behavior sequences at the corresponding level are extracted, including: S5-7-1 Extract the merge distance sequence arranged in the merge order from the hierarchical clustering tree; S5-7-2. Calculate the distance increment between the heights of adjacent nodes in the merged distance sequence to obtain the distance increment sequence; S5-7-3, Set the distance jump threshold; S5-7-4. If, along the ascending direction of the distance increment sequence, there exists a distance increment in the Hth merge that is greater than the distance jump threshold, then clustering is stopped after the Hth merge is completed. S5-7-5. Define the K clusters remaining after the Hth time when clustering stops as hot behavior sequence clusters; where K=NH.

[0012] This invention provides an intelligent method for regulating the injection temperature of injection molds, which has the following beneficial effects: This invention constructs a sequence of thermal behavior coefficients for each mold region node within a continuous time window, calculates the correlation between any two sequences, and converts this correlation into thermal behavior distance, thereby achieving a quantitative comparison of the thermal dynamic evolution patterns of the mold region. Based on this, a hierarchical clustering method is used to automatically generate multiple thermal behavior sequence clusters, and the physical region corresponding to each cluster is defined as a thermal response homogeneous region. This ensures that regions within the same homogeneous region exhibit highly similar temperature fluctuation evolution patterns. Consequently, the same mold temperature control parameters can be configured for each thermal response homogeneous region, avoiding hardware redundancy and increased control complexity caused by repeatedly setting independent temperature control channels for regions with similar thermal behavior, effectively suppressing molding defects caused by injection molds to the product.

[0013] Secondly, the present invention discloses an intelligent injection temperature control system for injection molds, used to execute the intelligent injection temperature control method for injection molds described in the first aspect, comprising: Mold node anchoring module, used to anchor N mold area nodes on an injection mold; The sequence construction module is used to construct N thermal behavior coefficient sequences corresponding to N mold region nodes; The correlation calculation module is used to calculate the correlation between any two sequences in N thermal behavior coefficient sequences, resulting in J thermal behavior correlations; where J = N(N-1) / 2; The distance calculation module is used to calculate the thermal behavior distance between any two sequences based on the thermal behavior correlation. The sequence clustering module is used to perform hierarchical clustering of N thermal behavior coefficient sequences based on thermal behavior distance, generating K thermal behavior sequence clusters; The same-cluster node anchoring module is used to extract the P node indices corresponding to each of the P thermal behavior coefficient sequences within any thermal behavior sequence cluster. The temperature strategy configuration module is used to define P key regions corresponding to P node numbers as homogeneous thermal response regions, and to configure temperature regulation strategies with the same rules for the homogeneous thermal response regions.

[0014] Compared with the prior art, the beneficial effects of the intelligent injection temperature regulation system for injection molds of the present invention are the same as those of the intelligent injection temperature regulation method for injection molds described above, so they will not be repeated here. Attached Figure Description

[0015] Figure 1 This is a flowchart illustrating an intelligent temperature control method for injection molds according to the present invention. Figure 2 This is a schematic diagram of the process for generating the thermal behavior coefficient sequence described in this invention; Figure 3 This is a schematic diagram of the calculation process for the thermal behavior correlation described in this invention; Figure 4 This is a structural block diagram of an intelligent temperature control system for injection molds according to the present invention. Detailed Implementation

[0016] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0017] Example 1: Please refer to Figures 1 to 3 This invention provides a method for intelligent adjustment of injection temperature for injection molds, comprising the following steps: S1, anchoring N mold area nodes on the injection mold; Specifically, the mold area nodes are predetermined by technicians based on mold thermal response characteristic analysis or process experience, and include at least one of the following: the area near the gate, the melt end filling area, the area corresponding to the thick-walled structure, the area corresponding to the thin-walled structure, and the area adjacent to the cooling channel; Furthermore, the node number is a unique identifier assigned to the N mold area nodes according to a preset spatial order or functional category, used to distinguish different area nodes.

[0018] S2. Construct N thermal behavior coefficient sequences corresponding to N mold region nodes; S3. Calculate the thermal behavior correlation between any two sequences in the N thermal behavior coefficient sequences to obtain J thermal behavior correlations; where J = N(N-1) / 2; S4. Calculate the thermal behavior distance between any two sequences based on the thermal behavior correlation. The formula for calculating the thermal behavior distance is: ; in, This represents the correlation of thermal behavior between two sequences, and its value ranges from (-1, 1). It represents the absolute value of the correlation between thermal behaviors, used to measure the strength of consistency in the evolutionary trends of two sequences (whether positive or negative, they are considered similar as long as the change patterns are similar). This represents the corresponding thermal behavior distance, with a value range of (0,1). The smaller the distance, the more similar the thermal dynamic evolution patterns of the nodes in the two mold regions are.

[0019] S5. Based on the thermal behavior distance, hierarchical clustering is performed on N thermal behavior coefficient sequences to generate K thermal behavior sequence clusters; wherein, each thermal behavior sequence cluster contains unequal or equal numbers of thermal behavior coefficient sequences, indicating that the temperature difference evolution pattern of the sequences within the cluster is the same. S6. For any cluster of thermal behavior sequences, extract the P node indices corresponding to each of the P thermal behavior coefficient sequences within the cluster. S7. Define the P key regions corresponding to the P node numbers as homogeneous thermal response regions, and configure temperature regulation strategies with the same rules for the homogeneous thermal response regions.

[0020] Specifically, the temperature regulation strategy includes: sharing the same set of mold temperature control parameters for all key areas within the homogeneous thermal response region, wherein the mold temperature control parameters include at least one of the following: cooling medium flow rate set value, heating power output ratio, mold temperature controller target temperature or cooling time compensation amount; Since the key regions within the homogeneous thermal response region have highly similar dynamic temperature evolution patterns, adopting a unified adjustment strategy can avoid local over-control or under-control, reduce the number of temperature control actuators, reduce system complexity, and improve the uniformity and stability of the overall temperature field of the mold, thereby suppressing molding defects such as product warping, shrinkage marks, or internal stress concentration.

[0021] Specifically, in this embodiment, step S2 includes: S2-1. Among N mold area nodes, obtain the total variation of injection temperature for any target area node within a time window M; Specifically, the total variation in injection temperature represents the cumulative fluctuation of the injection temperature of the target area node over time within a single time window, reflecting the thermal dynamic activity of the area during the corresponding time period.

[0022] S2-2. Normalize the total variation of injection temperature within M time windows to generate thermal behavior coefficients of the target region nodes within M time windows. Specifically, the thermal behavior coefficient represents the total variation of injection molding temperature after scale unification, which is used to eliminate dimensional differences between different time windows or different regions, so that the thermal dynamic behavior of each region can be compared laterally under the same benchmark. S2-3. Sort the M thermal behavior coefficients sequentially by time window to generate a sequence of thermal behavior coefficients for the target region nodes; S2-4. Traverse N mold region nodes and repeat the generation of thermal behavior coefficient sequences for each target region node until N thermal behavior coefficient sequences are obtained.

[0023] In this embodiment, by converting the temperature fluctuation of each mold area node in a continuous production cycle into a time sequence, regions that originally had different absolute temperature differences due to differences in structural position or cooling conditions (such as the area near the gate and the end of the melt) can be compared laterally based on their relative temperature fluctuation patterns.

[0024] Further, step S2-1 specifically includes: S2-1-1, Assign predefined node numbers to N mold area nodes; S2-1-2. Based on the sorting direction of N node numbers, anchor the target region node in the mold region node one by one; S2-1-3. Obtain the G instantaneous injection temperatures of the target region nodes within the time window; wherein the sampling period between the G instantaneous injection temperatures is constant; S2-1-4. Based on G instantaneous injection temperatures, calculate the total variation of injection temperature of the target region nodes within the time window; S2-1-5. Slide the time window continuously M times with a standard step size on the time axis to collect the total variation of injection temperature of the target area node in each of the M time windows.

[0025] In this embodiment, M total injection temperature variations are continuously acquired by sliding a window along the time axis, thereby achieving time-sequential capture of temperature fluctuation behavior in different regions of the mold during continuous injection cycles, avoiding the omission of thermal response characteristics caused by random sampling or single-cycle observation.

[0026] Further, step S2-1-4 specifically includes: S2-1-4-1, Anchoring G sampling timestamps corresponding to G instantaneous injection temperatures; S2-1-4-2. Based on the order of sampling timestamps, assign monotonically increasing sampling numbers to the G instantaneous injection temperatures; S2-1-4-3. Arrange the G instantaneous injection temperatures in ascending order according to the sampling sequence number to generate an instantaneous injection temperature sequence; S2-1-4-4 Calculate the G-1 absolute temperature differences between adjacent instantaneous injection temperatures in the instantaneous injection temperature sequence; Specifically, the absolute temperature difference represents the absolute value of the change in injection temperature of the target area node between two consecutive sampling times. It is used to eliminate the influence of the direction of temperature rise and fall and only reflects the magnitude of local temperature fluctuations.

[0027] S2-1-4-5. Sum the G-1 absolute temperature differences to generate the total variation of injection temperature within the time window.

[0028] In this embodiment, the total variation of injection temperature reflects the total temperature fluctuation of the target area node within a single time window caused by melt filling, holding pressure or cooling. This avoids underestimating the actual thermal disturbance intensity by canceling out the heating and cooling. This distinguishes between high dynamic response areas (such as near the gate) and low dynamic response areas (such as the far-end thin-walled area).

[0029] Furthermore, step S2-2 specifically includes: S2-2-1. Select the maximum and minimum total variations among the M total variations in injection molding temperature; S2-2-2. The difference between the maximum and minimum total variation is taken to obtain the range of total variation. S2-2-3. Select the current total variation from the M total variations in injection temperature; S2-2-4. Calculate the difference between the current total variation and the minimum total variation to obtain the current total variation offset; S2-2-5. Calculate the ratio between the total variation range and the current total variation offset to generate the thermal behavior coefficient corresponding to the current total variation. S2-2-6. Iterate through M total injection temperature variations until the thermal behavior coefficients of the target region nodes in M ​​time windows are obtained.

[0030] In this embodiment, by linearly normalizing the total temperature variation of a single region in M ​​consecutive injection cycles according to its own fluctuation range, the temperature activity changes of the region caused by process disturbances in different cycles are mapped to a unified range, making the thermal dynamic response intensity of the same region comparable under different time windows.

[0031] Specifically, in this embodiment, step S3 includes: S3-1. Select any two sequences from the N thermal behavior coefficient sequences and label them as the first coefficient sequence and the second coefficient sequence. S3-2. Calculate the mean of the first coefficient and the mean of the second coefficient in the first coefficient sequence and the second coefficient sequence; S3-3. Based on the mean of the first coefficient and the mean of the second coefficient, calculate the covariance term between the first coefficient sequence and the second coefficient sequence, as well as the first standard deviation and the second standard deviation of the first coefficient sequence and the second coefficient sequence, respectively. Specifically, the formula for calculating the covariance is: ; in: This represents the covariance term, used to characterize XXX; M represents the number of time windows; This represents the thermal behavior coefficients of the first coefficient sequence in the i-th time window; This represents the thermal behavior coefficients of the second coefficient sequence in the i-th time window; and These represent the mean of the first coefficient and the mean of the second coefficient, respectively. S3-4. If both the first and second standard deviations are positive, calculate the correlation of thermal behavior between the two sequences. The formula for calculating the correlation of thermal behavior is: ; in, Indicates the correlation of thermal behavior. and These represent the first standard deviation and the second standard deviation, respectively.

[0032] S3-5. If the first standard deviation or the second standard deviation is equal to zero, then the correlation of thermal behavior is set to 1. Specifically, a thermal behavior correlation of 1 indicates that any two sequences are constant sequences and their thermal behaviors are completely identical. S3-6. Traverse the non-repeating sequence pairs in the N thermal behavior coefficient sequences and repeatedly calculate the thermal behavior correlation until J thermal behavior correlations are obtained.

[0033] In this embodiment, the synchronicity of temperature fluctuation trends in mold area nodes during continuous injection molding cycles is measured by thermal behavior correlation quantification. For example, when the area near the gate heats up due to pressure holding, if a thick-walled area also heats up synchronously, the correlation between the two approaches 1. If one heats up and the other down or there is no regularity, the correlation approaches 0 or a negative value. For areas that are always stable without fluctuation (such as constant temperature cooling areas), they are considered to be completely consistent and assigned a correlation of 1, thereby providing a quantitative basis for judging whether different areas have similar thermal response evolution patterns.

[0034] Specifically, in this embodiment, step S5 includes: S5-1. Take the N thermal behavior coefficient sequences as N initial clusters, and initialize the N initial clusters as the current cluster set; S5-2. In the current cluster set, identify any two clusters that have the minimum thermal behavior distance and merge the cluster pair into a new cluster. S5-3. Remove the cluster pair from the current cluster set and add the new cluster, then update the current cluster set; S5-4. Repeat the update of the current cluster set until the current cluster set contains only a single cluster; S5-5. During each merge operation, record the merged cluster pairs and their corresponding thermal behavior distances to generate a merge record; S5-6. Construct a hierarchical clustering tree representing the evolutionary relationship of thermal behavior patterns based on merged records; Specifically, the hierarchical clustering tree is a binary tree structure, with leaf nodes corresponding to N initial thermal behavior coefficient sequences and internal nodes corresponding to the new clusters generated in each merging operation. The height of each internal node is equal to the thermal behavior distance between the merged cluster pairs. The merge record contains the identifiers of the two source clusters in each merge, the identifier of the new cluster after the merge, and the corresponding thermal behavior distance. By connecting the new cluster as the parent node and the source cluster as the child node in the merge order, and mapping the thermal behavior distance to the node height, a complete hierarchical clustering tree is constructed from the bottom up. This hierarchical clustering tree visually represents the hierarchical similarity relationship of nodes in each mold region in terms of thermal dynamic evolution patterns, providing a basis for determining the optimal number of clusters K.

[0035] S5-7. Based on the hierarchical clustering tree, extract K hot behavior sequence clusters at the corresponding level.

[0036] In this embodiment, by constructing a hierarchical clustering tree, the N temperature measurement points that were originally scattered on the mold can be gradually merged according to the similarity of their temperature fluctuation patterns, thereby providing operators with a reasonable number of groups.

[0037] Furthermore, steps S5-7 specifically include: S5-7-1 Extract the merge distance sequence arranged in the merge order from the hierarchical clustering tree; S5-7-2. Calculate the distance increment between the heights of adjacent nodes in the merged distance sequence to obtain the distance increment sequence; Specifically, the distance increment sequence represents the difference sequence of thermal behavior distances between two adjacent merging operations during hierarchical clustering, used to quantify the rate of decrease in thermal behavior pattern similarity during cluster merging; when the increment increases significantly, it indicates that continued merging will lead to the incorrect merging of regions with different thermal response patterns.

[0038] S5-7-3, Set the distance jump threshold; S5-7-4. If, along the ascending direction of the distance increment sequence, there exists a distance increment in the Hth merge that is greater than the distance jump threshold, then clustering is stopped after the Hth merge is completed. S5-7-5. Define the K clusters remaining after the Hth time when clustering stops as hot behavior sequence clusters; where K=NH.

[0039] In this embodiment, by analyzing the incremental changes in the merging distance in the hierarchical clustering tree and terminating the merging when the distance jump exceeds a preset threshold, the critical point at which the thermal behavior pattern undergoes essential differentiation can be automatically identified; thus ensuring that the final divided thermal response homogeneous regions maintain the consistency of their internal thermal behavior.

[0040] Example 2: See Figure 4 The technical solution of Embodiment 2 differs from Embodiment 1 in that it also discloses an intelligent injection temperature control system for injection molds. This system is used to implement the above-described method embodiments, and details already described will not be repeated. The terms "module," "unit," and "subunit" used below refer to combinations of software and / or hardware that achieve a predetermined function. Although the system described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0041] Figure 4 This is a structural block diagram of an intelligent injection temperature control system for injection molds according to the present invention. The system includes: Mold node anchoring module, used to anchor N mold area nodes on an injection mold; The sequence construction module is used to construct N thermal behavior coefficient sequences corresponding to N mold region nodes; The correlation calculation module is used to calculate the correlation between any two sequences in N thermal behavior coefficient sequences, resulting in J thermal behavior correlations; where J = N(N-1) / 2; The distance calculation module is used to calculate the thermal behavior distance between any two sequences based on the thermal behavior correlation. The sequence clustering module is used to perform hierarchical clustering of N thermal behavior coefficient sequences based on thermal behavior distance, generating K thermal behavior sequence clusters; The same-cluster node anchoring module is used to extract the P node indices corresponding to each of the P thermal behavior coefficient sequences within any thermal behavior sequence cluster. The temperature strategy configuration module is used to define P key regions corresponding to P node numbers as homogeneous thermal response regions, and to configure temperature regulation strategies with the same rules for the homogeneous thermal response regions.

[0042] This embodiment solves the problem of unnecessary temperature gradients caused by injection molds through the above modules.

[0043] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0044] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. A method for intelligent adjustment of injection temperature for an injection mold, characterized in that, include: S1, anchoring N mold area nodes on the injection mold; S2. Construct N thermal behavior coefficient sequences corresponding to N mold region nodes; S3. Calculate the thermal behavior correlation between any two sequences in the N thermal behavior coefficient sequences to obtain J thermal behavior correlations; where J = N(N-1) / 2; S4. Calculate the thermal behavior distance between any two sequences based on the thermal behavior correlation. S5. Perform hierarchical clustering on N thermal behavior coefficient sequences based on thermal behavior distance to generate K thermal behavior sequence clusters; S6. For any cluster of thermal behavior sequences, extract the P node indices corresponding to each of the P thermal behavior coefficient sequences within the cluster. S7. Define the P key regions corresponding to the P node numbers as homogeneous thermal response regions, and configure temperature regulation strategies with the same rules for the homogeneous thermal response regions.

2. The intelligent temperature control method for injection molds according to claim 1, characterized in that, Construct N thermal behavior coefficient sequences corresponding to N mold region nodes, including: S2-1. Among N mold area nodes, obtain the total variation of injection temperature for any target area node within a time window M; S2-2. Normalize the total variation of injection temperature within M time windows to generate thermal behavior coefficients of the target region nodes within M time windows. S2-3. Sort the M thermal behavior coefficients sequentially by time window to generate a sequence of thermal behavior coefficients for the target region nodes; S2-4. Traverse N mold region nodes and repeat the generation of thermal behavior coefficient sequences for each target region node until N thermal behavior coefficient sequences are obtained.

3. The intelligent temperature control method for injection molds according to claim 2, characterized in that, Obtain the total variation of injection molding temperature for any target region node within a time window M, including: S2-1-1, Assign predefined node numbers to N mold area nodes; S2-1-2. Based on the sorting direction of N node numbers, anchor the target region node in the mold region node one by one; S2-1-3. Obtain the G instantaneous injection temperatures of the target region nodes within the time window; wherein the sampling period between the G instantaneous injection temperatures is constant; S2-1-4. Based on G instantaneous injection temperatures, calculate the total variation of injection temperature at the nodes in the target region within the time window; S2-1-5. Slide the time window continuously M times with a standard step size on the time axis to collect the total variation of injection temperature of the target area node in each of the M time windows.

4. The intelligent temperature control method for injection molds according to claim 3, characterized in that, Calculate the total variation in injection temperature of the target region nodes within the time window, including: S2-1-4-1, Anchoring G sampling timestamps corresponding to G instantaneous injection temperatures; S2-1-4-2. Based on the order of sampling timestamps, assign monotonically increasing sampling numbers to the G instantaneous injection temperatures; S2-1-4-3. Arrange the G instantaneous injection temperatures in ascending order according to the sampling sequence number to generate an instantaneous injection temperature sequence; S2-1-4-4 Calculate the G-1 absolute temperature differences between adjacent instantaneous injection temperatures in the instantaneous injection temperature sequence; S2-1-4-5. Sum the G-1 absolute temperature differences to generate the total variation of injection temperature within the time window.

5. The intelligent temperature control method for injection molds according to claim 3, characterized in that, Generate the thermal behavior coefficients of the target region nodes over M time windows, including: S2-2-1. Select the maximum and minimum total variations among the M total variations in injection molding temperature; S2-2-2. The difference between the maximum and minimum total variation is taken to obtain the range of total variation. S2-2-3. Select the current total variation from the M total variations in injection temperature; S2-2-4. Calculate the difference between the current total variation and the minimum total variation to obtain the current total variation offset; S2-2-5. Calculate the ratio between the total variation range and the current total variation offset to generate the thermal behavior coefficient corresponding to the current total variation. S2-2-6. Iterate through M total injection temperature variations until the thermal behavior coefficients of the target region nodes in M ​​time windows are obtained.

6. The intelligent temperature control method for injection molds according to claim 1, characterized in that, Calculate the correlation of thermal behavior between any two sequences of N thermal behavior coefficients, including: S3-1. Select any two sequences from the N thermal behavior coefficient sequences and label them as the first coefficient sequence and the second coefficient sequence. S3-2. Calculate the mean of the first coefficient and the mean of the second coefficient in the first coefficient sequence and the second coefficient sequence; S3-3. Based on the mean of the first coefficient and the mean of the second coefficient, calculate the covariance term between the first coefficient sequence and the second coefficient sequence, as well as the first standard deviation and the second standard deviation of the first coefficient sequence and the second coefficient sequence, respectively. S3-4. If both the first and second standard deviations are positive, calculate the correlation of thermal behavior between the two sequences. S3-5. If the first standard deviation or the second standard deviation is equal to zero, then the correlation of thermal behavior is set to 1. S3-6. Traverse the non-repeating sequence pairs in the N thermal behavior coefficient sequences and repeatedly calculate the thermal behavior correlation until J thermal behavior correlations are obtained.

7. The intelligent temperature control method for injection molds according to claim 1, characterized in that, Hierarchical clustering of N thermal behavior coefficient sequences based on thermal behavior distance generates K thermal behavior sequence clusters, including: S5-1. Take the N thermal behavior coefficient sequences as N initial clusters, and initialize the N initial clusters as the current cluster set; S5-2. In the current cluster set, identify any two clusters that have the minimum thermal behavior distance and merge the cluster pair into a new cluster. S5-3. Remove the cluster pair from the current cluster set and add the new cluster, then update the current cluster set; S5-4. Repeat the update of the current cluster set until the current cluster set contains only a single cluster; S5-5. During each merge operation, record the merged cluster pairs and their corresponding thermal behavior distances to generate a merge record; S5-6. Construct a hierarchical clustering tree representing the evolutionary relationship of thermal behavior patterns based on merged records; S5-7. Based on the hierarchical clustering tree, extract K hot behavior sequence clusters at the corresponding level.

8. The intelligent temperature control method for injection molds according to claim 7, characterized in that, Extract K clusters of hot behavior sequences from the corresponding level, including: S5-7-1 Extract the merge distance sequence arranged in the merge order from the hierarchical clustering tree; S5-7-2. Calculate the distance increment between the heights of adjacent nodes in the merged distance sequence to obtain the distance increment sequence; S5-7-3, Set the distance jump threshold; S5-7-4. If, along the ascending direction of the distance increment sequence, there exists a distance increment in the Hth merge that is greater than the distance jump threshold, then clustering is stopped after the Hth merge is completed. S5-7-5. Define the K clusters remaining after the Hth time when clustering stops as hot behavior sequence clusters; where K=NH.

9. An intelligent injection temperature control system for injection molds, used to execute the intelligent injection temperature control method for injection molds as described in any one of claims 1 to 8, characterized in that, include: Mold node anchoring module, used to anchor N mold area nodes on an injection mold; The sequence construction module is used to construct N thermal behavior coefficient sequences corresponding to N mold region nodes; The correlation calculation module is used to calculate the correlation between any two sequences in N thermal behavior coefficient sequences, resulting in J thermal behavior correlations; where J = N(N-1) / 2; The distance calculation module is used to calculate the thermal behavior distance between any two sequences based on the thermal behavior correlation. The sequence clustering module is used to perform hierarchical clustering of N thermal behavior coefficient sequences based on thermal behavior distance, generating K thermal behavior sequence clusters; The same-cluster node anchoring module is used to extract the P node indices corresponding to each of the P thermal behavior coefficient sequences within any thermal behavior sequence cluster. The temperature strategy configuration module is used to define P key regions corresponding to P node numbers as homogeneous thermal response regions, and to configure temperature regulation strategies with the same rules for the homogeneous thermal response regions.

Images