Intelligent injection mold control system and method based on industrial internet

Abstract

The invention discloses an intelligent injection mold control system and method based on the industrial internet, and relates to the technical field of molds, in the step S1 and the step S2, based on the process before a melt is injected into a mold, the temperature difference value Wcy of each monitoring time period is analyzed, the temperature difference value Wcy is associated with the defect rate Lcp of a formed product, and a quality correlation index Zzg is calculated; and in the steps S3, S4 and S5, after an early warning instruction is received, temperature sensors deployed around the mold collect temperature distribution information and mold body temperature distribution state in real time after the mold is filled with the melt, and finite element analysis is combined to determine whether the mold body is filled with the melt. According to the method, a melt temperature distribution equilibrium index Zbh and a mold temperature distribution equilibrium index Zfb are obtained, a quality correlation index Zzg is introduced, deep learning fitting is carried out, an obtained heat influence evaluation index Zry is compared with an influence threshold Y, and a corresponding control instruction is generated and executed.

Description

Technical Field

[0001] The present invention relates to the field of mold technology, and specifically to an intelligent control system and method for injection molds based on industrial Internet. Background Art

[0002] As the basic process equipment in the manufacturing industry, molds are widely used in many fields such as automobiles, electronics, home appliances and medical care. Among the many types of molds, injection molds are highly valued because they can produce plastic products with high precision and complex structures. With the development of industrialization, the production efficiency and quality requirements of injection molds are constantly improving. The traditional manual experience-based control mode is gradually unable to meet the needs of modern production. In order to cope with the increasingly complex production process and quality control, intelligent control technology has emerged, especially intelligent control systems based on the industrial Internet, which can improve the stability and quality of the injection molding process through real-time data collection, analysis and feedback, and promote the transformation of the manufacturing industry to intelligence.

[0003] In the current intelligent control system of injection molds, the balance of mold and melt temperature distribution is one of the key factors affecting product quality. Uneven temperature distribution can cause defects in injection molded products, such as warping, uneven shrinkage and stress concentration, affecting the mechanical properties and appearance quality of the product. Existing means are insufficient in monitoring and adjusting the melt and mold temperature, especially the temperature changes when the melt is injected into the mold and the real-time monitoring and control of the temperature distribution status of different parts of the mold. This makes it impossible to respond to temperature anomalies in a timely manner, thus affecting the quality of the final product. Therefore, introducing more accurate temperature monitoring, deep learning technology and automated control methods based on the industrial Internet is the key to improving the intelligent control of injection molds. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides an intelligent control system and method for injection molds based on the industrial Internet, which solves the problems in the above-mentioned background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: an intelligent control method for injection molds based on industrial Internet, comprising:

[0006] S1. Obtaining melt temperature data information according to the temperature state of the melt before being injected into the mold, and obtaining mold temperature data information by monitoring the mold temperature state before the melt is injected into the mold, and also used to obtain the molded product defective rate Lcp by connecting to the Internet product inspection database;

[0007] S2, analyzing the melt temperature data information and mold body temperature data information in step S1, obtaining the temperature difference value Wcy in each monitoring time period, and correlating the temperature difference value Wcy in each monitoring time period with the product defective rate Lcp, analyzing the influence of the difference between the melt temperature and the mold body temperature on the product quality, so as to generate a quality correlation index Zzg, and compare and analyze it with the preset correlation threshold G to determine whether to issue a preliminary warning instruction;

[0008] S3. After receiving the preliminary warning instruction, a plurality of groups of temperature sensors are deployed around the mold to collect the temperature distribution information of the melt after the melt fills the mold in real time, and to obtain the temperature distribution status information of the mold body according to the temperature distribution of each position of the mold body after the melt fills the mold;

[0009] S4. Using convolutional neural network learning technology, convolutional neural network feature extraction is performed on the melt temperature distribution information and the mold body temperature distribution state information, and the finite element analysis model is used for calculation to obtain the melt temperature distribution balance index Zbh and the mold temperature distribution balance index Zfb respectively. By introducing the quality correlation index Zzg and after machine deep learning technology and dimensionless processing, the thermal impact assessment index Zry is obtained by fitting;

[0010] S5. Compare and analyze the thermal impact assessment index Zry obtained in step S4 with a preset impact threshold Y, obtain corresponding control instructions and execute them.

[0011] Preferably, the actual temperature of the melt before being injected into the mold is monitored by temperature sensors deployed in the melt flow channel and the injector to obtain melt temperature data information, wherein the melt temperature data information includes the pre-injection melt temperature value Dzr in each monitoring time period;

[0012] The temperature state of the mold body before the melt is injected into the mold body is monitored in real time by temperature sensors deployed around the mold body, and the temperature data information of the mold body in the corresponding monitoring time period is recorded to obtain the mold body temperature data information, wherein the mold body temperature data information includes the mold body temperature value Dmt before injection in each monitoring time period;

[0013] Through Internet technology, the products produced in each monitoring period are quality inspected to obtain the product defect rate Lcp in each monitoring period and upload it to the cloud platform.

[0014] Preferably, the melt temperature data information and the mold body temperature data information in step S1 are analyzed, and after dimensionless processing, a temperature difference value Wcy in a corresponding monitoring time period is obtained;

[0015] The temperature difference value Wcy in each monitoring time period is correlated with the product defect rate Lcp, and the influence of the difference between the melt temperature and the mold body temperature on the product quality is analyzed to generate a quality correlation index Zzg.

[0016] Preferably, a correlation threshold G is preset, and the correlation threshold G is compared and analyzed with the quality correlation index Zzg to determine whether the difference between the melt temperature and the mold body temperature has an impact on the product quality. The specific contents are as follows:

[0017] If the quality correlation index Zzg> the correlation threshold G, it means that the difference between the current melt temperature and the mold body temperature has an impact on the product quality, and a preliminary warning instruction is issued. At this time, the temperature will be further analyzed;

[0018] If the quality correlation index Zzg is less than the correlation threshold G, it means that the difference between the current melt temperature and the mold body temperature has an impact on the product quality, and a preliminary warning instruction is issued. At this time, the temperature will be further analyzed;

[0019] If the quality correlation index Zzg=the correlation threshold G, it means that the difference between the current melt temperature and the mold body temperature has no impact on the product quality, and no additional control instruction is issued at this time.

[0020] Preferably, after receiving the preliminary warning instruction, a plurality of groups of temperature sensors are deployed at multiple positions to collect the melt temperature distribution information at each point in the cavity in real time after the melt fills the mold, and obtain the melt temperature distribution information; and the temperature distribution information of the mold at each point on the mold surface is collected in real time after the melt fills the mold, and obtain the mold temperature distribution information;

[0021] The convolutional neural network processes the acquired melt temperature change information and mold temperature distribution information through multiple convolution layers and pooling layers, extracts the characteristics of melt temperature change with space and the characteristics of mold temperature in spatial distribution. The melt temperature distribution information includes the melt temperature value Drt at each point; the mold temperature distribution information includes the mold temperature value Dmj at each point.

[0022] Preferably, a finite element analysis model is used to simulate the flow and heat transfer process of the melt in the mold, analyze the melt temperature distribution at each point in the cavity after the melt fills the mold, and obtain the melt temperature distribution equilibrium index Zbh.

[0023] Preferably, a finite element analysis model is used to simulate the change in mold surface temperature after the melt fills the mold, analyze the mold temperature distribution at each point on the mold surface after the melt fills the mold, and obtain the mold temperature distribution balance index Zfb.

[0024] Preferably, the melt temperature distribution equilibrium index Zbh and the mold temperature distribution equilibrium index Zfb are obtained by introducing the quality correlation index Zzg, and after machine deep learning technology and dimensionless processing, the heat impact assessment index Zry is fitted.

[0025] Preferably, the thermal impact assessment index Zry obtained in step S4 is compared and analyzed with a preset impact threshold Y to obtain a corresponding control instruction, and the specific content of the control instruction is as follows:

[0026] If the thermal impact assessment index Zry≤the impact threshold Y, it means that the temperature state of the melt and the mold body during the process of injecting the melt into the mold is in a normal state for the time being, and no additional control instructions are issued at this time, and the current injection molding process is continued;

[0027] If the thermal impact assessment index Zry> the impact threshold Y, it means that the temperature state of the melt and the mold body during the process of injecting the melt into the mold is abnormal for the current situation, and a control instruction is issued;

[0028] The specific execution content of the control instruction is: stop the current injection molding process, issue an early warning prompt, and recommend manual intervention for inspection and adjustment, including checking whether there is a hardware failure in the heater and cooler, adjusting the heating system of the injection molding machine in real time, and adjusting the difference between the melt temperature and the mold body temperature to keep it within a reasonable range; and based on machine deep learning technology, continuously analyze historical data and current temperature status to optimize the process settings for the next injection molding cycle.

[0029] An intelligent control system for injection molds based on the industrial Internet, comprising a monitoring module, a correlation analysis module, a temperature acquisition module, a heat impact analysis module and a control module;

[0030] The monitoring module is used to obtain melt temperature data information according to the temperature state of the melt before being injected into the mold, and to obtain mold body temperature data information by monitoring the mold body temperature state before the melt is injected into the mold, and is also used to obtain the molded product defect rate Lcp by connecting to the Internet product inspection database;

[0031] The correlation analysis module is used to analyze the melt temperature data information and the mold body temperature data information to obtain the temperature difference value Wcy in each monitoring time period, and is also used to correlate the temperature difference value Wcy in each monitoring time period with the product defect rate Lcp, analyze the influence of the difference between the melt temperature and the mold body temperature on the product quality, so as to generate a quality correlation index Zzg, and compare and analyze it with the preset correlation threshold G to determine whether to issue a preliminary warning instruction;

[0032] The temperature acquisition module is used to collect the temperature distribution information of the melt after the melt fills the mold in real time by deploying a plurality of groups of temperature sensors around the mold after receiving the preliminary warning instruction, and also obtain the temperature distribution status information of the mold body according to the temperature distribution of each position of the mold body after the melt fills the mold;

[0033] The thermal impact analysis module is used to use convolutional neural network learning technology to perform convolutional neural network feature extraction on the melt temperature distribution information and the mold body temperature distribution state information, and calculate through a finite element analysis model to obtain the melt temperature distribution balance index Zbh and the mold temperature distribution balance index Zfb respectively, and by introducing the quality correlation index Zzg and after machine deep learning technology and dimensionless processing, the thermal impact assessment index Zry is obtained by fitting;

[0034] The control module is used to compare and analyze the obtained thermal impact assessment index Zry with a preset impact threshold Y, obtain corresponding control instructions and execute them.

[0035] The present invention provides an intelligent control system and method for injection molds based on the industrial Internet, which has the following beneficial effects:

[0036] (1) Through systematic data monitoring and analysis methods, the intelligence and accuracy of the injection molding production process are improved, the melt and mold temperature information is acquired and analyzed in real time, and the potential impact of the temperature difference value Wcy between the melt and the mold before injection on the product quality is identified, so as to provide early warning and automatically adjust the injection molding process. This not only reduces the need for manual intervention, but also provides in-depth analysis of temperature distribution balance through convolutional neural networks and finite element technology. Through comprehensive analysis of the quality correlation index Zzg and the heat impact assessment index Zry, control instructions can be automatically generated and executed when the temperature is abnormal, especially the real-time monitoring and control of the temperature change when the melt is injected into the mold and the temperature distribution status of different parts of the mold, so as to make timely responses to temperature abnormalities, thereby improving the quality of the final product, reducing material waste, improving production efficiency, and ultimately reducing production costs, thereby improving the automation level and economic benefits of the production line.

[0037] (2) By obtaining melt temperature data information and mold temperature data information, the system can effectively predict and prevent product defects caused by abnormal temperature. In particular, after obtaining the defective rate Lcp of the molded product through the Internet product inspection database, the system can correlate the temperature data with the product quality and generate a quality correlation index Zzg. This process helps to identify and analyze the impact of the difference between melt temperature and mold temperature on product quality, providing a scientific basis for subsequent analysis.

[0038] (3) Multiple temperature sensors are deployed to collect the temperature distribution information of the melt and the mold in real time, and convolutional neural networks are used for feature extraction. The melt temperature distribution balance index Zbh and the mold temperature distribution balance index Zfb are calculated in combination with the finite element analysis model. The heat impact assessment index Zry optimized by machine deep learning technology guides the control operation. When the heat impact assessment index Zry exceeds the preset impact threshold Y, the system will automatically issue control instructions for adjustment, thereby preventing production defects caused by uneven temperature, ensuring the high-quality production of injection molded products, and improving the stability and reliability of the production process. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 This is a schematic diagram of the steps of an intelligent control method for injection molds based on the industrial Internet of the present invention;

[0040] Figure 2 This is a block diagram of an intelligent control system for injection molds based on the Industrial Internet in the present invention. DETAILED DESCRIPTION

[0041] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0042] Example 1

[0043] See also Figure 1 The present invention provides an intelligent control method for injection molds based on industrial Internet, comprising:

[0044] S1. Obtaining melt temperature data information according to the temperature state of the melt before being injected into the mold, and obtaining mold temperature data information by monitoring the mold temperature state before the melt is injected into the mold, and also used to obtain the molded product defective rate Lcp by connecting to the Internet product inspection database;

[0045] S2, analyzing the melt temperature data information and mold body temperature data information in step S1, obtaining the temperature difference value Wcy in each monitoring time period, and correlating the temperature difference value Wcy in each monitoring time period with the product defective rate Lcp, analyzing the influence of the difference between the melt temperature and the mold body temperature on the product quality, so as to generate a quality correlation index Zzg, and compare and analyze it with the preset correlation threshold G to determine whether to issue a preliminary warning instruction;

[0046] S3. After receiving the preliminary warning instruction, a plurality of groups of temperature sensors are deployed around the mold to collect the temperature distribution information of the melt after the melt fills the mold in real time, and to obtain the temperature distribution status information of the mold body according to the temperature distribution of each position of the mold body after the melt fills the mold;

[0047] S4. Using convolutional neural network learning technology, convolutional neural network feature extraction is performed on the melt temperature distribution information and the mold body temperature distribution state information, and the finite element analysis model is used for calculation to obtain the melt temperature distribution balance index Zbh and the mold temperature distribution balance index Zfb respectively. By introducing the quality correlation index Zzg and after machine deep learning technology and dimensionless processing, the thermal impact assessment index Zry is obtained by fitting;

[0048] S5. Compare and analyze the thermal impact assessment index Zry obtained in step S4 with a preset impact threshold Y, obtain corresponding control instructions and execute them.

[0049] In this embodiment, through the intelligent control method of injection molds based on the industrial Internet, real-time monitoring and analysis of the temperature status of the melt and mold can be achieved, and deep learning calculations can be performed with product quality-related data to generate a quality correlation index Zzg and a heat impact assessment index Zry. Through convolutional neural network feature extraction and finite element analysis, the uniformity of temperature distribution and its impact on product quality can be evaluated, thereby effectively predicting and warning of abnormal situations in production. Combined with the generation and execution of automatic control instructions, the system can quickly make adjustments to keep the melt and mold temperature status within a reasonable range, thereby improving the quality of molded products and reducing the defective rate.

[0050] Example 2

[0051] Please refer to Figure 1 Specifically: the actual temperature of the melt before being injected into the mold is monitored by temperature sensors deployed in the melt flow channel and the injector to obtain melt temperature data information, wherein the melt temperature data information before injection includes the melt temperature value Dzr before injection in each monitoring time period;

[0052] The temperature state of the mold body before the melt is injected into the mold body is monitored in real time by temperature sensors deployed around the mold body, and the temperature data information of the mold body in the corresponding monitoring time period is recorded to obtain the mold body temperature data information, wherein the mold body temperature data information includes the mold body temperature value Dmt before injection in each monitoring time period;

[0053] Through Internet technology, the products produced in each monitoring period are quality inspected to obtain the product defect rate Lcp in each monitoring period and upload it to the cloud platform.

[0054] In this embodiment, by deploying temperature sensors in the melt flow channel and the syringe, the actual temperature information of the melt before being injected into the mold can be monitored in real time, and the pre-injection melt temperature value Dzr in each monitoring time period can be accurately obtained, thereby providing data support for temperature control during melt injection. At the same time, the temperature sensors deployed around the mold can monitor the temperature state of the mold before melt injection in real time, and record the mold body temperature value Dmt before injection. Through the combination of Internet technology and cloud platform, the product quality inspection results in each monitoring time period, the product defective rate Lcp is obtained, and then uploaded to the cloud platform in real time, to realize online monitoring and data storage of product quality. Through this intelligent monitoring method, effective monitoring of temperature parameters in the production process can be realized, so that the entire injection molding process can be monitored intelligently and efficiently.

[0055] Example 3

[0056] Please refer to Figure 1 Specifically: the melt temperature data information and the mold body temperature data information are analyzed, and after dimensionless processing, the temperature difference value Wcy in the corresponding monitoring time period is obtained, and the temperature difference value Wcy is obtained by the following formula;

[0057] Wcy=|Dzr-Dmt|;

[0058] In the formula, Dzr represents the melt temperature before injection, and Dmt represents the mold temperature before injection;

[0059] It should be noted that an increase in the temperature difference value Wcy will cause the melt to have too weak fluidity after entering the mold, resulting in uneven filling. This uneven filling will cause internal defects and uneven appearance of the product, and will also cause inconsistent cooling rates of the melt and the mold. This inconsistent cooling will cause the product to warp, deform and crack.

[0060] The temperature difference value Wcy in each monitoring time period is correlated with the product defect rate Lcp, and the influence of the difference between the melt temperature and the mold body temperature on the product quality is analyzed to generate a quality correlation index Zzg, and the quality correlation index Zzg is obtained by the following formula;

[0061]

[0062] Where Wcy i Expressed as the temperature difference value in the i-th monitoring period, Lcp i It is expressed as the defective rate of products in the i-th monitoring period, It is expressed as the mean value of the temperature difference during the monitoring period. It is expressed as the mean value of the product defective rate within the monitoring period, i=1, 2, 3, ..., n, where n is the monitoring period.

[0063] Specifically, a correlation threshold G is preset, and the correlation threshold G is compared and analyzed with the quality correlation index Zzg to determine whether the difference between the melt temperature and the mold body temperature has an impact on the product quality. The specific contents are as follows:

[0064] If the quality correlation index Zzg> the correlation threshold G, it means that the difference between the current melt temperature and the mold body temperature has an impact on the product quality, and a preliminary warning instruction is issued. At this time, the temperature will be further analyzed;

[0065] If the quality correlation index Zzg is less than the correlation threshold G, it means that the difference between the current melt temperature and the mold body temperature has an impact on the product quality, and a preliminary warning instruction is issued. At this time, the temperature will be further analyzed;

[0066] If the quality correlation index Zzg=the correlation threshold G, it means that the difference between the current melt temperature and the mold body temperature has no impact on the product quality, and no additional control instruction is issued at this time.

[0067] In this embodiment, by analyzing and processing the temperature data information before melt injection and the temperature data information before mold injection, the temperature difference value Wcy can be obtained after dimensionless processing, which effectively eliminates the influence of data units, so that data under different temperature states can be directly compared to ensure the accuracy of the calculation results. Through the correlation analysis of the temperature difference value Wcy and the product defect rate Lcp, the influence of the difference between the melt temperature and the mold temperature on the product quality can be reflected. The quality correlation index Zzg generated at this time can quantify the influence of this difference on the product defect rate, which provides a reliable basis for judging the influence of the temperature state on the product quality during the production process. By introducing a preset correlation threshold G, by comparing and analyzing the quality correlation index Zzg with the correlation threshold G, it can be determined whether to conduct further analysis on the temperature. When the quality correlation index Zzg is greater than the correlation threshold G, the system can automatically issue a preliminary early warning instruction, indicating that the current temperature difference affects the product quality and requires further analysis of the temperature distribution and adjustment. Conversely, when the quality correlation index Zzg is less than or equal to the correlation threshold G, it is considered that the temperature state temporarily affects the product quality and no additional control instructions are required. Through this intelligent control strategy, the impact of the difference in melt temperature and mold temperature in production on product quality can be identified in advance.

[0068] Example 4

[0069] Please refer to Figure 1Specifically: after receiving the preliminary warning instruction, by deploying several groups of temperature sensors at multiple locations, after the melt fills the mold, the melt temperature distribution information at each point in the cavity is collected in real time to obtain the melt temperature distribution information; it is also used to collect the mold temperature distribution information at each point on the mold surface in real time after the melt fills the mold to obtain the mold temperature distribution information;

[0070] The convolutional neural network processes the acquired melt temperature change information and mold temperature distribution information through multiple convolution layers and pooling layers, extracts the characteristics of melt temperature change with space and the characteristics of mold temperature in spatial distribution. The melt temperature distribution information includes the melt temperature value Drt at each point; the mold temperature distribution information includes the mold temperature value Dmj at each point.

[0071] The convolutional neural network is a deep learning model specifically designed to process data with a grid structure. By simulating the mechanism of the biological visual system, the convolutional layer is used to extract local features in the image, which are then abstracted and combined layer by layer to identify higher-level patterns. The convolutional layer performs local operations on the image in a sliding window manner to automatically extract features without the need for manually designed feature extraction algorithms. Afterwards, the pooling layer is used to reduce the dimension and computational complexity of the features while retaining key features. The hierarchical structure of the data is gradually learned through stacking, which is suitable for image recognition and can automatically learn and optimize features from the data, thereby improving the accuracy of prediction and the generalization ability of the model.

[0072] In this embodiment, by deploying temperature sensors at multiple points, the system can collect in real time the melt temperature distribution information of each point in the cavity after the melt fills the mold and the mold temperature distribution information of each point on the mold surface, providing a basis for subsequent quality control. The convolutional neural network processes the temperature distribution information obtained through multiple convolutional layers and pooling layers, which can not only extract the characteristics of the melt temperature changing with space, but also capture the subtle differences in the spatial distribution of the mold surface temperature, thereby reflecting the temperature change law during the injection molding process, and can analyze the temperature distribution state of the melt and the mold, and generate a corresponding temperature balance index. By analyzing the melt temperature value Drt and the mold temperature value Dmj, the system can identify potential problems of temperature imbalance during the injection molding process, thereby helping to optimize the injection molding process. The monitoring and analysis of temperature distribution helps to timely discover hidden dangers in product quality and reduce the defective rate. In addition, the mold temperature control system can also be automatically adjusted to achieve balanced temperature control, improve production efficiency, reduce energy consumption, and improve the overall quality of the product.

[0073] Example 5

[0074] Please refer to Figure 1Specifically: the finite element analysis model is used to simulate the flow and heat transfer process of the melt in the mold, the melt temperature distribution at each point in the cavity after the melt is filled with the mold is analyzed, and the melt temperature distribution balance index Zbh is obtained. The melt temperature distribution balance index Zbh is obtained by the following formula;

[0075]

[0076] In the formula, It is expressed as the maximum temperature of the melt at the jth melt point. It is represented as the minimum melt temperature value of the jth melt point, where σDrt is represented as the standard deviation of the melt temperature value, and ∈ is represented as the first correction constant.

[0077] Specifically, a finite element analysis model is used to simulate the temperature change of the mold surface after the melt is filled into the mold, and the mold temperature distribution at each point on the mold surface after the melt is filled into the mold is analyzed to obtain the mold temperature distribution balance index Zfb. The mold temperature distribution balance index Zfb is obtained by the following formula;

[0078]

[0079] In the formula, It is expressed as the maximum temperature value of the phantom at the s-th phantom point. It is represented as the minimum temperature value of the model at the s-th model point, where σDmj is represented as the standard deviation of the model temperature value, and θ is represented as the second correction constant.

[0080] It should be noted that the uneven temperature distribution of the melt and the mold will further lead to inconsistent melt fluidity, resulting in uneven filling. This uneven filling will cause the product to be underfilled, have bubbles, flow marks and surface defects. It will also affect the cooling rate of the melt in the mold. The melt in the higher temperature area cools more slowly, resulting in uneven internal stress in the product, which will cause warping, deformation and stress cracking quality problems. Due to the different degrees of cooling and solidification of the melt in different areas, the physical properties of the product will also be different.

[0081] In this embodiment, the finite element analysis model is used to simulate the flow and heat transfer process of the melt in the mold, and the temperature distribution of the melt in the mold can be analyzed to obtain the melt temperature distribution balance index Zbh. The melt temperature distribution balance index Zbh can reflect the uniformity of the melt temperature by evaluating the maximum and minimum temperatures of the melt at each point in the mold and combining the standard deviation calculation. This process helps to identify the temperature non-uniformity phenomenon in the melt flow and heat transfer process, and provides important data support for improving mold design and process control. Similarly, the finite element model is used to analyze the change in mold surface temperature, which can be used to obtain the melt temperature distribution balance index Zbh. To obtain the mold temperature distribution balance index Zfb, the mold temperature distribution balance index Zfb can reflect the balance of the mold temperature by calculating the maximum and minimum temperatures of each point on the mold surface in combination with the standard deviation. By obtaining and analyzing the melt temperature distribution balance index Zbh and the mold temperature distribution balance index Zfb, the temperature state of the melt and the mold can be monitored and optimized, and product defects caused by uneven temperature during the injection molding process can be reduced, thereby improving the consistency and quality stability of the finished product, which not only improves production efficiency, but also effectively reduces material waste and production costs, while ensuring product quality.

[0082] Example 6

[0083] Please refer to Figure 1 Specifically: the melt temperature distribution balance index Zbh and the mold temperature distribution balance index Zfb are obtained by introducing the quality correlation index Zzg, and after machine deep learning technology and dimensionless processing, the heat impact assessment index Zry is fitted;

[0084]

[0085] Where β1, β2 and β3 represent the weight values ​​of melt temperature distribution balance index Zbh, mold temperature distribution balance index Zfb and quality correlation index Zzg respectively. Expressed as the third correction constant.

[0086] Specifically, the obtained thermal impact assessment index Zry is compared and analyzed with a preset impact threshold Y to obtain a corresponding control instruction, and the specific content of the control instruction is as follows:

[0087] If the thermal impact assessment index Zry≤the impact threshold Y, it means that the temperature state of the melt and the mold body during the process of injecting the melt into the mold is in a normal state for the time being, and no additional control instructions are issued at this time, and the current injection molding process is continued;

[0088] If the thermal impact assessment index Zry> the impact threshold Y, it means that the temperature state of the melt and the mold body during the process of injecting the melt into the mold is abnormal for the current situation, and a control instruction is issued;

[0089] The specific execution content of the control instruction is: stop the current injection molding process, issue an early warning prompt, and recommend manual intervention for inspection and adjustment, including checking whether there is a hardware failure in the heater and cooler, adjusting the heating system of the injection molding machine in real time, and adjusting the difference between the melt temperature and the mold body temperature to keep it within a reasonable range; and based on machine deep learning technology, continuously analyze historical data and current temperature status to optimize the process settings for the next injection molding cycle.

[0090] In this embodiment, by introducing the melt temperature distribution balance index Zbh, the mold temperature distribution balance index Zfb and the quality correlation index Zzg, and combining the machine deep learning technology and the dimensionless processing method, the heat impact assessment index Zry is generated, which can improve the intelligent control ability of the injection molding process. Specifically, by comparing and analyzing the heat impact assessment index Zry with the preset impact threshold Y, the temperature state of the melt and the mold can be monitored in real time, and abnormal conditions can be identified. When the heat impact assessment index Zry exceeds the impact threshold Y, the system will immediately issue a control instruction, automatically stop the current injection molding process and issue an early warning prompt. This mechanism can not only prevent the injection molding process caused by abnormal temperature, but also prevent the injection molding process from being stopped. It can not only identify product quality problems, but also promptly guide manual inspections and adjustments, including troubleshooting of heaters and coolers, and real-time adjustment of the heating system of the injection molding machine. By adjusting the temperature difference value and in-depth analysis of historical data, it can optimize the process settings for the next injection molding cycle and improve production stability and product consistency. This comprehensive control method reduces material waste and production costs caused by uneven temperature, improves product quality and production efficiency, and ensures high-standard control of the injection molding process. This not only improves the level of production automation, but also strengthens the ability to predict and manage potential problems in complex production environments, and has economic benefits and technological innovation value.

[0091] Example 7

[0092] Please refer to Figure 1 and Figure 2 ,Specifically: An intelligent control system for injection mold based on industrial Internet, including a monitoring module, a correlation analysis module, a temperature acquisition module, a heat impact analysis module and a control module;

[0093] The monitoring module is used to obtain melt temperature data information according to the temperature state of the melt before being injected into the mold, and to obtain mold body temperature data information by monitoring the mold body temperature state before the melt is injected into the mold, and is also used to obtain the molded product defect rate Lcp by connecting to the Internet product inspection database;

[0094] The correlation analysis module is used to analyze the melt temperature data information and the mold body temperature data information to obtain the temperature difference value Wcy in each monitoring time period, and is also used to correlate the temperature difference value Wcy in each monitoring time period with the product defect rate Lcp, analyze the influence of the difference between the melt temperature and the mold body temperature on the product quality, so as to generate a quality correlation index Zzg, and compare and analyze it with the preset correlation threshold G to determine whether to issue a preliminary warning instruction;

[0095] The temperature acquisition module is used to collect the temperature distribution information of the melt after the melt fills the mold in real time by deploying a plurality of groups of temperature sensors around the mold after receiving the preliminary warning instruction, and also obtain the temperature distribution status information of the mold body according to the temperature distribution of each position of the mold body after the melt fills the mold;

[0096] The thermal impact analysis module is used to use convolutional neural network learning technology to perform convolutional neural network feature extraction on the melt temperature distribution information and the mold body temperature distribution state information, and calculate through a finite element analysis model to obtain the melt temperature distribution balance index Zbh and the mold temperature distribution balance index Zfb respectively, and by introducing the quality correlation index Zzg and after machine deep learning technology and dimensionless processing, the thermal impact assessment index Zry is obtained by fitting;

[0097] The control module is used to compare and analyze the obtained thermal impact assessment index Zry with a preset impact threshold Y, obtain corresponding control instructions and execute them.

[0098] In this embodiment, the intelligent control system for injection molds based on the industrial Internet improves the intelligent management level of the injection molding process by integrating a monitoring module, a correlation analysis module, a temperature acquisition module, a heat impact analysis module and a control module. The system first obtains the melt temperature data information and the mold body temperature data information in real time through the monitoring module, and obtains the defective rate Lcp of the molded product through the Internet product detection database. The correlation analysis module conducts an in-depth analysis of the temperature data information of the melt and the mold body, calculates the temperature difference value Wcy and associates it with the product defective rate Lcp to generate a quality correlation index Zzg. By comparing it with the preset correlation threshold G, the system can determine whether there is a situation where a preliminary warning needs to be issued. After receiving the warning, the temperature acquisition module arranges temperature sensors around the mold. The sensor collects the temperature distribution information of the melt and the mold in real time. The heat impact analysis module uses the convolutional neural network to extract the temperature distribution characteristics, and calculates the melt temperature distribution balance index Zbh and the mold temperature distribution balance index Zfb through the finite element analysis model. It combines the quality correlation index Zzg for deep learning and dimensionless processing to generate the heat impact assessment index Zry. The control module compares Zry with the preset impact threshold Y and automatically issues control instructions to adjust the injection molding process. This system can not only monitor and optimize the temperature status of the melt and the mold in real time to prevent product defects caused by abnormal temperature, but also optimize the production process through intelligent analysis and deep learning, improve product quality and production efficiency, reduce the need for manual intervention, and improve the automation and intelligence level of the production line.

[0099] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent control method for injection molds based on industrial Internet, characterized in that: include, S1. Obtaining melt temperature data information according to the temperature state of the melt before being injected into the mold, and obtaining mold temperature data information by monitoring the mold temperature state before the melt is injected into the mold, and also used to obtain the molded product defective rate Lcp by connecting to the Internet product inspection database; S2, analyzing the melt temperature data information and mold body temperature data information in step S1, obtaining the temperature difference value Wcy in each monitoring time period, and correlating the temperature difference value Wcy in each monitoring time period with the product defective rate Lcp, analyzing the influence of the difference between the melt temperature and the mold body temperature on the product quality, so as to generate a quality correlation index Zzg, and compare and analyze it with the preset correlation threshold G to determine whether to issue a preliminary warning instruction; S3. After receiving the preliminary warning instruction, a plurality of groups of temperature sensors are deployed around the mold to collect the temperature distribution information of the melt after the melt fills the mold in real time, and to obtain the temperature distribution status information of the mold body according to the temperature distribution of each position of the mold body after the melt fills the mold; S4. Using convolutional neural network learning technology, convolutional neural network feature extraction is performed on the melt temperature distribution information and the mold body temperature distribution state information, and the finite element analysis model is used for calculation to obtain the melt temperature distribution balance index Zbh and the mold temperature distribution balance index Zfb respectively. By introducing the quality correlation index Zzg and after machine deep learning technology and dimensionless processing, the thermal impact assessment index Zry is obtained by fitting; S5. Compare and analyze the thermal impact assessment index Zry obtained in step S4 with a preset impact threshold Y, obtain corresponding control instructions and execute them.

2. According to the method of intelligent control of injection molds based on industrial Internet according to claim 1, it is characterized in that: The actual temperature of the melt before being injected into the mold is monitored by temperature sensors deployed in the melt flow channel and the injector to obtain melt temperature data information; the melt temperature data information includes the pre-injection melt temperature value Dzr in each monitoring time period; The temperature state of the mold body before the melt is injected into the mold body is monitored in real time by temperature sensors deployed around the mold body, and the temperature data information of the mold body in the corresponding monitoring time period is recorded to obtain the mold body temperature data information; the mold body temperature data information includes the mold body temperature value Dmt before injection in each monitoring time period; Through Internet technology, the products produced in each monitoring time period are quality inspected to obtain the product defect rate Lcp in each monitoring time period and upload it to the cloud platform.

3. According to the method of intelligent control of injection molds based on industrial Internet according to claim 2, it is characterized in that: The melt temperature data information and the mold body temperature data information in step S1 are analyzed, and after dimensionless processing, a temperature difference value Wcy in a corresponding monitoring time period is obtained; The temperature difference value Wcy in each monitoring time period is correlated with the product defect rate Lcp, and the influence of the difference between the melt temperature and the mold body temperature on the product quality is analyzed to generate a quality correlation index Zzg.

4. According to the method of intelligent control of injection molds based on industrial Internet according to claim 3, it is characterized in that: A correlation threshold G is preset, and the correlation threshold G is compared and analyzed with the quality correlation index Zzg to determine whether the difference between the melt temperature and the mold body temperature has an impact on the product quality. The specific contents are as follows: If the quality correlation index Zzg> the correlation threshold G, it means that the difference between the current melt temperature and the mold body temperature has an impact on the product quality, and a preliminary warning instruction is issued. At this time, the temperature will be further analyzed; If the quality correlation index Zzg is less than the correlation threshold G, it means that the difference between the current melt temperature and the mold body temperature has an impact on the product quality, and a preliminary warning instruction is issued. At this time, the temperature will be further analyzed; If the quality correlation index Zzg=the correlation threshold G, it means that the difference between the current melt temperature and the mold body temperature has no impact on the product quality, and no additional control instruction is issued at this time.

5. According to the method of intelligent control of injection molds based on industrial Internet according to claim 4, it is characterized in that: After receiving the preliminary warning instruction, several groups of temperature sensors are deployed at multiple locations to collect the melt temperature distribution information at each point in the cavity in real time after the melt fills the mold, and obtain the melt temperature distribution information; it is also used to collect the mold temperature distribution information at each point on the mold surface in real time after the melt fills the mold, and obtain the mold temperature distribution information; The convolutional neural network processes the acquired melt temperature change information and mold temperature distribution information through multiple convolution layers and pooling layers, extracts the characteristics of melt temperature change with space and the characteristics of mold temperature in spatial distribution. The melt temperature distribution information includes the melt temperature value Drt at each point; the mold temperature distribution information includes the mold temperature value Dmj at each point.

6. The method for intelligent control of injection molds based on industrial Internet according to claim 5 is characterized in that: The finite element analysis model is used to simulate the flow and heat transfer process of the melt in the mold, analyze the melt temperature distribution at each point in the cavity after the melt fills the mold, and obtain the melt temperature distribution equilibrium index Zbh.

7. The method for intelligent control of injection molds based on industrial Internet according to claim 5 is characterized in that: The finite element analysis model is used to simulate the temperature change of the mold surface after the melt fills the mold, analyze the mold temperature distribution at each point on the mold surface after the melt fills the mold, and obtain the mold temperature distribution balance index Zfb.

8. The method for intelligent control of injection molds based on industrial Internet according to claim 1 is characterized in that: The melt temperature distribution balance index Zbh and mold temperature distribution balance index Zfb are obtained by introducing the quality correlation index Zzg, and after machine deep learning technology and dimensionless processing, the heat impact assessment index Zry is fitted.

9. The method for intelligent control of injection molds based on industrial Internet according to claim 8 is characterized in that: The thermal impact assessment index Zry obtained in step S4 is compared and analyzed with the preset impact threshold Y to obtain the corresponding control instruction, and the specific content of the control instruction is as follows: If the thermal impact assessment index Zry≤the impact threshold Y, it means that the temperature state of the melt and the mold body during the process of injecting the melt into the mold is in a normal state for the time being, and no additional control instructions are issued at this time, and the current injection molding process is continued; If the thermal impact assessment index Zry> the impact threshold Y, it means that the temperature state of the melt and the mold body during the process of injecting the melt into the mold is abnormal for the current situation, and a control instruction is issued; The specific execution content of the control instruction is: stop the current injection molding process, issue an early warning prompt, and recommend manual intervention for inspection and adjustment, including checking whether there is a hardware failure in the heater and cooler, adjusting the heating system of the injection molding machine in real time, and adjusting the difference between the melt temperature and the mold body temperature to keep it within a reasonable range; and based on machine deep learning technology, continuously analyze historical data and current temperature status to optimize the process settings for the next injection molding cycle.

10. An intelligent control system for injection molds based on the industrial Internet, comprising an intelligent control method for injection molds based on the industrial Internet as described in any one of claims 1 to 9, characterized in that: It includes monitoring module, correlation analysis module, temperature acquisition module, thermal impact analysis module and control module; The monitoring module is used to obtain melt temperature data information according to the temperature state of the melt before being injected into the mold, and to obtain mold body temperature data information by monitoring the mold body temperature state before the melt is injected into the mold, and is also used to obtain the molded product defect rate Lcp by connecting to the Internet product inspection database; The correlation analysis module is used to analyze the melt temperature data information and the mold body temperature data information to obtain the temperature difference value Wcy in each monitoring time period, and is also used to correlate the temperature difference value Wcy in each monitoring time period with the product defect rate Lcp, analyze the influence of the difference between the melt temperature and the mold body temperature on the product quality, so as to generate a quality correlation index Zzg, and compare and analyze it with the preset correlation threshold G to determine whether to issue a preliminary warning instruction; The temperature acquisition module is used to collect the temperature distribution information of the melt after the melt fills the mold in real time by deploying a plurality of groups of temperature sensors around the mold after receiving the preliminary warning instruction, and also obtain the temperature distribution status information of the mold body according to the temperature distribution of each position of the mold body after the melt fills the mold; The thermal impact analysis module is used to use convolutional neural network learning technology to perform convolutional neural network feature extraction on the melt temperature distribution information and the mold body temperature distribution state information, and calculate through a finite element analysis model to obtain the melt temperature distribution balance index Zbh and the mold temperature distribution balance index Zfb respectively, and by introducing the quality correlation index Zzg and after machine deep learning technology and dimensionless processing, the thermal impact assessment index Zry is obtained by fitting; The control module is used to compare and analyze the obtained thermal impact assessment index Zry with a preset impact threshold Y, obtain corresponding control instructions and execute them.

Images