Production line intelligent control method and device based on industrial internet and storage medium

Abstract

The invention relates to the technical field of industrial production control, in particular to a production line intelligent control method and device based on the industrial internet and a storage medium, and the method comprises the steps: collecting melt data, mold data and energy consumption data; modeling is carried out on the melt uniformity index, and a dynamic adjustment strategy is generated; a production protection strategy is generated, and meanwhile a speed adjustment threshold value is determined; carrying out feature extraction on the grayscale image of the product surface image, and judging the surface quality state according to a feature extraction result so as to update a dynamic adjustment strategy; constructing an energy consumption index according to the energy consumption data collected in the monitoring period, calculating a comprehensive quality score based on the melt uniformity index, the viscosity index and the energy consumption index in the monitoring period so as to judge the quality state, and comprehensively managing the judgment result of the quality state in the period to send a fault alarm to a user; the production efficiency of the production line is effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial production control, and particularly to an intelligent control method, device and storage medium for a production line based on the industrial Internet. Background Art

[0002] Traditional injection molding production relies on fixed process parameters and manual experience for adjustment, and it is difficult to adapt to dynamic changes such as fluctuations in material properties and mold wear. Single-sensor monitoring is prone to ignoring the coupling effect between parameters. For example, only controlling the melt temperature may cause the injection pressure to exceed the limit; the lagging manual quality inspection cannot intervene in the process chain defects in real time, often resulting in batch scrapping.

[0003] Chinese Patent Publication No. CN110134074A discloses a production line system and its control method. Among them, a control system for a production line includes: a plurality of control subsystems for respectively controlling devices corresponding to each control subsystem; an instruction dispatcher for allocating the specification instructions to the control subsystem corresponding to the type among the plurality of control subsystems according to the type of the specification instructions. In addition, the present invention also provides a computer-readable storage medium for storing processor-executable instructions and a computer device. Using the present invention can increase the accuracy, stability and portability of the production line control system, facilitate the mass production of flexible production lines, and also make the flexible production line have high availability; thus, it can be seen that this solution does not perform data coupling analysis on production data, and at the same time does not feedback the production line control parameters in time, resulting in the problem of low production efficiency of the production line. Summary of the Invention

[0004] The purpose of the present invention is to provide an intelligent control method, device and storage medium for a production line based on the industrial Internet to solve at least one of the problems existing in the prior art.

[0005] To achieve the above purpose, the present invention adopts the following technical solutions: An intelligent control method for a production line based on the industrial Internet includes: Performing data coupling on the melt temperature, injection pressure and mold closing precision deviation collected within a monitoring period to model the melt uniformity index, and generating a dynamic adjustment strategy according to the melt uniformity index; Collecting the melt pressure difference, screw data and runner data within the monitoring period to calculate the shear stress and shear rate, and constructing a viscosity index according to the shear stress and shear rate to generate a production protection strategy, and at the same time determining the speed adjustment threshold; Obtaining the product surface image within the monitoring period, extracting features from the grayscale image of the product surface image, and judging the surface quality state according to the feature extraction result to update the dynamic adjustment strategy.

[0006] Optionally, data coupling is performed on the melt temperature, injection pressure, and mold closing precision deviation collected during the monitoring period to model the melt uniformity index; Perform data coupling analysis on the melt temperature Tm, melting temperature threshold Ty, injection pressure Pm, injection pressure threshold Py, mold closing precision deviation d, and deviation threshold d0 to determine the melt uniformity index R. The expression for R is: ; where α1 is the temperature weight, α2 is the pressure weight, and α3 is the precision deviation weight.

[0007] Optionally, compare the melt uniformity index R with the melt discrimination factor r0. When the melt uniformity index R is greater than the melt discrimination factor r0, generate a dynamic adjustment strategy; The dynamic adjustment strategy includes: adjusting the screw speed in the next monitoring period to St. The expression for St is St = S base ×[1 - β×lg4×(R - r0) / lg5], where S base is the screw reference speed and β is the correction factor; Adjust the injection speed in the next monitoring period to Vz. The expression for Vz is Vz = V base ×exp[r0 - R], where V base is the injection reference speed.

[0008] Optionally, calculate the shear stress and shear rate based on the melt pressure difference, screw data, and runner data, and construct a viscosity index based on the shear stress and shear rate; When constructing the viscosity index, calculate the shear stress YL based on the melt pressure difference △P, runner diameter LD, and runner length L. The expression for YL is YL = △P×LD / 4L; Calculate the shear rate SL based on the screw cross-sectional area LA, screw propulsion speed Lv, and runner diameter LD. The expression for SL is SL = 32×LA×Lv / (π×LD 3 ); Take the ratio of the shear stress YL to the shear rate SL as the viscosity index η.

[0009] Optionally, generate a production protection strategy based on the viscosity index and determine the speed adjustment threshold at the same time; Compare the viscosity index η and the viscosity discrimination factor np to generate a production protection strategy. When the viscosity index η is greater than the viscosity discrimination factor np, set the holding pressure for the next monitoring period to BP1. The expression for BP1 is BP1 = BP0 + BP × {1 + exp[3 × (η - np) / np - 3]}, where BP is the preset pressure adjustment threshold and BP0 is the reference holding pressure. At the same time, determine the speed adjustment threshold as V1. The expression for V1 is V1 = V0 × [1 + γ × (η - np) / np], where V0 is the preset speed adjustment value and γ is the correction coefficient. When the viscosity index η is less than or equal to the viscosity discrimination factor np, keep the holding pressure unchanged. At the same time, determine the speed adjustment threshold as V2. The expression for V2 is V2 = V0.

[0010] Optionally, compare the image variance σ 2 with the variance discrimination factor A to judge the surface quality status. When the image variance σ 2 is greater than the variance discrimination factor A, determine that the surface quality status is an abnormal state. Otherwise, determine that the surface quality status is a normal state. When the surface quality status is an abnormal state, update the injection reference speed to tB to improve the filling uniformity. The expression for tB is tB = V base - speed adjustment threshold × lg[(σ 2 - A) / A + 1].

[0011] Optionally, it further includes: constructing an energy consumption index based on the energy consumption data collected within the monitoring period, and calculating a comprehensive quality score based on the melt uniformity index, viscosity index, and energy consumption index within the monitoring period to judge the quality status, and sending a fault alarm to the user based on the judgment result of the quality status within the management period. Construct an energy consumption index NH based on the heater power rq and cooling water flow sq collected within the monitoring period. Calculate a comprehensive quality score Qp based on the melt uniformity index R, viscosity index η, and energy consumption index NH within the monitoring period. The expression for Qp is Qp = F1 × R / r0 + F2 × η / np + F3 × NH / nh, where F1 is the melt uniformity weight, F2 is the viscosity weight, F3 is the energy consumption weight, and nh is the energy consumption threshold. Compare the comprehensive quality score Qp with the score threshold qp to judge the quality status of the production line. If the comprehensive quality score Qp is less than or equal to the score threshold qp, determine that the quality status of the production line in the current monitoring period is normal. Otherwise, determine that the quality status of the production line in the current monitoring period is abnormal. When the ratio of the number of monitoring periods with an abnormal quality status of the production line to the total number of monitoring periods within the management period is less than or equal to the ratio BL, do not send a fault alarm to the user. Otherwise, send a fault alarm to the user.

[0012] Optionally, melt data, mold data, and energy consumption data are collected. The melt data includes melt temperature and injection pressure, the mold data is the deviation of mold closing accuracy, and the energy consumption data includes heater power and cooling water flow rate.

[0013] According to another aspect of the present application, an intelligent control device for a production line based on the industrial Internet is provided, including: A collection unit for collecting melt data, mold data, and energy consumption data; A first control unit for coupling data of the melt temperature, injection pressure, and mold closing accuracy deviation collected within a monitoring period to model the melt uniformity index and generate a dynamic adjustment strategy according to the melt uniformity index; A second control unit for collecting the melt pressure difference, screw data, and runner data within a monitoring period to calculate the shear stress and shear rate, constructing a viscosity index according to the shear stress and shear rate to generate a production protection strategy, and determining a speed adjustment threshold; A surface quality monitoring unit for obtaining the product surface image within a monitoring period, extracting features from the grayscale image of the product surface image, and judging the surface quality status according to the feature extraction result to update the dynamic adjustment strategy; An alarm unit for constructing an energy consumption index according to the energy consumption data collected within a monitoring period, calculating a comprehensive quality score based on the melt uniformity index, viscosity index, and energy consumption index within the monitoring period to judge the quality status, and sending a fault alarm to the user based on the judgment result of the quality status within the comprehensive management period.

[0014] According to yet another aspect of the present application, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program, wherein the computer program is used to control an electronic device where the computer-readable storage medium is located to execute an intelligent control method for a production line based on the industrial Internet when running.

[0015] The beneficial effects of the present invention are as follows: Through the deep fusion and dynamic modeling technology of multi-dimensional data, the coupling effect between process parameters is accurately captured, promoting the production process to shift from experience-driven to data-driven. The coordinated optimization of melt state, shear characteristics, surface quality, and energy consumption indicators effectively balances the quality, efficiency, and cost objectives. The comprehensive scoring and early warning mechanism provides a panoramic view for production management, enabling equipment maintenance to shift from "post-fault response" to "pre-risk intervention", overall improving the reliability, flexibility, and sustainability of the production system, and enhancing the production efficiency of the production line. Description of the Drawings

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0017] Figure 1 This is a schematic flow chart of the intelligent control method for a production line based on the industrial Internet in this embodiment.

[0018] Figure 2 This is a schematic flow chart of the method for generating the dynamic adjustment strategy in this embodiment.

[0019] Figure 3 This is a schematic flow chart of the method for generating the production protection strategy in this embodiment.

[0020] Figure 4 This is a schematic flow chart of the method for judging the quality status in this embodiment.

[0021] Figure 5 This is a schematic structural diagram of the intelligent control device for a production line based on the industrial Internet in this embodiment.

[0022] Figure 6 This is a schematic structural diagram of the electronic device provided in this embodiment. Specific Embodiments

[0023] To more clearly illustrate the present invention, the following further describes the present invention in conjunction with preferred embodiments and the accompanying drawings. Similar components in the drawings are denoted by the same reference numerals. Those skilled in the art should understand that the specific content described below is illustrative rather than restrictive, and should not be used to limit the protection scope of the present invention.

[0024] It should be noted that although terms such as first, second, and third may be used in the embodiments of the present application for description, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, without departing from the scope of the embodiments of the present application, the first can also be referred to as the second, and similarly, the second can also be referred to as the first.

[0025] Specifically, this embodiment is applied to an intelligent injection molding production line for plastic products, and realizes dynamic optimization of process parameters through multi-dimensional data fusion. The system continuously executes the following core functions during the continuous operation of the production line: intelligent regulation of process parameters, runner protection mechanism, self-correction of surface defects, and combined evaluation of energy efficiency and quality, achieving early detection, precise adjustment, and self-recovery of quality abnormalities in the injection molding process.

[0026] Please refer to Figure 1As shown, it is a schematic structural diagram of the intelligent control method for a production line based on the industrial Internet, including: Step S101, collect melt data, mold data, and energy consumption data. The melt data includes melt temperature and injection pressure. The mold data is the mold closing precision deviation, which is the difference between the actual closing position and the theoretically designed closing position of the mold in the closed state. The energy consumption data includes heater power and cooling water flow.

[0027] Exemplarily, an embedded thermocouple can be used to collect the melt temperature in real time, with a sampling frequency of 20 Hz; the injection pressure can be obtained through a piezoelectric pressure sensor, and the data is denoised by Kalman filtering; the mold closing precision deviation can be measured by a laser displacement sensor; the heater power can be collected through an intelligent electricity meter, and the cooling water flow can be collected through a flow meter; in this embodiment, the specific collection methods of each data are not specifically limited, and those skilled in the art can freely set them according to requirements.

[0028] Please continue to refer to Figure 1 As shown, the intelligent control method for the production line based on the industrial Internet further includes: Step S102, perform data coupling on the melt temperature, injection pressure, and mold closing precision deviation collected within the monitoring period to model the melt uniformity index, and generate a dynamic adjustment strategy according to the melt uniformity index.

[0029] Please refer to Figure 2 As shown, the method for generating the dynamic adjustment strategy includes: Step S201, perform data coupling on the melt temperature, injection pressure, and mold closing precision deviation collected within the monitoring period to model the melt uniformity index.

[0030] Specifically, perform data coupling analysis on the melt temperature Tm, melting temperature threshold Ty, injection pressure Pm, injection pressure threshold Py, mold closing precision deviation d, and deviation threshold d0 to determine the melt uniformity index R. The expression of R is: ; where α1 is the temperature weight, α2 is the pressure weight, α3 is the precision deviation weight, and α1 + α2 + α3 = 1.

[0031] Exemplarily, the melting temperature threshold Ty can be set according to the material type, such as ABS plastic can be set to 220°C, the pressure threshold Py can be set according to the mold capacity, and the typical value is 120MPa, the deviation threshold d0 can be set to 0.1mm, the temperature weight can be set to 0.4, the pressure weight can be set to 0.3, and the deviation weight can be set to 0.3; in this embodiment, the setting of the melting temperature threshold, pressure threshold, deviation threshold and each weight is not specifically limited, and technical personnel in this field can freely set them according to needs.

[0032] Specifically, the multi-dimensional parameter coupling analysis of temperature, pressure and mold deviation breaks through the limitations of traditional single threshold control. By weighted integration of the influence of different process parameters, the melt uniformity index realizes a global evaluation of the material flow state.

[0033] Please continue reading Figure 2 As shown, the method for generating the dynamic adjustment strategy also includes: Step S202, comparing the melt uniformity index and the melt discrimination factor to generate a dynamic adjustment strategy.

[0034] Specifically, the melt uniformity index R and the melt discrimination factor r0 are compared, and when the melt uniformity index R is greater than the melt discrimination factor r0, a dynamic adjustment strategy is generated.

[0035] Specifically, the dynamic adjustment strategy includes: adjusting the screw speed in the next monitoring period to St, where the expression of St is St=S base ×[1-β×lg4×(R-r0) / lg5], the S base is the screw reference speed, and β is the correction factor; Adjust the injection speed of the next monitoring cycle to Vz, and the expression of Vz is Vz=V base × exp[r0-R], the V base It is the injection reference speed.

[0036] Specifically, based on the real-time comparison between the melt uniformity index and the melt discrimination factor, the system can quickly trigger the dynamic adjustment of the screw speed and injection speed. When the melt homogeneity decreases, the plasticizing time is extended by reducing the screw speed to promote full mixing of the material. At the same time, the injection acceleration curve is adjusted to optimize the pressure gradient in the filling stage and reduce the stagnation phenomenon at the melt front. This process not only improves the density of the internal structure of the product, but also shortens the cycle of iterative optimization of process parameters.

[0037] Exemplarily, the reference rotational speed of the screw can be set to 50 RPM for general plastics (such as PP, HDPE, ABS), 30 RPM for engineering plastics (such as PA6, PC, POM), and 20 for high-temperature materials (such as PEEK, LCP, PEI); the reference injection speed can be set to 50 mm / s for general plastics (such as PP, HDPE, ABS), 30 mm / s for engineering plastics (such as PA6, PC, POM), and 20 mm / s for high-temperature materials (such as PEEK, LCP, PEI), β can be set to 0.3, and the melt discrimination factor can be set to 0.56. In this embodiment, the settings of the reference rotational speed of the screw, the reference injection speed, the correction factor, and the melt discrimination factor are not specifically limited, and those skilled in the art can freely set them according to requirements.

[0038] Please continue to refer to Figure 1 as shown, the intelligent control method for the production line based on the industrial Internet further includes: Step S103, collect the melt pressure difference, screw data, and runner data within the monitoring period to calculate the shear stress and shear rate, and construct a viscosity index based on the shear stress and shear rate to generate a production protection strategy, and at the same time determine the speed adjustment threshold. The screw data includes the screw propulsion speed and the screw cross-sectional area, and the runner data includes the runner diameter and the runner length.

[0039] Exemplarily, the collection of the melt pressure difference can be performed using a high-precision differential pressure sensor installed at a key position of the melt flow in the injection molding machine (such as between the injection cylinder and the runner inlet of the mold), the screw propulsion speed can be collected using an optical encoder or a high-precision position sensor built into the servo motor, and the screw cross-sectional area and the runner data can be collected interactively; in this embodiment, the collection methods of each data are not specifically limited, and those skilled in the art can freely set them according to requirements.

[0040] Please refer to Figure 3 as shown, the method for generating the production protection strategy includes: Step S301, calculate the shear stress and shear rate according to the melt pressure difference, screw data, and runner data, and construct a viscosity index based on the shear stress and shear rate.

[0041] Specifically, when constructing the viscosity index, calculate the shear stress YL according to the melt pressure difference △P, the runner diameter LD, and the runner length L. The expression of YL is YL = △P × LD / 4L; Calculate the shear rate SL according to the screw cross-sectional area LA, the screw propulsion speed Lv, and the runner diameter LD. The expression of SL is SL = 32 × LA × Lv / (π × LD 3 ) Take the ratio of the shear stress YL and the shear rate SL as the viscosity index η.

[0042] Specifically, the unit of the melt pressure difference ΔP is Pascal, the unit of the runner diameter LD is meter, the unit of the runner length L is meter, the unit of the screw cross-sectional area LA is square meter, and the unit of the screw propulsion speed is meter per second.

[0043] Specifically, by calculating the shear stress and rate of the melt in the runner, the rheological properties of the material are deeply analyzed. In a runner with a high length-diameter ratio, combined with the screw geometric parameters and propulsion speed, the viscosity change trend of the melt in the slit flow can be accurately predicted, avoiding problems such as runner blockage caused by too high viscosity or overflow caused by too low viscosity.

[0044] Please continue to refer to Figure 3 As shown, the method for generating the production protection strategy further includes: Step S302, generating a production protection strategy according to the viscosity index and determining the speed adjustment threshold at the same time.

[0045] Specifically, the viscosity index η and the viscosity discrimination factor np are compared to generate a production protection strategy. When the viscosity index η is greater than the viscosity discrimination factor np, the holding pressure for the next monitoring period is set to BP1, and the expression of BP1 is BP1 = BP0 + BP × {1 + exp[3 × (η - np) / np - 3]}, where BP is the preset pressure adjustment threshold and BP0 is the reference holding pressure. At the same time, the speed adjustment threshold is determined to be V1, and the expression of V1 is V1 = V0 × [1 + γ × (η - np) / np], where V0 is the preset speed adjustment value and γ is the correction coefficient; when the viscosity index η is less than or equal to the viscosity discrimination factor np, the holding pressure remains unchanged, where BP is the preset pressure adjustment threshold and BP0 is the reference holding pressure. At the same time, the speed adjustment threshold is determined to be V2, and the expression of V2 is V2 = V0.

[0046] Specifically, the holding pressure and the speed adjustment threshold are adjusted according to the dynamic change of the viscosity index. When the material viscosity abnormally increases, the system automatically increases the holding pressure to compensate for the viscous resistance to ensure complete cavity filling; at the same time, a differentiated speed threshold is set to prevent the risk of shear heat accumulation or mold expansion caused by too high speed.

[0047] Exemplarily, the viscosity discrimination factor np can be set to 1000 Pa·s, the correction coefficient can be set to 0.15, the preset pressure adjustment threshold can be set to 0.05 × the reference holding pressure, the preset speed adjustment value is 0.06 × the injection reference speed, and when the material type is PA66, the reference holding pressure can be set to 80 MPa. Please continue to refer to Figure 1 As shown, the intelligent control method for the production line based on the industrial Internet further includes: Step S104: Obtain the product surface image within the monitoring period, extract features from the grayscale image of the product surface image, and judge the surface quality status based on the feature extraction results to update the dynamic adjustment strategy.

[0048] Specifically, capture the product surface image through a high-speed industrial camera, and convert the RGB color image into a grayscale image. The calculation formula is: I(x,y)=0.299×R(x,y)+0.587×G(x,y)+0.114×B(x,y), where R, G, and B are the red, green, and blue channel values respectively, and (x,y) is the pixel coordinate; Calculate the grayscale mean μ, ; where W×H is the image resolution, and N = W×H is the total number of pixels Calculate the image variance σ 2 , ; Compare the image variance σ 2 with the variance discrimination factor A to judge the surface quality status. When the image variance σ 2 is greater than the variance discrimination factor A, it is determined that the surface quality status is an abnormal state; otherwise, it is determined that the surface quality status is a normal state; When the surface quality status is an abnormal state, update the injection reference speed to tB to improve the filling uniformity. The expression of tB is tB = V base - speed adjustment threshold × lg[(σ 2 - A) / A + 1].

[0049] Specifically, convert the color image captured by the high-speed industrial camera into a grayscale image for feature extraction. Quantify the surface uniformity through the grayscale mean and variance calculations, and effectively identify micro-defects (such as fog spots and flow marks) that are difficult to capture by traditional manual visual inspection. When it is determined that the surface quality is abnormal, the system automatically updates the reference injection speed. This closed-loop feedback mechanism enables the process parameters to adapt to product quality fluctuations and reduces the frequency of manual intervention.

[0050] Exemplarily, the RGB values and the image resolution can capture RAW data through Bayer filter spectroscopy. Software (such as OpenCV) reads and separates each channel. The origin position can be set at the upper left corner of the image, with the horizontal right direction as the X-axis and the vertical downward direction as the Y-axis to establish a coordinate system to determine the pixel point position.

[0051] Exemplarily, the variance discrimination factor A can be set to 150; in this embodiment, the data acquisition method and the setting of the variance discrimination factor are not specifically limited, and those skilled in the art can freely set them according to requirements.

[0052] Please continue to refer to Figure 1As shown, the intelligent control method for the production line based on the industrial Internet of Things further includes: Step S105: Construct an energy consumption index based on the energy consumption data collected within the monitoring period, calculate a comprehensive quality score based on the melt uniformity index, viscosity index, and energy consumption index within the monitoring period to determine the quality status, and send a fault alarm to the user based on the determination result of the quality status within the management period.

[0053] Please refer to Figure 4 As shown, the method for determining the quality status includes: Step S401: Construct an energy consumption index based on the energy consumption data collected within the monitoring period, calculate a comprehensive quality score based on the melt uniformity index, viscosity index, and energy consumption index within the monitoring period to determine the quality status of the production line.

[0054] Specifically, construct an energy consumption index NH based on the heater power rq and cooling water flow sq collected within the monitoring period. The expression of the energy consumption index NH is NH = (rq / rq0 + sq / sq0) / 2, where rq0 is the power threshold and sq0 is the flow threshold; Calculate the comprehensive quality score Qp based on the melt uniformity index R, viscosity index η, and energy consumption index NH within the monitoring period. The expression of Qp is Qp = F1×R / r0 + F2×η / np + F3×NH / nh, where F1 is the melt uniformity weight, F2 is the viscosity weight, F3 is the energy consumption weight, F1 + F2 + F3 = 1, and nh is the energy consumption threshold; Compare the comprehensive quality score Qp with the score threshold qp to determine the quality status of the production line. If the comprehensive quality score Qp is less than or equal to the score threshold qp, it is determined that the quality status of the production line in the current monitoring period is normal; otherwise, it is determined that the quality status of the production line in the current monitoring period is abnormal.

[0055] Specifically, the scoring model that comprehensively considers melt uniformity, viscosity stability, and energy efficiency level replaces the traditional single-dimensional quality inspection mode. When the comprehensive quality score is abnormal, the scoring model can identify potential faults in the equipment drive system to improve the production efficiency of the production line.

[0056] Exemplarily, the melt uniformity weight can be set to 0.4, the viscosity weight can be set to 0.4, the energy consumption weight can be set to 0.2, and the energy consumption threshold can be set to 1.2. If the injection molding machine is a small machine, the power threshold can be set to 20kW, and the flow threshold can be set to 40L / min; in this embodiment, the settings of each weight and energy consumption threshold are not specifically limited, and those skilled in the art can freely set them according to requirements.

[0057] Please continue to refer to Figure 4 As shown, the method for determining the quality status further includes: Step S402: Send a fault alarm to the user based on the judgment result of the quality status of the production line within the comprehensive management cycle.

[0058] Specifically, when the ratio of the number of monitoring cycles with abnormal quality status of the production line to the total number of monitoring cycles within the management cycle is less than or equal to the ratio BL, no fault alarm is sent to the user; otherwise, a fault alarm is sent to the user.

[0059] Exemplarily, BL can be set to 0.2; in this embodiment, the setting of BL is not specifically limited, and those skilled in the art can freely set it according to requirements.

[0060] Exemplarily, in this embodiment, the monitoring cycle can be set to 1 min, and the management cycle can be set to 2 h. In this embodiment, the settings of the monitoring cycle and the management cycle are not specifically limited, and those skilled in the art can freely set them according to requirements.

[0061] Please refer to Figure 5 As shown, the intelligent control device for the production line based on the industrial Internet includes: An acquisition unit 501, configured to acquire melt data, mold data, and energy consumption data; A first control unit 502, configured to perform data coupling on the melt temperature, injection pressure, and mold closing precision deviation acquired within the monitoring cycle, model the melt uniformity index, and generate a dynamic adjustment strategy based on the melt uniformity index; A second control unit 503, configured to acquire the melt pressure difference, screw data, and runner data within the monitoring cycle, calculate the shear stress and shear rate, construct a viscosity index based on the shear stress and shear rate, generate a production protection strategy, and determine the speed adjustment threshold; A surface quality monitoring unit 504, configured to obtain the product surface image within the monitoring cycle, perform feature extraction on the grayscale image of the product surface image, and judge the surface quality status according to the feature extraction result to update the dynamic adjustment strategy; An alarm unit 505, configured to construct an energy consumption index based on the energy consumption data acquired within the monitoring cycle, calculate a comprehensive quality score based on the melt uniformity index, viscosity index, and energy consumption index within the monitoring cycle to judge the quality status, and send a fault alarm to the user based on the judgment result of the quality status within the comprehensive management cycle.

[0062] The embodiment of the present application further provides an electronic device, which is configured to execute the aforementioned intelligent control method for the production line based on the industrial Internet, as Figure 6 shown, including: A processing unit 601, which is at least one integrated circuit device selected from the group consisting of a central processing unit (CPU), a graphics processing unit (GPU), and a field programmable gate array (FPGA), configured to perform data access operations and generate control instructions corresponding to the method; A storage module 602, having a volatile storage area formed by a random access memory (RAM) and a non-volatile storage area formed by a flash drive, a solid state drive (SSD), or a combination thereof, the storage module being configured to store executable program code, algorithm operation intermediate variables, and a historical data set; A communication interaction component 603, integrated with: a cable communication sub-module supporting an Ethernet protocol or an RS-485 protocol, the sub-module being topologically connected to a sensing network through a physical interface; and a wireless transmission sub-module supporting LoRa communication, fifth generation mobile communication technology (5G), and a satellite communication protocol, the wireless transmission sub-module being configured to establish a data link with a remote service host; A bus system 604, implemented with PCI Express bus technology or AXI bus structure for substrate routing, the bus system having an adaptive clock synchronization mechanism to achieve real-time and synchronous high-speed data communication among the processing unit, the storage module, and the communication interaction component.

[0063] This embodiment further provides a computer-readable storage medium, which physically stores computer-executable instructions. When the instructions are transmitted to the processing unit via an integrated circuit substrate, they are encapsulated and processed through the data channel of the bus system and then solidified into the non-volatile storage area of the storage module. The executable instructions are configured to implement the complete technical solution of the intelligent control device for a production line based on the industrial Internet when executed by a processor.

[0064] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, rather than limitations on the implementation manners of the present invention. For those of ordinary skill in the art, other different forms of changes or variations can be made based on the above description. It is impossible to enumerate all the implementation manners here. Any obvious changes or variations derived from the technical solutions of the present invention still fall within the protection scope of the present invention.

Claims

1. An intelligent control method for a production line based on the industrial Internet, characterized in that Including: Couple the data of the melt temperature, injection pressure, and mold closing precision deviation collected during the monitoring period to model the melt uniformity index and generate a dynamic adjustment strategy based on the melt uniformity index; Collect the melt pressure difference, screw data, and runner data during the monitoring period to calculate the shear stress and shear rate, construct a viscosity index based on the shear stress and shear rate to generate a production protection strategy, and determine the speed adjustment threshold; Obtain the product surface image during the monitoring period, extract features from the grayscale image of the product surface image, and judge the surface quality status based on the feature extraction results to update the dynamic adjustment strategy.

2. The intelligent control method for a production line based on the industrial Internet according to claim 1, wherein Couple the data of the melt temperature, injection pressure, and mold closing precision deviation collected during the monitoring period to model the melt uniformity index; Conduct data coupling analysis on the melt temperature Tm, melting temperature threshold Ty, injection pressure Pm, injection pressure threshold Py, mold closing precision deviation d, and deviation threshold d0 to determine the melt uniformity index R. The expression of R is: ; where α1 is the temperature weight, α2 is the pressure weight, and α3 is the precision deviation weight.

3. The intelligent control method for a production line based on the industrial Internet according to claim 2, wherein Compare the melt uniformity index R with the melt discrimination factor r0. When the melt uniformity index R is greater than the melt discrimination factor r0, generate a dynamic adjustment strategy; The dynamic adjustment strategy includes: adjusting the screw speed in the next monitoring cycle to St, and the expression of St is St = S base ×[1 - β×lg4×(R - r0) / lg5], where the S base is the reference screw speed, and the β is the correction factor; Adjust the injection speed in the next monitoring cycle to Vz, and the expression of Vz is Vz = V base × exp[r0 - R], where the V base is the injection reference speed.

4. The intelligent control method for a production line based on the industrial Internet according to claim 3, characterized in that Calculate the shear stress and shear rate based on the melt pressure difference, screw data, and runner data, and construct a viscosity index based on the shear stress and shear rate; When constructing the viscosity index, calculate the shear stress YL based on the melt pressure difference △P, runner diameter LD, and runner length L. The expression of YL is YL = △P × LD / 4L; Calculate the shear rate SL according to the screw cross-sectional area LA, the screw advancement speed Lv, and the runner diameter LD. The expression for SL is SL = 32×LA×Lv / (π×LD 3 ); Take the ratio of the shear stress YL to the shear rate SL as the viscosity index η.

5. The intelligent control method for a production line based on the industrial Internet according to claim 4, wherein, Generate a production protection strategy based on the viscosity index and determine the speed adjustment threshold; Compare the viscosity index η with the viscosity discrimination factor np to generate a production protection strategy. When the viscosity index η is greater than the viscosity discrimination factor np, set the holding pressure for the next monitoring period as BP1. The expression of BP1 is BP1 = BP0 + BP × {1 + exp[3 × (η - np) / np - 3]}, where BP is the preset pressure adjustment threshold, BP0 is the reference holding pressure. At the same time, determine the speed adjustment threshold as V1. The expression of V1 is V1 = V0 × [1 + γ × (η - np) / np], where V0 is the preset speed adjustment value and γ is the correction coefficient; when the viscosity index η is less than or equal to the viscosity discrimination factor np, keep the holding pressure unchanged. At the same time, determine the speed adjustment threshold as V2. The expression of V2 is V2 = V0.

6. The intelligent control method for a production line based on the industrial Internet according to claim 5, wherein Compare the image variance σ 2 with the variance discrimination factor A to determine the surface quality status. When the image variance σ 2 is greater than the variance discrimination factor A, the surface quality status is determined to be an abnormal state; otherwise, the surface quality status is determined to be a normal state. When the surface quality state is an abnormal state, update the injection reference speed to tB to improve filling uniformity. The expression of tB is tB = V base - speed adjustment threshold × lg[(σ 2 - A) / A + 1].

7. The intelligent control method for a production line based on the industrial Internet according to claim 6, characterized in that, Also including: Construct an energy consumption index based on the energy consumption data collected during the monitoring period, calculate the comprehensive quality score based on the melt uniformity index, viscosity index, and energy consumption index during the monitoring period to judge the quality status, and send a fault alarm to the user based on the judgment result of the quality status during the comprehensive management period; Construct an energy consumption index NH based on the heater power rq and cooling water flow sq collected during the monitoring period; Calculate the comprehensive quality score \(Q_p\) based on the melt uniformity index \(R\), viscosity index \(\eta\), and energy consumption index \(NH\) within the monitoring period. The expression of \(Q_p\) is \(Q_p = F_1\times R / r_0+F_2\times\eta / n_p + F_3\times NH / nh\), where \(F_1\) is the melt uniformity weight, \(F_2\) is the viscosity weight, \(F_3\) is the energy consumption weight, and \(nh\) is the energy consumption threshold; Compare the comprehensive quality score \(Q_p\) with the score threshold \(qp\) to judge the quality status of the production line. If the comprehensive quality score \(Q_p\) is less than or equal to the score threshold \(qp\), it is determined that the quality status of the production line in the current monitoring period is normal; otherwise, it is determined that the quality status of the production line in the current monitoring period is abnormal; When the ratio of the number of monitoring periods with abnormal quality status of the production line to the total number of monitoring periods within the management period is less than or equal to the ratio \(BL\), no fault alarm is sent to the user; otherwise, a fault alarm is sent to the user.

8. The intelligent control method for a production line based on the industrial Internet according to claim 1, characterized in that Collect melt data, die data, and energy consumption data. The melt data includes melt temperature and injection pressure, the die data is the die closing precision deviation, and the energy consumption data includes heater power and cooling water flow.

9. An intelligent control device for a production line based on the industrial Internet, characterized in that, Include: A collection unit for collecting melt data, die data, and energy consumption data; A first control unit for coupling the melt temperature, injection pressure, and die closing precision deviation collected within the monitoring period to model the melt uniformity index and generate a dynamic adjustment strategy based on the melt uniformity index; A second control unit for collecting the melt pressure difference, screw data, and runner data within the monitoring period to calculate the shear stress and shear rate, constructing a viscosity index based on the shear stress and shear rate to generate a production protection strategy, and determining the speed adjustment threshold; A surface quality monitoring unit for obtaining the product surface image within the monitoring period, extracting features from the grayscale image of the product surface image, and judging the surface quality status based on the feature extraction results to update the dynamic adjustment strategy; An alarm unit for constructing an energy consumption index based on the energy consumption data collected within the monitoring period, calculating the comprehensive quality score based on the melt uniformity index, viscosity index, and energy consumption index within the monitoring period to judge the quality status, and sending a fault alarm to the user based on the judgment results of the quality status within the management period; 10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein the computer program is used to control the electronic device where the computer-readable storage medium is located to execute the intelligent control method for the production line based on the industrial Internet according to any one of claims 1 - 8 when running.

Images