An industrial process collaborative optimization service system based on the Industrial Internet

Abstract

The present invention relates to the technical field of industrial Internet of Things, and specifically to an industrial process collaborative optimization service system based on the industrial Internet, which includes a multi-source data acquisition unit for real-time acquisition of operating data and environmental data of equipment during material production and collection of historical operating data and environmental data of equipment operation; a temperature zone determination unit for determining and adjusting the temperature zone of the melt in real time according to an upper threshold, a lower threshold, a critical low temperature value, and a critical high temperature value of the melt temperature; a temperature interval judgment unit for determining the zone in which the melt temperature is located; a temperature optimization adjustment unit for adjusting the temperature of the melt to a safe operating zone based on a method combining a real-time temperature response model with a multi-objective Pareto optimization; the system maximizes the temperature adjustment speed and optimizes the process smoothness, and ensures the integrity of the material phase change while adjusting the temperature.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial Internet of Things, and in particular to an industrial process collaborative optimization service system based on the industrial Internet. Background Art

[0002] Precise control of melt temperature plays a crucial role in plastic injection molding production lines. It not only directly impacts product quality and production efficiency, but also significantly impacts energy consumption and production costs. With the continuous development of the Industrial Internet and intelligent manufacturing technologies, intelligent and automated melt temperature regulation will become a core competitive advantage for improving production efficiency and product quality in the future manufacturing industry.

[0003] In traditional temperature control systems, overheating or overcooling may lead to energy waste. Old systems often fail to fully consider the relationship between temperature adjustment and energy efficiency. With the promotion of intelligent energy management systems, more and more production lines are reducing unnecessary energy consumption through energy optimization algorithms and real-time monitoring. However, even so, in some scenarios, the system still suffers from overcooling or overheating, especially when temperature control is inaccurate. Therefore, an industrial process collaborative optimization service system based on the Industrial Internet is designed. Summary of the Invention

[0004] The purpose of the present invention is to provide an industrial process collaborative optimization service system based on the industrial Internet to solve the problem raised in the above background technology that the system may be overcooled or overheated when the temperature control is inaccurate.

[0005] To achieve the above objectives, the present invention provides an industrial process collaborative optimization service system based on the Industrial Internet, comprising:

[0006] A multi-source data acquisition unit, which is used to collect real-time operating data and environmental data of equipment during material production and to collect historical operating data and environmental data of equipment operation;

[0007] A temperature zone determination unit, which is used to dynamically set the upper and lower thresholds of the melt temperature based on the equipment's operating data and environmental data and in combination with historical melt temperature fluctuation data, and simultaneously determine the critical low temperature value and critical high temperature value. The melt temperature zone is determined and adjusted in real time based on the upper and lower thresholds, critical low temperature value, and critical high temperature value of the melt temperature; the melt temperature zone includes a low temperature risk zone, a safe operation zone, a high temperature risk zone, and an extreme danger zone;

[0008] A temperature interval judgment unit is used to compare the melt temperature with an upper threshold, a lower threshold, a critical low temperature value, and a critical high temperature value to determine the zone in which the melt temperature is located. If the melt temperature zone is in a low temperature risk zone or a high temperature risk zone, an optimization signal is triggered; if the melt temperature zone is in an extreme danger zone, an emergency signal is triggered;

[0009] A temperature optimization and adjustment unit, which, after receiving the optimization signal, adjusts the temperature of the melt to a safe operating zone based on a method combining a real-time temperature response model and a multi-objective Pareto optimization;

[0010] A safety protection unit triggers a danger alarm after receiving an optimization signal, and triggers an emergency shutdown after receiving an emergency signal.

[0011] As a further improvement of the present technical solution, the operating data includes injection speed, heating power, cooling power and energy consumption.

[0012] As a further improvement of the present technical solution, the specific steps of setting the upper and lower thresholds of the melt temperature in the temperature region determination unit are as follows:

[0013] S21. Determine the ideal target temperature of the melt temperature ;

[0014] S22. Analyze the melt temperature fluctuation range in the historical temperature fluctuation data and obtain the standard deviation of the melt temperature , thereby determining the influence coefficient of temperature fluctuation ;

[0015] S23, set the target temperature , the influence coefficient of temperature fluctuation , heating power and ambient temperature Perform data fusion and introduce thermal inertia Optimize and obtain the upper threshold of melt temperature ;

[0016] S24, set the target temperature , the influence coefficient of temperature fluctuation , cooling power and ambient temperature Perform data fusion and introduce thermal inertia Optimize and obtain the lower limit threshold of melt temperature .

[0017] As a further improvement of the present technical solution, the temperature division of the melt in the temperature region determination unit is specifically as follows:

[0018] when When , the temperature area is the safe operating area;

[0019] when When , the temperature area is a low temperature risk area;

[0020] when When , the temperature area is a high temperature risk area;

[0021] when or When , the temperature area is an extreme danger zone;

[0022] in, is the melt temperature; is the critical low temperature value; is the critical high temperature value.

[0023] As a further improvement of the present technical solution, the temperature optimization and adjustment unit includes a response model prediction module, a dual-objective optimization module and a collaborative adjustment execution module;

[0024] The response model prediction module is used to construct a temperature relationship response model and input the collected operating data into the temperature relationship response model to predict the trajectory of melt temperature changes over time, as well as the cycle time and energy consumption fluctuations required to reach a stable temperature.

[0025] The dual-objective optimization module predicts the cycle time required to reach a stable temperature based on the melt temperature zone provided by the response model prediction module. and energy consumption fluctuations , taking injection speed and cooling power as collaborative decision variables to search for the optimal solution set, achieving dual-objective joint optimization, and finally outputting the optimal injection speed adjustment amount and optimal cooling power regulation ;

[0026] The coordinated adjustment execution module is used to adjust the injection speed according to the injection speed. and cooling power adjustment Adjust the values ​​of injection speed and cooling power, and monitor the changes in melt temperature after the injection speed and cooling power are adjusted in real time.

[0027] As a further improvement of the present technical solution, the specific steps of establishing the temperature relationship response model in the response model prediction module are as follows:

[0028] S411, combining heat transfer equations and real-time data correction to build a linear model;

[0029] S412, adding a nonlinear coupling function to the linear model to generate a nonlinear model;

[0030] S413, the nonlinear model is divided into two groups according to the sampling period. Discretization, for the future Injection speed increment within a step , cooling power increment Iterate step by step to predict the temperature trajectory;

[0031] S414, during the iteration process, when the predicted temperature enters the preset safe operating area and continuously When the temperature change amplitude of the time step is less than the temperature change amplitude threshold, the iteration is stopped and the prediction cycle time is calculated. , and record the predicted energy consumption data;

[0032] S415. During the prediction cycle, the energy consumption values ​​generated by the heating power and cooling power corresponding to each time step are accumulated, and the standard deviation of the energy consumption sequence is calculated as the energy consumption fluctuation value. ;

[0033] S416. Each time the melt temperature is adjusted to a safe operating zone, the actual cycle time and actual energy consumption are collected to update the parameters of the temperature relationship response model.

[0034] As a further improvement of the present technical solution, the dual objectives in the dual-objective optimization module include minimizing the predicted cycle time and minimizing the energy consumption fluctuation value.

[0035] As a further improvement of the present technical solution, in the dual-objective optimization module, the constraints for achieving dual-objective joint optimization include the constraints of the injection speed range, the constraints of the cooling power range, the constraints of the predicted temperature trajectory, and the constraints of the temperature change rate; among them, the constraints of the predicted temperature trajectory are specifically a certain future time point within the cycle time, so that the predicted melt temperature at this time point enters the safe operating zone for the first time and continues to remain in the safe operating zone.

[0036] As a further improvement of the present technical solution, in the dual-objective optimization module, the specific steps of searching for the optimal solution set by using injection speed and cooling power as collaborative decision variables are as follows:

[0037] S421, injection speed increment and cooling power increment Generate an initial equidistant grid within the feasible range for discretization, and dynamically refine the grid based on the risk level of the real-time temperature area;

[0038] S422. For each collaborative decision variable generated after discretization, call the temperature relationship response model to perform parallel prediction, and output the cycle time, energy consumption fluctuation, and melt temperature trajectory corresponding to the decision variable in real time;

[0039] S423. Based on the constraints, exclude the decision points that do not meet the constraints, construct the objective function for the decision points that meet the constraints, introduce the material phase change kinetics penalty term into the objective function for optimization, and select the decision point with the smallest objective function value as the optimal solution.

[0040] As a further improvement of this technical solution, in S423, the specific process of constructing the objective function is as follows:

[0041] S1. Calculate a weight value based on the current melt temperature using a weight function. The weight function is designed as a monotonically decreasing function of the melt temperature, such that the penalty weight for energy consumption fluctuations is reduced in high-temperature risk areas and increased in low-temperature risk areas.

[0042] S2. Setting an energy consumption fluctuation tolerance threshold, where the threshold is associated with the injection speed adjustment amount, constructing an objective function based on the energy consumption fluctuation tolerance threshold, calculating the objective function values ​​for all feasible decision points, and selecting the decision point that minimizes the objective function value as the optimal collaborative adjustment solution;

[0043] S3. Introduce the material phase change kinetic penalty term into the objective function for optimization; first establish the differential equation of crystallinity and temperature history, extract the key phase change indicators, which include the minimum allowable crystallinity and the maximum allowable crystallization rate; establish the dynamic penalty term based on the key phase change indicators, and convert the dynamic penalty term into Integrate it into the objective function to generate the optimized objective function.

[0044] Compared with the prior art, the present invention has the following beneficial effects:

[0045] 1. In this industrial process collaborative optimization service system based on the Industrial Internet, through the dynamic collaborative optimization of injection speed and cooling power, while ensuring the quality of material phase change, a multi-objective Pareto optimal strategy is used to simultaneously maximize the temperature adjustment speed and optimize the process smoothness, completely resolving the contradiction in traditional temperature control where rapid adjustment causes thermal shock or smooth adjustment causes delay.

[0046] 2. In this industrial process collaborative optimization service system based on the Industrial Internet, a material phase change kinetic penalty term is introduced in the process of constructing the objective function. By dynamically penalizing the problems of insufficient crystallinity and crystallization rate mismatch, the quality of the material microscopic phase change is included in the optimization target, fundamentally avoiding hidden product quality defects caused by inaccurate temperature control. The optimization process ensures the integrity of the material phase change while adjusting the temperature. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is the overall flow chart of the present invention;

[0048] Figure 2This is a system block diagram of the temperature optimization and adjustment unit in the present invention;

[0049] The meaning of each number in the figure is:

[0050] 1. Multi-source data acquisition unit; 2. Temperature zone determination unit; 3. Temperature interval judgment unit; 4. Temperature optimization and adjustment unit; 41. Response model prediction module; 42. Dual-objective optimization module; 43. Collaborative adjustment execution module; 5. Safety protection unit. DETAILED DESCRIPTION

[0051] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0052] Example: See Figure 1-Figure 2 As shown in the figure, an industrial process collaborative optimization service system based on the Industrial Internet is provided. This system is applied in a plastic injection molding production line and involves multiple devices, such as injection machines, heaters, and cooling systems. The equipment combination scheme includes settings such as injection speed, heating power, and cooling power. The goal is to maximize production efficiency (the number of products produced per unit time) while minimizing energy consumption (reducing energy consumption per unit product). The system includes a multi-source data acquisition unit 1, a temperature zone determination unit 2, a temperature interval judgment unit 3, a temperature optimization and adjustment unit 4, and a safety protection unit 5:

[0053] The multi-source data acquisition unit 1 is used to collect the operating data and environmental data of the equipment during material production in real time and to collect the historical operating data and environmental data of the equipment; the operating data includes injection speed, heating power, cooling power and energy consumption;

[0054] The temperature zone determination unit 2 is used to dynamically set the upper and lower threshold values ​​of the melt temperature based on the equipment's operating data and environmental data and in combination with historical melt temperature fluctuation data, and simultaneously determine the critical low temperature value and the critical high temperature value, and determine and adjust the melt's temperature zone in real time based on the upper and lower threshold values, the critical low temperature value and the critical high temperature value of the melt temperature; the melt's temperature zone includes a low-temperature risk zone, a safe operating zone, a high-temperature risk zone and an extreme danger zone; among them, the critical low temperature value is usually set based on the historical minimum safety temperature and process requirements, and the critical high temperature value can be determined by the material's heat resistance upper limit and process limit.

[0055] The specific steps of setting the upper and lower thresholds of the melt temperature in the temperature region determination unit 2 are as follows:

[0056] S21. Determine the ideal target temperature of the melt temperature ;

[0057] S22. Analyze the melt temperature fluctuation range in the historical temperature fluctuation data and obtain the standard deviation of the melt temperature , thereby determining the influence coefficient of temperature fluctuation The temperature fluctuation coefficient reflects the instability of temperature changes, allowing the system to dynamically adjust the temperature safety range based on historical data. If the historical temperature fluctuation is large, the system can increase the upper and lower temperature thresholds to better adapt to the uncertainty of the production process.

[0058] S23, set the target temperature , the influence coefficient of temperature fluctuation , heating power and ambient temperature Perform data fusion and introduce thermal inertia Optimize and obtain the upper threshold of melt temperature ;

[0059]

[0060] Where, The upper limit of the melt temperature is the basic fluctuation range, which is a basic fluctuation value within the ideal range of the melt temperature. It is usually determined during design based on material properties and production experience. is the melt injection speed; The coefficient of influence of ambient temperature on melt temperature. When the ambient temperature is high, the efficiency of the cooling system may decrease, affecting the control of melt temperature; The coefficient of thermal inertia on temperature adjustment indicates the hysteresis effect when the melt temperature changes. The melt temperature does not respond immediately to changes in heating and cooling power, but there is a lag time.

[0061] S24, set the target temperature , the influence coefficient of temperature fluctuation , cooling power and ambient temperature Perform data fusion and introduce thermal inertia Optimize and obtain the lower limit threshold of melt temperature ;

[0062]

[0063] Where, is the basic fluctuation range of the lower limit of melt temperature;

[0064] The temperature division of the melt in the temperature region determination unit 2 is specifically as follows:

[0065] when When , the temperature area is the safe operating area;

[0066] when When , the temperature area is a low temperature risk area;

[0067] when When , the temperature area is a high temperature risk area;

[0068] when or When , the temperature area is an extreme danger zone;

[0069] in, is the melt temperature; is the critical low temperature value; is the critical high temperature value;

[0070] In this embodiment, the upper threshold of the melt temperature is 215°C, the lower threshold is 185°C, and the critical low temperature value is , the critical high temperature value is , then the low temperature risk area is , the safe operating area is , high temperature risk areas are , and the extreme danger zone is or ;

[0071] Based on the acquired temperature data and threshold ranges, the melt temperature zones are divided, and different early warning mechanisms and operation strategies are set according to different temperature ranges. Through the dynamic division of temperature zones, abnormal fluctuations in the melt temperature can be detected and responded to in a timely manner, thereby achieving optimized control and preventive maintenance of the equipment.

[0072] The temperature range judgment unit 3 is used to compare the melt temperature with the upper threshold, the lower threshold, the critical low temperature value, and the critical high temperature value to determine the zone in which the melt temperature is located. If the melt temperature zone is in the low temperature risk zone or the high temperature risk zone, an optimization signal is triggered. If the melt temperature zone is in the extreme danger zone, an emergency signal is triggered.

[0073] After receiving the optimization signal, the temperature optimization and adjustment unit 4 adjusts the temperature of the melt to a safe operating zone based on a method combining a real-time temperature response model and a multi-objective Pareto optimization;

[0074] The temperature optimization and adjustment unit 4 includes a response model prediction module 41, a dual-objective optimization module 42 and a coordinated adjustment execution module 43;

[0075] The response model prediction module 41 is used to construct a temperature relationship response model and input the collected operating data into the temperature relationship response model to predict the trajectory of melt temperature change over time and the cycle time and energy consumption fluctuation value required to reach a stable temperature;

[0076] The specific steps of establishing the temperature relationship response model in the response model prediction module 41 are:

[0077] S411, combining heat transfer equations and real-time data correction to build a linear model;

[0078] The linear model is specifically:

[0079]

[0080] Where, is the heat capacity of the melt; is the current melt temperature; is the heating power; is the heat transfer coefficient of the cooling system; is the temperature of the cooling medium; is the thermal conductivity of the environment; is the ambient temperature;

[0081] S412. In practice, the effects of heating power and cooling power on temperature are nonlinear, and changes in injection speed directly affect the residence time of the material in the heating barrel and shear heating. Therefore, a nonlinear coupling function is added to the linear model to generate a nonlinear model.

[0082]

[0083] Where, is the material characteristic parameter; is the nonlinear coupling function; is the historical temperature change trend;

[0084] S413, the nonlinear model is divided into two groups according to the sampling period. Discretization, for the future Injection speed increment within a step , cooling power increment Iterate step by step to predict the temperature trajectory;

[0085] Let the current time be ,future The temperature prediction for the first step is:

[0086]

[0087] in: ; ;

[0088] Where, is the current injection speed, is the current cooling power; For the Update based on historical data; For the time steps; For the melt temperature of the first step; For the melt temperature of the first step; For the Melt injection speed of the first step; For the Cooling power of the step;

[0089] S414, during the iteration process, when the predicted temperature enters the preset safe operating area and continuously The temperature change amplitude of the time step is less than the temperature change amplitude threshold, stop the iteration and calculate the prediction cycle time , the cumulative number of time steps at this time multiplied by the time step length is the prediction cycle time, and the predicted energy consumption data is recorded;

[0090] S415. During the prediction cycle, the energy consumption values ​​generated by the heating power and cooling power corresponding to each time step are accumulated, and the standard deviation of the energy consumption sequence is calculated as the energy consumption fluctuation value. ;

[0091]

[0092] Where, For the Total energy consumption of the step; , For the Heating power of the step; is the average energy consumption during the forecast period; is the number of time steps;

[0093] S416. Each time the melt temperature is adjusted to a safe operating zone, actual cycle time and actual energy consumption are collected to update the parameters of the temperature relationship response model;

[0094] The dual-objective optimization module 42 predicts the cycle time required to reach the stable temperature based on the response model provided by the response model prediction module 41 according to the region where the melt temperature is located. and energy consumption fluctuations , taking injection speed and cooling power as collaborative decision variables to search for the optimal solution set, achieving dual-objective joint optimization, and finally outputting the optimal injection speed adjustment amount and optimal cooling power regulation ;

[0095] The dual objectives in the dual objective optimization module 42 include minimizing the predicted cycle time and minimizing the energy consumption fluctuation value; in the dual objective optimization module 42, the constraints for achieving dual objective joint optimization include the constraints of the injection speed range, the cooling power range, the predicted temperature trajectory and the temperature change rate; among them, the constraints of the predicted temperature trajectory are specifically the existence of the cycle time At a certain future time point within the specified time range, the predicted melt temperature at that time point enters the safe operating zone for the first time and continues to remain in the safe operating zone; entering the safe zone for the first time and continuing to maintain it can prevent the temperature from getting out of control again after briefly touching the safe zone, resulting in interruption of material phase change, and eliminating the thermal stress concentration caused by repeated temperature jumps, ensuring the continuity and stability of the melt solidification process. The temperature change rate constraint means that the temperature change is always within the allowable range to avoid thermal shock. The injection speed range constraint means that the adjusted injection speed must be within the physical limit of the equipment to prevent equipment overload or insufficient injection molding. The cooling power range constraint means that the adjusted cooling power must be within the system design capacity to avoid freezing of the refrigeration system or cooling failure.

[0096] In the dual-objective optimization module 42, the specific steps of searching for the optimal solution set using the injection speed and cooling power as collaborative decision variables are as follows:

[0097] S421, injection speed increment and cooling power increment Generate an initial equidistant grid within the feasible range for discretization, and dynamically refine the grid based on the risk level of the real-time temperature zone; the grid density is dynamically adjusted with the temperature risk level. When in the high-temperature risk zone, the grid resolution is increased in the cooling power increment dimension; when in the low-temperature risk zone, the grid resolution is increased in the injection speed increment dimension; the high-temperature risk zone focuses on the cooling power dimension, while the low-temperature risk zone focuses on the injection speed dimension;

[0098] The dynamic grid refinement strategy adjusts the grid density based on real-time temperature, providing a more refined search capability in high- and low-temperature risk areas. This significantly improves the accuracy and efficiency of temperature regulation and avoids excessive and inefficient calculations. While simple, the traditional fixed grid strategy can be inefficient when temperatures fluctuate significantly, failing to fully utilize the characteristics of temperature fluctuations to optimize the temperature control process.

[0099] S422. For each collaborative decision variable generated after discretization, call the temperature relationship response model to perform parallel prediction, and output the cycle time, energy consumption fluctuation, and melt temperature trajectory corresponding to the decision variable in real time;

[0100] S423. Based on the constraints, exclude the decision points that do not meet the constraints, construct the objective function for the decision points that meet the constraints, introduce the material phase change kinetics penalty term into the objective function for optimization, and select the decision point with the smallest objective function value as the optimal solution.

[0101] In S423, the specific process of constructing the objective function is:

[0102] S1, according to the current melt temperature , calculating the weight value through a weight function, wherein the weight function is designed as a monotonically decreasing function of the melt temperature, so that the penalty weight of energy consumption fluctuation is reduced in the high-temperature risk area and increased in the low-temperature risk area;

[0103] In the specific implementation, the exponential function form is adopted:

[0104]

[0105] in, is the weight base (range 0.5~1.0), is the sensitivity coefficient (value ranges from 0.02 to 0.1), is the median temperature of the safe operating area;

[0106] In high temperature risk areas, rapid cooling is required and greater energy consumption fluctuations can be tolerated, so the In low temperature risk areas, there is no risk of material degradation, and energy stability is prioritized, which increases ;

[0107] S2. Setting an energy consumption fluctuation tolerance threshold, where the threshold is associated with the injection speed adjustment amount, constructing an objective function based on the energy consumption fluctuation tolerance threshold, calculating the objective function values ​​for all feasible decision points, and selecting the decision point that minimizes the objective function value as the optimal collaborative adjustment solution;

[0108]

[0109] in, is the energy consumption fluctuation tolerance threshold; is the basic tolerance value, is the adjustment coefficient; Because this is the first The change value of the injection speed adjustment amount;

[0110] Objective function:

[0111]

[0112] is the objective function value; For the The injection speed and Predicted cycle time at subcooling power; For the The injection speed and The predicted energy fluctuation value under sub-cooling power;

[0113] Among them, the first one optimizes production efficiency, and the second one constrains energy consumption fluctuations to be within a tolerable range;

[0114] S3. Introduce the material phase change kinetics penalty term into the objective function for optimization; the traditional objective function only focuses on the temperature value and ignores the insufficient completion of the phase change. That is, although the temperature is in the safe zone, the crystallinity is less than 90%, which will lead to a decrease in the mechanical strength of the product and a mismatch in the phase change rate. That is, too fast cooling leads to uneven crystal size and an increase in the haze of the product.

[0115] First, a differential equation of crystallinity and temperature history is established to extract key phase transition indicators, including the minimum allowable crystallinity and the maximum allowable crystallization rate. The minimum allowable crystallinity ensures the strength of the product, while the maximum allowable crystallization rate prevents crystallization defects.

[0116] Establish dynamic penalty terms based on key phase transition indicators , the dynamic penalty term Integrate it into the objective function to generate an optimized objective function; it can strongly suppress insufficient crystallization and excessive crystallization conditions;

[0117] The differential equation of crystallinity and temperature history is:

[0118]

[0119] Where, is the real-time crystallinity; is the temperature-dependent rate constant; is the Avrami index;

[0120] Dynamic penalty term for:

[0121]

[0122] Where, is the crystallinity penalty coefficient, which is used to adjust the impact of crystallinity deviation on the objective function. The value of this coefficient affects the contribution of crystallinity to the objective function. is the minimum allowable crystallinity; is the crystallinity at the end of the cycle time; is the crystallization rate penalty coefficient, which is used to adjust the impact of the crystallization rate on the objective function and control the variation range of the crystallization rate; The end moment of the cycle time; is the maximum allowable crystallization rate;

[0123] The optimized objective function is:

[0124]

[0125] Where, The optimized objective function value; This is the adjustment factor based on the melt temperature, which represents the effect of temperature on the phase transition process. Temperature has a direct impact on crystallinity and crystallization rate, so this item needs to be adjusted according to the current melt temperature;

[0126] Among them, the dynamic penalty term The first item: at the end of the prediction cycle time When the crystallinity The minimum allowable crystallinity is not reached (For example, 0.9) penalty, the penalty amount is proportional to the square of the deficiency, the weight Larger (e.g. 10.0);

[0127] Dynamic penalty term The second item: the crystallization rate during the entire cycle time Exceeding the maximum allowable crystallization rate (For example, 0.03s^-1) penalty, the penalty amount is the integral of the square of the excess part over the entire time, the weight (e.g. 2.0). Dynamic weight According to the melt temperature and the crystallization temperature of the material Relationship segmentation settings:

[0128]

[0129] Where, is the crystallization temperature;

[0130] In this way, the optimized objective function not only takes into account time and energy consumption, but also the quality of the material phase change process (crystallization and crystallization rate), thereby guiding the system to select process parameters that are more in line with the material properties during the optimization process.

[0131] The coordinated adjustment execution module 43 is used to adjust the injection speed according to the injection speed. and cooling power adjustment Adjust the injection speed and cooling power values, and monitor the changes in melt temperature after the injection speed and cooling power are adjusted in real time;

[0132] The safety protection unit 5 triggers a danger alarm after receiving the optimization signal, and triggers an emergency shutdown after receiving the emergency signal.

[0133] The basic principles, main features, and advantages of the present invention are shown and described above. It should be understood by those skilled in the art that the present invention is not limited to the above-described embodiments. The above-described embodiments and descriptions are merely preferred examples of the present invention and are not intended to limit the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention, and such changes and modifications fall within the scope of the invention claimed.

Claims

1. An industrial process collaborative optimization service system based on the Industrial Internet, characterized in that: include: A multi-source data acquisition unit (1), the multi-source data acquisition unit (1) is used to collect real-time operation data and environmental data of equipment during material production and to collect historical operation data and environmental data of equipment operation; A temperature zone determination unit (2), the temperature zone determination unit (2) is used to dynamically set an upper threshold value and a lower threshold value of the melt temperature based on the operation data and environmental data of the equipment and in combination with historical melt temperature fluctuation data, and simultaneously determine a critical low temperature value and a critical high temperature value, and determine and adjust the temperature zone of the melt in real time according to the upper threshold value, the lower threshold value, the critical low temperature value and the critical high temperature value of the melt temperature; the temperature zone of the melt includes a low temperature risk zone, a safe operation zone, a high temperature risk zone and an extreme danger zone; A temperature interval judgment unit (3), the temperature interval judgment unit (3) is used to compare the melt temperature with an upper threshold, a lower threshold, a critical low temperature value, and a critical high temperature value to determine the zone where the melt temperature is located. If the temperature zone of the melt is in a low temperature risk zone or a high temperature risk zone, an optimization signal is triggered; if the temperature zone of the melt is in an extreme danger zone, an emergency signal is triggered; A temperature optimization and adjustment unit (4), which, after receiving the optimization signal, adjusts the temperature of the melt to a safe operating zone based on a method combining a real-time temperature response model and a multi-objective Pareto optimization; A safety protection unit (5) triggers a danger alarm after receiving an optimization signal, and triggers an emergency shutdown after receiving an emergency signal.

2. The industrial process collaborative optimization service system based on the Industrial Internet according to claim 1 is characterized by: The operating data includes injection speed, heating power, cooling power and energy consumption.

3. The industrial process collaborative optimization service system based on the Industrial Internet according to claim 2 is characterized by: The specific steps of setting the upper and lower thresholds of the melt temperature in the temperature region determination unit (2) are as follows: S21. Determine the ideal target temperature of the melt temperature ; S22. Analyze the melt temperature fluctuation range in the historical temperature fluctuation data and obtain the standard deviation of the melt temperature , thereby determining the influence coefficient of temperature fluctuation ; S23, set the target temperature , the influence coefficient of temperature fluctuation , heating power and ambient temperature Perform data fusion and introduce thermal inertia Optimize and obtain the upper threshold of melt temperature ; S24, set the target temperature , the influence coefficient of temperature fluctuation , cooling power and ambient temperature Perform data fusion and introduce thermal inertia Optimize and obtain the lower limit threshold of melt temperature .

4. The industrial process collaborative optimization service system based on the Industrial Internet according to claim 3 is characterized by: The temperature division of the melt in the temperature region determination unit (2) is specifically as follows: when When , the temperature area is the safe operating area; when When , the temperature area is a low temperature risk area; when When , the temperature area is a high temperature risk area; when or When , the temperature area is an extreme danger zone; in, is the melt temperature; is the critical low temperature value; is the critical high temperature value.

5. The industrial process collaborative optimization service system based on the Industrial Internet according to claim 4 is characterized in that: The temperature optimization and adjustment unit (4) includes a response model prediction module (41), a dual-objective optimization module (42) and a coordinated adjustment execution module (43); Among them, the response model prediction module (41) is used to construct a temperature relationship response model and input the collected operating data into the temperature relationship response model to predict the trajectory of melt temperature change over time and the cycle time and energy consumption fluctuation value required to reach a stable temperature; The dual-objective optimization module (42) predicts the cycle time required to reach the stable temperature based on the response model provided by the response model prediction module (41) according to the region where the melt temperature is located. and energy consumption fluctuations , taking injection speed and cooling power as collaborative decision variables to search for the optimal solution set, achieving dual-objective joint optimization, and finally outputting the optimal injection speed adjustment amount and optimal cooling power regulation ; The coordinated adjustment execution module (43) is used to adjust the amount according to the injection speed and cooling power adjustment Adjust the values ​​of injection speed and cooling power, and monitor the changes in melt temperature after the injection speed and cooling power are adjusted in real time.

6. The industrial process collaborative optimization service system based on the Industrial Internet according to claim 5 is characterized by: The specific steps of establishing the temperature relationship response model in the response model prediction module (41) are: S411, combining heat transfer equations and real-time data correction to build a linear model; S412, adding a nonlinear coupling function to the linear model to generate a nonlinear model; S413, the nonlinear model is divided into two groups according to the sampling period. Discretization, for the future Injection speed increment within a step , cooling power increment Iterate step by step to predict the temperature trajectory; S414, during the iteration process, when the predicted temperature enters the preset safe operating area and continuously When the temperature change amplitude of the time step is less than the temperature change amplitude threshold, the iteration is stopped and the prediction cycle time is calculated. , and record the predicted energy consumption data; S415. During the prediction cycle, the energy consumption values ​​generated by the heating power and cooling power corresponding to each time step are accumulated, and the standard deviation of the energy consumption sequence is calculated as the energy consumption fluctuation value. ; S416. Each time the melt temperature is adjusted to a safe operating zone, the actual cycle time and actual energy consumption are collected to update the parameters of the temperature relationship response model.

7. The industrial process collaborative optimization service system based on the Industrial Internet according to claim 6 is characterized by: The dual objectives in the dual objective optimization module (42) include minimizing the predicted cycle time and minimizing the energy consumption fluctuation value.

8. The industrial process collaborative optimization service system based on the Industrial Internet according to claim 7 is characterized in that: In the dual-objective optimization module (42), the constraints for achieving dual-objective joint optimization include the constraints of the injection speed range, the constraints of the cooling power range, the constraints of the predicted temperature trajectory, and the constraints of the temperature change rate; wherein the constraints of the predicted temperature trajectory specifically exist at a certain future time point within the cycle time, so that the predicted melt temperature at this time point enters the safe operating area for the first time and continues to remain in the safe operating area.

9. The industrial process collaborative optimization service system based on the Industrial Internet according to claim 8 is characterized by: In the dual-objective optimization module (42), the specific steps of searching for the optimal solution set by using the injection speed and the cooling power as collaborative decision variables are as follows: S421, injection speed increment and cooling power increment Generate an initial equidistant grid within the feasible range for discretization, and dynamically refine the grid based on the risk level of the real-time temperature area; S422. For each collaborative decision variable generated after discretization, call the temperature relationship response model to perform parallel prediction, and output the cycle time, energy consumption fluctuation, and melt temperature trajectory corresponding to the decision variable in real time; S423. Based on the constraints, exclude the decision points that do not meet the constraints, construct the objective function for the decision points that meet the constraints, introduce the material phase change kinetics penalty term into the objective function for optimization, and select the decision point with the smallest objective function value as the optimal solution.

10. The industrial process collaborative optimization service system based on the Industrial Internet according to claim 9 is characterized in that: In S423, the specific process of constructing the objective function is as follows: S1. Calculate a weight value based on the current melt temperature using a weight function. The weight function is designed as a monotonically decreasing function of the melt temperature, such that the penalty weight for energy consumption fluctuations is reduced in high-temperature risk areas and increased in low-temperature risk areas. S2. Setting an energy consumption fluctuation tolerance threshold, where the threshold is associated with the injection speed adjustment amount, constructing an objective function based on the energy consumption fluctuation tolerance threshold, calculating the objective function values ​​for all feasible decision points, and selecting the decision point that minimizes the objective function value as the optimal collaborative adjustment solution; S3. Introducing a material phase transition kinetic penalty term into the objective function for optimization; first, establishing a differential equation for crystallinity and temperature history to extract key phase transition indicators, including the minimum allowable crystallinity and the maximum allowable crystallization rate; According to the key phase transition index, a dynamic penalty term is established. Integrate it into the objective function to generate the optimized objective function.

Images