Router plastic shell injection intelligent control method and system

Abstract

The application relates to the technical field of injection molding control, in particular to a router plastic shell injection intelligent control method and system, which comprises the following steps: acquiring the melt temperature in a barrel, nozzle temperature, injected melt temperature, cooling water flow and quality score of all injection processes; dividing the injection process into a cooling participating process and a non-cooling participating process; acquiring each cooling sub-sequence of each cooling participating process; acquiring the injection control amplitude of each cooling participating process according to the quality score change amount under unit temperature change, the cooling water flow change amount, the temperature difference characteristics between the melt in the barrel and the injected melt when the cooling system is not running in each cooling participating process, and the number of cooling sub-sequences; setting the injection control amplitude of each non-cooling participating process as 0; and then optimizing the initial proportional coefficient of the current injection process. The application improves the injection quality of the plastic shell by adaptively adjusting the proportional coefficient of the current injection process.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of injection molding control, in particular to a router plastic shell injection intelligent control method and system. BACKGROUND

[0002] In the production process of the router shell, recycled waste ABS plastic is used as raw material for processing and recycling, which not only achieves the concept of environmental protection, but also meets the basic performance requirements of the router shell. In the injection control engineering of the router plastic shell, the traditional plastic mold design and control method has been difficult to meet the current mold upgrading, and cannot meet the production demand of high-quality plastic production. Therefore, it is of great significance to build a control method of the router plastic shell injection molding machine to realize accurate regulation and control of the injection process and improve product quality.

[0003] When using recycled plastic waste to injection mold the plastic shell of the router, the quality of the router shell is affected by the injection melt temperature. If the temperature is too low, the plastic melt will damage the screw and the machine injection port during injection; if the temperature is too high, the plastic is easy to burn. In order to ensure the quality stability of the router plastic shell, the prior art usually uses a fixed control parameter of the PID control algorithm to ensure the temperature stability of the injection melt. However, the prior art does not fully consider that the nozzle temperature of the injection molding machine will produce heat accumulation during the injection process, thereby producing additional temperature rise of the injection melt, and since the nozzle temperatures of different batches are inconsistent, the temperature rise of the injection melt is also dynamically changing. Therefore, the PID control algorithm with fixed parameters is difficult to adapt to the dynamic injection process, resulting in poor control effect, which in turn affects the injection quality of the plastic shell. SUMMARY

[0004] In order to solve the above technical problems, the purpose of the present application is to provide a router plastic shell injection intelligent control method and system, and the technical solution adopted is as follows:

[0005] In a first aspect, the application provides a router plastic shell injection intelligent control method, which comprises the following steps:

[0006] Obtaining the barrel melt temperature data, nozzle temperature data, injection melt temperature data, and cooling water flow data of the injection molding machine in a preset number of injection processes, and the quality score corresponding to each injection process;

[0007] According to the discrete degree of the cooling water flow data of each injection process, all injection processes are divided into cooling participating processes and non-cooling participating processes; the injection melt temperature of each cooling participating process is divided into a plurality of subsequences, and each cooling subsequence is extracted;

[0008] Based on the change in mass score under unit initial nozzle temperature change during all injection processes, and the difference between the change amplitude of each cooling subsequence in each cooling process and the change amplitude of the corresponding cooling water flow rate data in the same time period, the injection control sensitivity of each cooling process is obtained.

[0009] The data corresponding to the time period of all cooling subsequences in the data of melt temperature inside the barrel and melt temperature injected during each cooling process are removed. Based on the changing trend of the temperature difference between the remaining melt temperature inside the barrel and melt temperature injected, as well as the number of cooling subsequences and injection control sensitivity in each cooling process, the injection control amplitude of each cooling process is obtained.

[0010] Set the injection control amplitude of each non-cooling process to 0; cluster the initial nozzle temperature of the current injection process with the initial nozzle temperatures of all injection processes, and optimize the initial proportional coefficient of the current injection process based on the injection control amplitude of all other injection processes in the cluster where the initial nozzle temperature of the current injection process is located.

[0011] Preferably, the specific process of dividing all injection processes into cooling-involved processes and non-cooling-involved processes is as follows: calculate the variance of the cooling water flow data for each injection process, and record the injection process with a variance greater than or equal to a preset segmentation threshold as a cooling-involved process; record the injection process with a variance less than the preset segmentation threshold as a non-cooling-involved process.

[0012] Preferably, the specific process of extracting each cooling subsequence is as follows: the injection melt temperature data of each cooling process is divided into multiple subsequences, and the subsequences whose slope of the fitted line is less than a preset slope threshold are recorded as the cooling subsequences of each cooling process.

[0013] Preferably, the injection control sensitivity of each cooling-involved process refers to the product of the first ratio of all injection processes and the flow change factor of each corresponding cooling-involved process; wherein, the process of obtaining the first ratio of all injection processes is as follows: all injection processes with a quality score greater than or equal to a preset score threshold are recorded as good injection processes; the absolute difference c1 between the average initial nozzle temperature of all good injection processes and all bad injection processes, and the absolute difference c2 between the average quality score of all good injection processes and all bad injection processes are calculated respectively, and the ratio of the absolute difference c2 to the absolute difference c1 is recorded as the first ratio of all injection processes.

[0014] Preferably, the process of obtaining the flow rate change factor of each cooling process is as follows: based on the time period corresponding to each cooling subsequence in each cooling process, obtain each flow rate subsequence in the same time period in the flow rate sequence of each cooling process; sort all cooling subsequences and all flow rate subsequences in each cooling process according to the time sequence; calculate the ratio of the internal range of each flow rate subsequence in each cooling process to the internal range of the cooling subsequence in the same position, and record the average of all ratios as the flow rate change factor of each cooling process.

[0015] Preferably, the injection control amplitude of each cooling process is positively correlated with the injection control sensitivity of each cooling process, the total number of all cooling subsequences, and the first slope.

[0016] Preferably, the process of obtaining the first slope of each cooling process is as follows: the in-cylinder melt temperature data and the injection melt temperature data of each injection process are respectively recorded as the in-cylinder temperature sequence and the injection temperature sequence of each injection process according to the time sequence; elements belonging to the cooling subsequence in the injection temperature sequence of each cooling process are removed, and the sequence of the remaining elements according to the time sequence is recorded as the new injection temperature sequence of each cooling process; at the same time, according to the position of the elements in the cooling subsequence of each cooling process in the injection temperature sequence, the elements of the corresponding position are removed from the in-cylinder temperature sequence, and the sequence of the remaining elements in the in-cylinder temperature sequence according to the time sequence is recorded as the new in-cylinder temperature sequence of each cooling process.

[0017] Preferably, the calculation formula for optimizing the initial proportional coefficient of the current injection process is as follows: In the formula, This is the proportionality coefficient for the current injection process; The initial proportional coefficient preset for the current injection process; It is a regulatory factor in the current injection process; This is the normalization function; These are preset weighting coefficients.

[0018] Preferably, the process of obtaining the control factor of the current injection process is as follows: obtain the initial nozzle temperature w of the current injection process, cluster the initial nozzle temperature w with the initial nozzle temperatures of all injection processes; and record the average value of the injection control amplitude of all other injection processes in the cluster containing the initial nozzle temperature w of the current injection process as the control factor of the current injection process.

[0019] Secondly, embodiments of this application also provide a router plastic shell injection molding intelligent control system, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of any of the above-described router plastic shell injection molding intelligent control methods.

[0020] This application has at least the following beneficial effects:

[0021] This application addresses the problem in existing technologies that fail to adequately consider the dynamic changes in nozzle temperature heat accumulation, leading to unstable melt temperature and impacting finished product quality. By analyzing the change in quality score per unit nozzle temperature change and the change in cooling water flow rate per unit injection melt temperature change, an injection control sensitivity is constructed. This sensitivity reflects the degree of influence of temperature differences on finished product quality and the required adjustment range of cooling water flow rate. Furthermore, by analyzing the temperature difference trend between the melt temperature inside the barrel and the injection melt temperature during the non-operational phase of the cooling system, an injection control range is constructed. This range reflects the required response speed of the control system. The required proportional coefficient adjustment amount under different nozzle temperatures is then calculated, and the proportional coefficient of the current injection process is dynamically adjusted. This allows the cooling water flow rate of the cooling system to dynamically adapt to the heat accumulation trend at the nozzle, improving melt temperature stability and ultimately enhancing the injection molding quality of the plastic casing. Attached Figure Description

[0022] To more clearly illustrate the technical solutions and advantages in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 A flowchart illustrating the steps of an intelligent control method for injection molding a router's plastic casing, provided in one embodiment of this application;

[0024] Figure 2 A flowchart illustrating the acquisition of injection control amplitude for each cooling process provided in one embodiment of this application. Detailed Implementation

[0025] To further illustrate the technical means and effects adopted by this application to achieve the intended inventive purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a router plastic shell injection molding intelligent control method and system proposed in this application. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0026] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains.

[0027] The following description, in conjunction with the accompanying drawings, details a specific scheme for an intelligent control method and system for injection molding a router's plastic casing provided in this application.

[0028] Please see Figure 1 The diagram illustrates a flowchart of a router plastic casing injection molding intelligent control method according to an embodiment of this application. The method includes the following steps:

[0029] Step 1: Obtain the barrel melt temperature data, nozzle temperature data, ejected melt temperature data, cooling water flow rate data, and the corresponding quality score for each injection process of the injection molding machine for a preset number of injection processes.

[0030] This application uses recycled ABS plastic for the injection molding of the router casing. The injection molding machine heats the melt in the barrel using its own electromagnetic induction heating device and cools the melt in the barrel using its own water cooling system. This application collects the temperature data of the melt in the barrel using the injection molding machine's own temperature sensor; obtains the nozzle temperature data at the barrel outlet using a thermocouple; collects the temperature of the melt discharged from the nozzle using an infrared thermometer; and obtains the cooling water flow rate data using the injection molding machine's cooling system. All data are collected synchronously and in real time. In this embodiment, the acquisition frequency of all types of data is 100Hz.

[0031] The entire process from the melt being discharged from the nozzle of the barrel until it fills the router mold is recorded as one injection process. This application collects relevant data from a preset number T (300 in this embodiment). Based on the melt temperature data in the barrel, nozzle temperature data, melt discharge temperature data, and cooling water flow rate data collected in each injection process, the barrel temperature sequence, nozzle temperature sequence, discharge temperature sequence, and flow rate sequence corresponding to each injection process are constructed according to the time sequence of data collection.

[0032] Next, after each injection process is completed, pressure holding, cooling and demolding, and quality inspection are performed to obtain the quality score data of the finished product corresponding to each injection process. The specific process for obtaining the quality score is as follows: existing visual inspection methods are used to inspect the quality of the produced router plastic casing and obtain a quality score. Visual inspection algorithms are not limited to image defect detection, classification recognition, and casing matching. In this embodiment, casing matching is used for quality inspection: the image of the produced finished casing is matched with the image of the casing of a standard sample; a perfect match results in a quality score of 100, and a complete mismatch results in a quality score of 0.

[0033] To eliminate the influence of dimensions between data, all data sequences are normalized. Normalization methods include Z-score, maximum value normalization, and maximum-minimum value normalization. This embodiment uses maximum-minimum value normalization.

[0034] Step 2: Based on the dispersion of cooling water flow data for each injection process, all injection processes are divided into cooling-involved processes and non-cooling-involved processes; the injection melt temperature of each cooling-involved process is divided into multiple subsequences, and each cooling subsequence is extracted.

[0035] When injection molding the plastic casing of a router, the melt inside the barrel already has a high temperature. Furthermore, when it exits the nozzle under pressure, it generates significant shear force at the nozzle, causing the melt temperature at the nozzle and the nozzle temperature to rise. This results in the injected melt temperature exceeding the preset value, affecting the injection molding effect. Therefore, existing technologies typically employ cooling systems to lower the melt temperature, thereby improving the quality of the finished router plastic casing.

[0036] When the cooling system is not operating to lower the temperature, i.e., the temperature of the injected melt is within the preset temperature range, the flow rate of the cooling water is low and relatively stable. However, if the cooling system is operating to lower the temperature, the flow rate of the cooling water will increase and become more variable. Therefore, by analyzing the changes in the flow rate of the cooling water, we can initially extract the cooling data of the injected melt, thus providing a data basis for subsequent adjustment of the cooling water flow rate.

[0037] The dispersion of the flow sequence for each injection process is calculated, and the dispersion of all flow sequences is used as input to the Otsu thresholding method. The output is a segmentation threshold, which is denoted as the preset segmentation threshold. Injection processes corresponding to flow sequences with dispersion greater than or equal to the preset segmentation threshold are denoted as cooling-involved processes; injection processes corresponding to flow sequences with dispersion less than the preset segmentation threshold are denoted as non-cooling-involved processes. The calculation of dispersion is not limited to variance, coefficient of variation, and standard deviation; variance is used in this embodiment.

[0038] Let's take the i-th cooling process as an example for analysis.

[0039] During the injection molding process of router casing molds, if the cooling system is not running, the injected melt temperature data will show a stable or rising trend; however, if the cooling system is running and participating in the melt cooling process, the injected melt temperature data will show a local downward trend.

[0040] Therefore, the injection temperature sequence in the i-th cooling process is divided into multiple sub-sequences using a sequence segmentation algorithm. Then, a linear fitting algorithm is used to fit a linear relationship to each of the segmented sub-sequences. Finally, the sub-sequence with a slope less than a preset slope threshold is recorded as the cooling sub-sequence of the i-th cooling process. In this embodiment, the preset slope threshold is set to 0. The sequence segmentation algorithm is not limited to the BG segmentation algorithm or the MK segmentation algorithm; the linear fitting algorithm is not limited to the least squares method or the polynomial fitting method.

[0041] In the same manner, obtain each cooling subsequence in each cooling process.

[0042] Thus, the cooling data from the melt temperature data during the operation of the cooling system was obtained, providing data support for the subsequent evaluation of the adjustment range of cooling water flow.

[0043] Step 3: Based on the change in mass score under unit initial nozzle temperature change during all injection processes, and the difference between the change amplitude of each cooling subsequence in each cooling process and the change amplitude of the corresponding cooling water flow rate data in the same time period, obtain the injection control sensitivity of each cooling process.

[0044] Furthermore, since injection molding is a classic batch production process with short intervals between batches, the nozzle temperature gradually increases after numerous injection steps, which in turn affects the temperature of the melt flowing through the nozzle. Therefore, to improve the stability of router casing injection molding quality, it is necessary to analyze the nozzle temperature differences at the beginning of injection.

[0045] Injection processes with a quality score greater than or equal to a preset score threshold (90 points in this embodiment) are designated as good injection processes. The first element of the nozzle temperature sequence for each injection process is designated as the initial nozzle temperature for that process. The absolute difference c1 between the average initial nozzle temperature of all good injection processes and all bad injection processes, and the absolute difference c2 between the average quality score of all good injection processes and all bad injection processes are calculated. The ratio of the absolute difference c2 to the absolute difference c1 is designated as the first ratio for all injection processes. This first ratio quantifies the impact of a unit temperature difference in the initial nozzle temperature on the quality of the injection-molded product when injection molding the router's casing. A larger value indicates a greater influence of the initial nozzle temperature on the quality of the finished casing, thus requiring a larger adjustment range for the control parameters.

[0046] It should be noted that during the calculation of the first ratio, when the denominator is 0, in order to ensure the normal operation of the first ratio, the denominator is taken from the range of [0.005, 0.01]. The value has a very small impact on the calculation and can be ignored. In this embodiment, 0.008 is taken.

[0047] Furthermore, since injection molding machines use the method of adjusting the cooling water flow rate for temperature regulation and control, it is also necessary to analyze the degree of change in the cooling water flow rate required for unit temperature adjustment in order to achieve precise regulation and control.

[0048] Let's take the i-th cooling process as an example for analysis. Since the temperature of the injected melt continuously rises due to shear force, nozzle temperature, and heat conduction, the cooling system may participate in the operation multiple times during a single injection. Therefore, to improve control accuracy, the flow sequence also needs to be processed.

[0049] Based on the time periods corresponding to each cooling subsequence in the i-th cooling process, obtain the flow subsequences for the same time period in the flow sequence of the i-th cooling process. Sort all cooling subsequences and all flow subsequences in the i-th cooling process according to time sequence, so that one flow subsequence corresponds to one cooling subsequence. Calculate the ratio of the internal range of each flow subsequence in the i-th cooling process to the internal range of the corresponding cooling subsequence in the same position, and record the average of all ratios as the flow variation factor of the i-th cooling process. The flow variation factor quantifies the degree of change in cooling water flow required to adjust the unit temperature of the injected melt. The larger the value, the greater the amplitude of the change in cooling water flow required to adjust the temperature of the injected melt in the i-th cooling process, and therefore the greater the adjustment degree required by the control algorithm.

[0050] As a preferred embodiment, the injection control sensitivity of each cooling process is obtained based on the change in mass score under a unit initial nozzle temperature change during all injection processes, and the difference between the change amplitude of each cooling subsequence in each cooling process and the change amplitude of the corresponding cooling water flow rate data in the same time period. This sensitivity is used to characterize the degree of sensitivity to melt temperature control in each cooling process.

[0051] In this embodiment, the injection control sensitivity of the i-th cooling process is denoted as . Its specific expression is: In the formula, For the injection control sensitivity of the i-th cooling process, This is the first ratio for all injection procedures. Let be the flow rate change factor in the i-th cooling process.

[0052] Injection control sensitivity reflects the magnitude of cooling water flow rate adjustment required due to initial nozzle temperature deviation. The higher the value, the greater the sensitivity of the router's injection molded shell quality to the initial nozzle temperature, and the greater the degree of cooling water regulation required to control the temperature of the injected melt. When controlling the temperature through cooling water flow rate, a larger adjustment is needed.

[0053] Step 4: Remove the data corresponding to the time period of all cooling subsequences in the data of melt temperature inside the barrel and melt temperature outside the injection barrel during each cooling process. Based on the changing trend of the temperature difference between the remaining melt temperature inside the barrel and melt temperature outside the injection barrel, as well as the number of cooling subsequences and injection control sensitivity in each cooling process, obtain the injection control amplitude of each cooling process.

[0054] Furthermore, in the melt injection molding process of router casings, the temperature of the injected melt is affected by various factors such as shear force and heat conduction from the nozzle, leading to temperature rise. When cooling the melt, if the cooling water flow rate is too low, the cooling effect will be insufficient, and the injected melt temperature will still be high; if the cooling water flow rate is too high, the cooling effect will be excessive, causing the injected melt temperature to fall below the preset value, both of which will affect the quality of the injection-molded product. Therefore, it is necessary to further quantify and analyze the temperature rise of the injected melt during the injection process to obtain the optimal cooling water flow rate.

[0055] Let's take the i-th cooling process as an example for analysis.

[0056] First, elements belonging to the cooling subsequence in the injection temperature sequence of the i-th cooling process are removed. The sequence of the remaining elements in chronological order is denoted as the new injection temperature sequence for the i-th cooling process. Simultaneously, based on the position of the elements in the cooling subsequence within the injection temperature sequence, elements at the corresponding positions are removed from the cylinder temperature sequence. The sequence of the remaining elements in the cylinder temperature sequence in chronological order is denoted as the new cylinder temperature sequence for the i-th cooling process, ensuring that the data length and sampling time of the new injection temperature sequence and the new cylinder temperature sequence are consistent. After removing the data corresponding to the cooling subsequence time period, the cooling system is in a non-operating phase at the time corresponding to the remaining data in the injection temperature sequence and the cylinder temperature sequence. Therefore, the temperature of the injection temperature sequence is always greater than or equal to the temperature of the cylinder temperature sequence.

[0057] Calculate the absolute difference between all elements of the same sequence in the newly injected temperature sequence and the newly generated cylinder temperature sequence. Sort all absolute differences in chronological order and perform linear fitting. The slope of the fitted line is denoted as the first slope of the i-th cooling process. The absolute difference between each corresponding sequence reflects the temperature change of the melt after passing through the nozzle. The larger the first slope, the greater the rate of temperature rise of the injected melt due to shear force and nozzle influence at the initial nozzle temperature of the i-th cooling process. Therefore, a larger proportional coefficient is required for control adjustment, thereby improving the control response speed of the cooling control system.

[0058] Therefore, based on the changing trend of the temperature difference between the new in-canister temperature sequence and the new injection temperature sequence, as well as the number of cooling sub-sequences and injection control sensitivity in each cooling process, the injection control amplitude of each cooling process is obtained to characterize the required response speed of the control system for each cooling process. The injection control amplitude of each cooling process is positively correlated with the injection control sensitivity of each cooling process, the total number of all cooling sub-sequences, and the first slope. The process for obtaining the injection control amplitude of each cooling process is as follows: Figure 2 As shown. It should be noted that the positive correlation refers to the dependent variable increasing (decreasing) as the independent variable increases (decreases).

[0059] Preferably, in this embodiment, the injection control amplitude of the i-th cooling process is denoted as... Its specific expression is: In the formula, The injection control amplitude for the i-th cooling process; Let be the total number of all cooling subsequences involved in the i-th cooling process. The larger the value, the more times the cooling system participates in cooling the melt at the initial nozzle temperature of the i-th cooling process, and the more proportion factor is needed. To control the sensitivity of injection during the plasticizing process; The first slope of the i-th cooling process; As a preset constant, in order to avoid the problem that the parameter is 0 and thus other parameters are meaningless, the value is taken from the range (0.001, 0.01). The value has little impact on the calculation and can be ignored. In this embodiment, 0.008 is taken.

[0060] Injection amplitude control It can reflect the magnitude of the proportional coefficient that needs to be adjusted in the i-th cooling process; the larger the value, the greater the proportional coefficient needs to be increased at the initial nozzle temperature in the i-th cooling process, so as to obtain a higher response speed and improve the injection molding quality of the finished product.

[0061] Step 5: Set the injection control amplitude of each non-cooling process to 0; cluster the initial nozzle temperature of the current injection process with the initial nozzle temperatures of all injection processes, and optimize the initial proportional coefficient of the current injection process based on the injection control amplitude of all other injection processes in the cluster where the initial nozzle temperature of the current injection process is located.

[0062] Furthermore, taking the current injection process as an example, the proportion coefficient of the current injection process is adjusted as follows.

[0063] The initial nozzle temperature w of the current injection process is obtained, and then the initial nozzle temperature w is clustered with the initial nozzle temperatures of all injection processes. The clustering algorithm is not limited to k-means algorithm, DPC algorithm, and DBSCAN algorithm. This embodiment uses the k-means algorithm to obtain the optimal number of clusters through the silhouette coefficient.

[0064] It should be noted that since the cooling system is not involved in the non-cooling process, there is no need to adjust the control parameters during the cooling process. Therefore, the injection control amplitude of all non-cooling processes should be set to 0 to avoid additional errors.

[0065] The cluster containing the initial nozzle temperature w of the current injection process is denoted as the regulation cluster of the current injection process. The mean value of the injection regulation amplitude of all other injection processes in the regulation cluster, excluding the current injection process, is calculated and denoted as the regulation factor of the current injection process.

[0066] Furthermore, based on the regulatory factors of the current injection process, the proportion coefficient of the current injection process is calculated. Its expression is: In the formula, This is the proportionality coefficient for the current injection process; The initial proportional coefficient preset for the current injection process is 1.2 in this embodiment; It is a regulatory factor in the current injection process; The normalization function is tanh; in this embodiment, the normalization function is tanh. The preset weighting coefficient is set to 2 in this embodiment to avoid excessive adjustment that could affect the stability of the control system.

[0067] During the current injection process, the control system generates control signals in real time based on the calculated proportional coefficient and the PID algorithm. These signals are used to adjust the cooling water flow in the cooling system, thereby dynamically adapting to the heat accumulation trend in the nozzle area, improving the response speed and stability of temperature control, and achieving precise control of the actual temperature of the melt.

[0068] Based on the same inventive concept as the above methods, this application also provides a router plastic shell injection molding intelligent control system, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of any one of the above-described router plastic shell injection molding intelligent control methods.

[0069] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, specific embodiments of this specification have been described above. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0070] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0071] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the principles of this application should be included within the protection scope of this application.

Claims

1. A method for intelligent control of router plastic casing injection molding, characterized in that, The method includes the following steps: The injection molding machine acquires barrel melt temperature data, nozzle temperature data, ejected melt temperature data, cooling water flow rate data, and quality score corresponding to each injection process for a preset number of injection processes. Based on the dispersion of cooling water flow data for each injection process, all injection processes are divided into cooling-involved processes and non-cooling-involved processes; the injection melt temperature of each cooling-involved process is divided into multiple subsequences, and each cooling subsequence is extracted. Based on the change in mass score under unit initial nozzle temperature change during all injection processes, and the difference between the change amplitude of each cooling subsequence in each cooling process and the change amplitude of the corresponding cooling water flow rate data in the same time period, the injection control sensitivity of each cooling process is obtained. The data corresponding to the time period of all cooling subsequences in the data of melt temperature inside the barrel and melt temperature injected during each cooling process are removed. Based on the changing trend of the temperature difference between the remaining melt temperature inside the barrel and melt temperature injected, as well as the number of cooling subsequences and injection control sensitivity in each cooling process, the injection control amplitude of each cooling process is obtained. Set the injection control amplitude of each non-cooling process to 0; cluster the initial nozzle temperature of the current injection process with the initial nozzle temperatures of all injection processes, and optimize the initial proportional coefficient of the current injection process based on the injection control amplitude of all other injection processes in the cluster where the initial nozzle temperature of the current injection process is located. The injection control sensitivity of each cooling-involved process refers to the product of the first ratio of all injection processes and the flow change factor of each corresponding cooling-involved process. The process of obtaining the first ratio of all injection processes is as follows: all injection processes with a quality score greater than or equal to a preset score threshold are recorded as good injection processes; the absolute difference c1 between the average initial nozzle temperature of all good injection processes and all bad injection processes, and the absolute difference c2 between the average quality score of all good injection processes and all bad injection processes are calculated respectively, and the ratio of the absolute difference c2 to the absolute difference c1 is recorded as the first ratio of all injection processes.

2. The intelligent control method for injection molding a router plastic casing as described in claim 1, characterized in that, The specific process of dividing all injection processes into cooling-involved processes and non-cooling-involved processes is as follows: calculate the variance of the cooling water flow data for each injection process, and record the injection process with a variance greater than or equal to a preset segmentation threshold as a cooling-involved process; record the injection process with a variance less than the preset segmentation threshold as a non-cooling-involved process.

3. The intelligent control method for injection molding a router plastic casing as described in claim 1, characterized in that, The specific process for extracting each cooling subsequence is as follows: the injection melt temperature data of each cooling process is divided into multiple subsequences, and the subsequences whose slope of the fitted line is less than a preset slope threshold are recorded as the cooling subsequences of each cooling process.

4. The intelligent control method for injection molding a router plastic casing as described in claim 1, characterized in that, The process for obtaining the flow rate change factor of each cooling process is as follows: based on the time period corresponding to each cooling subsequence in each cooling process, obtain each flow rate subsequence in the same time period in the flow rate sequence of each cooling process; sort all cooling subsequences and all flow rate subsequences in each cooling process according to the time sequence. Calculate the ratio of the internal range of each flow subsequence in each cooling process to the internal range of the corresponding cooling subsequence, and record the mean of all ratios as the flow change factor for each cooling process.

5. The intelligent control method for injection molding a router plastic casing as described in claim 1, characterized in that, The injection control amplitude of each cooling process is positively correlated with the injection control sensitivity of each cooling process, the total number of all cooling subsequences, and the first slope.

6. The intelligent control method for injection molding a router plastic casing as described in claim 5, characterized in that, The process of obtaining the first slope of each cooling process is as follows: the in-bottle melt temperature data and the injection melt temperature data of each injection process are respectively arranged in chronological order and recorded as the in-bottle temperature sequence and injection temperature sequence of each injection process; elements belonging to the cooling subsequence are removed from the injection temperature sequence of each cooling process, and the sequence of the remaining elements arranged in chronological order is recorded as the new injection temperature sequence of each cooling process; at the same time, according to the position of the elements in the cooling subsequence of each cooling process in the injection temperature sequence, the elements of the corresponding position are removed from the in-bottle temperature sequence, and the sequence of the remaining elements in the in-bottle temperature sequence arranged in chronological order is recorded as the new in-bottle temperature sequence of each cooling process.

7. The intelligent control method for injection molding a router plastic casing as described in claim 1, characterized in that, The calculation formula for optimizing the initial proportional coefficient of the current injection process is as follows: In the formula, This is the proportionality coefficient for the current injection process; The initial proportional coefficient preset for the current injection process; It is a regulatory factor in the current injection process; This is the normalization function; These are preset weighting coefficients.

8. The intelligent control method for injection molding a router plastic casing as described in claim 7, characterized in that, The process of obtaining the control factor of the current injection process is as follows: obtain the initial nozzle temperature w of the current injection process, cluster the initial nozzle temperature w with the initial nozzle temperatures of all injection processes; and record the average value of the injection control amplitude of all other injection processes in the cluster containing the initial nozzle temperature w of the current injection process as the control factor of the current injection process.

9. A router plastic shell injection molding intelligent control system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the intelligent control method for injection molding of a router plastic shell as described in any one of claims 1-8.

Images