Mould temperature controller self-adaptive regulation and control method and system based on digital twinning

Abstract

The invention discloses a model temperature controller adaptive regulation and control method and system based on digital twinning, and relates to the technical field related to intelligent regulation and control, and the method comprises the steps: analyzing a model temperature controller regulation and control influence variable, constructing a multi-granularity simulation unit, and embedding a digital twinning model for operation simulation; obtaining a regulation variable and a regulation constraint condition, and configuring a self-adaptive regulation mechanism based on the regulation target and the sample data; simulation mapping is carried out through real-time monitoring data, regulation and control deviation characteristics are identified, and regulation and control compensation target parameters are positioned; and matching a corresponding self-adaptive regulation and control mechanism, and performing regulation and control parameter quantitative compensation regulation and control analysis to obtain a regulation and control strategy. The technical problems of low regulation and control precision, response lag and poor energy efficiency caused by the fact that mold temperature controller control depends on fixed parameters and experience adjustment and is difficult to adapt to dynamic change working conditions in the prior art are solved, and the technical effects of improving the mold temperature controller regulation and control precision, energy efficiency and response efficiency through multi-granularity simulation driven by digital twinning are achieved.

Description

Technical Field

[0001] This invention relates to the field of intelligent control technology, specifically to an adaptive control method and system for mold temperature controllers based on digital twins. Background Technology

[0002] Mold temperature controllers are critical temperature control devices in industrial fields such as injection molding, die casting, and composite material molding. Their temperature control accuracy and dynamic response performance directly affect product quality, production efficiency, and energy consumption. However, traditional mold temperature controller control modes mostly adopt fixed-parameter PID control strategies, relying on operator experience for parameter tuning. This makes it difficult to adapt to the production needs of multi-variety, small-batch, and high-precision manufacturing. In actual operation, mold temperature controllers are affected by multiple variables, including equipment parameters such as heating power, pump characteristics, and piping layout; operating parameters such as set temperature and flow rate; and working condition parameters such as ambient temperature, mold heat capacity, and material characteristics. These multiple parameters are coupled with each other and may change dynamically during production, leading to significant limitations in control. Fixed-parameter controllers cannot adapt to changes such as equipment aging and operating condition switching, resulting in overshoot, oscillation, or response lag. The control quality lacks a systematic and adaptive optimization mechanism, and it cannot pre-compensate for impending disturbances or setting changes, resulting in a passive response.

[0003] Therefore, in the current related technologies, there are technical problems such as mold temperature controllers relying on fixed parameters and experience-based adjustments, which makes it difficult to adapt to dynamically changing working conditions, resulting in low control accuracy, slow response, and poor energy efficiency. Summary of the Invention

[0004] This application provides a digital twin-based adaptive control method and system for mold temperature controllers, which solves the technical problems in the prior art where mold temperature controller control relies on fixed parameters and experience adjustments, making it difficult to adapt to dynamically changing working conditions, resulting in low control accuracy, slow response, and poor energy efficiency. It achieves the technical effect of improving the accuracy, energy efficiency, and high response efficiency of mold temperature controller control through multi-granularity simulation driven by digital twins.

[0005] This application provides an adaptive control method for mold temperature controllers based on digital twins. The method includes: analyzing the influencing variables of the mold temperature controller during the control process, constructing a multi-granularity simulation unit, and embedding it into the digital twin model as a built-in adjustment module for operation simulation. The influencing variables include equipment parameters, operating parameters, and working condition parameters. The method also includes acquiring control variables and control constraints related to the temperature control of the mold temperature controller; configuring an adaptive control mechanism for the control variables based on the control target and sample data, combined with the control constraints. This adaptive control mechanism includes fixed control, mapping compensation control, and computational control. The method further involves simulating and mapping the real-time monitoring data of the mold temperature controller through the digital twin model; identifying the control deviation characteristics of the current allowable state based on the interactive processing of the multi-granularity simulation unit; and locating the corresponding control compensation target parameter based on the control deviation characteristics. Finally, the method uses the control compensation target parameter to match the corresponding adaptive control mechanism, performs quantitative compensation control analysis of the control parameters according to the monitoring data, and obtains the control strategy.

[0006] In one possible implementation, the influence variables of the mold temperature controller during the control process are analyzed, and a multi-granularity simulation unit is constructed. This includes: collecting the operating data of the mold temperature controller during the temperature control process, and analyzing the influence variables affecting the mold temperature change based on the operating data; classifying the influence variables according to their physical properties and dynamic change characteristics; and constructing a multi-granularity simulation unit based on the classified influence variables and fitting the influence relationship according to the operating data.

[0007] In a possible implementation, based on the categorized influencing variables, the influence relationships are fitted according to the operational data to construct a multi-granularity simulation unit, including: for the categorized influencing variables, analyzing the characteristics and scale of the effects of various influencing variables on mold temperature changes in conjunction with the operational data, and determining the modeling granularity corresponding to different types of influencing variables; according to the operational data, fitting the influence relationships between different types of influencing variables and mold temperature response, and constructing a multi-granularity simulation unit corresponding to the modeling granularity.

[0008] In possible implementations, constructing multi-granularity simulation units corresponding to the modeling granularity includes: when the influencing variable is equipment parameter, analyzing the influence relationship between the change amplitude and rate of change of the influencing variable and the mold temperature response, and constructing fine-grained simulation units using parameter-level and amplitude-level granularity; when the influencing variable is operation parameter, analyzing the correspondence between the operation behavior type, target, and duration and the mold temperature controller state change, and constructing operation behavior simulation units using event-level granularity; when the influencing variable is operating condition parameter, analyzing the thermal load intensity, change rhythm, and coupling relationship between multiple operating condition parameters, and constructing operating condition simulation units using medium-granularity or fine-granularity that reflects the load state and interaction characteristics.

[0009] In a possible implementation, based on the control target and sample data, and in conjunction with the control constraints, an adaptive control mechanism for the control variables is configured, including: determining the control temperature target of the mold temperature controller; analyzing the dynamic characteristics of the influence of the control variables on the mold temperature using sample data, wherein the dynamic characteristics include sensitivity, response time delay, and coupling relationship; classifying the control variables into steady-state baseline parameters, rule-driven parameters, and dynamic core parameters according to the analysis results of the dynamic characteristics and the allowable state range defined by the control constraints; and configuring differentiated adaptive control mechanisms for different categories of control variables under the control constraints, wherein a fixed control mechanism is configured for the steady-state baseline parameters, a rule mapping compensation mechanism is configured for the rule-driven parameters, and a model prediction calculation control mechanism is configured for the dynamic core parameters.

[0010] In possible implementations, the control variables are classified into steady-state baseline parameters, rule-driven parameters, and dynamic core parameters. This includes: based on sample data, identifying parameters among the control variables that have a weak impact on mold temperature fluctuations or whose response time lag is much greater than the main dynamic cycle, and classifying them as steady-state baseline parameters; based on sample data, identifying parameters among the control variables whose changes have a clear mapping relationship with specific working conditions, process stages, or external events, and whose control values ​​can be determined based on preset rules or empirical models, and classifying them as rule-driven parameters; and based on sample data, identifying parameters among the control variables that are sensitive to temperature deviations, respond rapidly, and whose optimal control values ​​need to be calculated online to offset real-time disturbances and coupling effects, and classifying them as dynamic core parameters.

[0011] In a possible implementation, the real-time monitoring data of the mold temperature controller is simulated and mapped using the digital twin model. Based on the interactive processing of multi-granularity simulation units, the control deviation characteristics of the current allowable state are identified. This includes: extracting change features from the collected real-time monitoring data to obtain feature information reflecting the trend, magnitude, and rate of change of the mold temperature, and identifying the influencing variables whose degree of change reaches the control analysis threshold based on the feature information; mapping the real-time monitoring data and change features to the corresponding multi-granularity simulation units according to the identified influencing variable categories, performing simulation processing of the influencing variables, and obtaining the temperature control influence results of the influencing variables on the mold temperature control process; based on the comparative analysis between the temperature control influence results and the preset temperature control target, determining whether the current mold temperature controller operating state meets the temperature control target, and generating control deviation characteristics to characterize the deviation state of the current operating state if the temperature control target is not met.

[0012] In a possible implementation, the corresponding control compensation target parameter is located based on the control deviation characteristics, including: based on the control deviation characteristics, analyzing the influence correlation between the control deviation characteristics and each control variable in a multi-granularity simulation unit, screening control variables that have a major causal correlation with the current control deviation characteristics, and forming a set of control compensation candidate parameters; judging the effectiveness of the set of control compensation candidate parameters according to the current operating allowable state and control constraints, and eliminating control variables that do not meet safety constraints or stability constraints; and determining at least one control compensation target parameter from the control variables that meet the requirements to eliminate or alleviate the control deviation characteristics.

[0013] In a possible implementation, the adaptive control mechanism corresponding to the control compensation target parameter is matched, and the control parameter is quantitatively compensated and analyzed according to the monitoring data to obtain the control strategy. This includes: matching the adaptive control mechanism according to the parameter category and dynamic influence characteristics of the control compensation target parameter to determine the corresponding adaptive control mechanism; under the adaptive control mechanism, based on the real-time collected monitoring data and control constraints, quantitative analysis is performed on the compensation direction, compensation amplitude, and parameter update rate of the control compensation target parameter to generate parameter adjustment quantitative data as the control strategy; wherein, when there are multiple control compensation target parameters, the parameter adjustment quantitative data of multiple control compensation target parameters are combined by control timing analysis to obtain the control strategy, and adaptive control of the mold temperature controller is performed.

[0014] This application also provides an adaptive control system for a mold temperature controller based on digital twins. The system includes: an influencing variable analysis module, used to analyze the influencing variables of the mold temperature controller during the control process, construct multi-granularity simulation units, and embed them into the digital twin model as a built-in adjustment module for operational simulation. The influencing variables include equipment parameters, operating parameters, and working condition parameters. A control mechanism configuration module, used to acquire control variables and control constraints related to the temperature control of the mold temperature controller, and configure an adaptive control mechanism for the control variables based on the control target and sample data, combined with the control constraints. The adaptive control mechanism includes fixed control, mapping compensation control, and computational control. A target parameter positioning module, used to simulate and map the real-time monitoring data of the mold temperature controller through the digital twin model, identify the control deviation characteristics of the current allowable state based on the interactive processing of the multi-granularity simulation units, and locate the corresponding control compensation target parameter based on the control deviation characteristics. A compensation control analysis module, used to match the corresponding adaptive control mechanism using the control compensation target parameter, perform quantitative compensation control analysis of the control parameters according to the monitoring data, and obtain a control strategy.

[0015] This application proposes a digital twin-based adaptive control method and system for mold temperature controllers. This method analyzes the variables influencing mold temperature controller control, constructs multi-granularity simulation units, and embeds them into a digital twin model for operational simulation. It acquires control variables and constraints, configures an adaptive control mechanism based on control targets and sample data, performs simulation mapping using real-time monitoring data, identifies control deviation characteristics, and locates target parameters for control compensation. Finally, it matches the corresponding adaptive control mechanism, performs quantitative compensation control analysis of control parameters, and obtains the control strategy. This solves the technical problems in existing mold temperature controllers that rely on fixed parameters and experience-based adjustments, making it difficult to adapt to dynamically changing operating conditions, resulting in low control accuracy, slow response, and poor energy efficiency. It achieves the technical effect of improving the accuracy, energy efficiency, and high response efficiency of mold temperature controller control through multi-granularity simulation driven by a digital twin. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings of the embodiments of this disclosure will be briefly described below. Flowcharts are used in this application to illustrate the operations performed by the system according to the embodiments of this application. It should be understood that the preceding or following operations are not necessarily performed precisely in sequence. Instead, various steps can be processed in reverse order or simultaneously as needed. Furthermore, other operations can be added to these processes, or one or more steps can be removed from these processes.

[0017] Figure 1 A schematic diagram of the adaptive control method for mold temperature controller based on digital twin provided in the embodiments of this application.

[0018] Figure 2 A schematic diagram of the structure of a digital twin-based adaptive temperature control system for molds provided in this application embodiment.

[0019] Figure labeling: Module 10 for influencing variable analysis, Module 20 for regulation mechanism configuration, Module 30 for target parameter positioning, and Module 40 for compensation regulation analysis. Detailed Implementation

[0020] To further illustrate the technical means and effects adopted by the present invention in order to achieve the intended purpose, the following detailed description is provided in conjunction with the accompanying drawings and preferred embodiments, based on the specific implementation methods, structures, features and effects of the present invention.

[0021] This application provides an adaptive control method for mold temperature controllers based on digital twins, such as... Figure 1 As shown, the method includes:

[0022] Step S100: Analyze the influencing variables of the mold temperature controller during the control process, construct a multi-granularity simulation unit, and embed it into the digital twin model as a built-in adjustment module for operation simulation. The influencing variables include equipment parameters, operating parameters, and working condition parameters.

[0023] Step S100 further includes collecting the operating data of the mold temperature controller during the temperature control process, and analyzing the influencing variables affecting the mold temperature change based on the operating data; classifying the influencing variables according to their physical properties and dynamic change characteristics; and constructing a multi-granularity simulation unit based on the classified influencing variables and fitting the influence relationship according to the operating data.

[0024] Preferably, the operating data of the mold temperature controller during actual temperature control is collected, including measured or state values ​​of the actual mold temperature, heater power, circulating medium flow rate, pump pressure, inlet and outlet medium temperature, ambient temperature, and current production cycle stage, etc., changing over time. The operating data is analyzed using correlation analysis, principal component analysis, etc., to identify and determine the variables affecting mold temperature changes, including equipment parameters, operating parameters, and working condition parameters. Equipment parameters include the inherent attributes, configuration status, or performance characteristics of the mold temperature controller, such as heating unit parameters like the rated power of the heater, and circulating unit parameters like the rated flow rate and head characteristics of the pump. Meta-parameters include control unit parameters such as temperature sensor measurement accuracy and response time; operational parameters are the operational behaviors and status parameters that affect the mold temperature regulation behavior during the operation of the mold temperature controller, triggered by manual operation or the upper control system, such as mold changing operation, mold preheating / precooling command, and mold locking / unlocking command; and working condition parameters are the status parameters that affect the mold's thermal load and temperature response during the operation of the mold temperature controller, caused by changes in the production process, external environment, or process state and not directly generated by control commands, such as the heat carried away by a single cycle of products, the average heat dissipation power of the mold, and the heat input / output per unit time.

[0025] Preferably, the physical properties and dynamic characteristics of the influencing variables are analyzed and determined, and these variables are classified. Physical properties include temperature, flow rate, pressure, power, on / off status, or time setpoints. Dynamic characteristics refer to the time-related behavioral features exhibited by the variables during system operation, such as the magnitude of change, rate of change, and coupling relationship with temperature response lag time and response intensity. Then, based on the classified influencing variables, the influence relationships are fitted according to the operating data. This involves using data-driven or physical laws-based methods to establish the correlation between each type of influencing variable and the mold temperature response. This includes determining the mapping rules from the influencing variable values ​​to mold temperature changes and constructing multi-granularity simulation units with varying degrees of granularity, potentially with different temporal and spatial detail granularities, to reflect the dynamic behavior of the real mold temperature controller at different levels. These multi-granularity simulation units are embedded in the digital twin model. Each simulation unit is connected according to real physical, logical, and data interaction relationships, serving as a built-in adjustment module for operational simulation. Based on the input operation instructions / parameters and current operating conditions, all relevant simulation units are driven to operate collaboratively, calculating the evolution trajectory of key variables such as mold temperature in real time based on current equipment parameters.

[0026] Furthermore, step S100 also includes, for the classified influencing variables, analyzing the characteristics and scale of the effects of various influencing variables on the mold temperature change in conjunction with the running data, determining the modeling granularity corresponding to different types of influencing variables; and fitting the influence relationship between different types of influencing variables and the mold temperature response based on the running data, constructing a multi-granularity simulation unit corresponding to the modeling granularity.

[0027] Preferably, by combining operational data analysis to determine the characteristics and scale of the effects of various influencing variables on mold temperature changes, the corresponding modeling granularity is determined for each type of influencing variable. Among them, the characteristics of the effect refer to the influence of the variable on the mold temperature, including the intensity of the effect, the mode of the effect, and the dynamic response. The intensity of the effect represents the amount of temperature change caused by a unit change in the variable. For example, if the heating power is increased by 1kW, the mold temperature rises by 2°C per minute, and the ambient temperature changes by 1°C, causing the mold temperature to change by 0.1°C per minute. The mode of the effect represents the effect on the heat transfer medium, ambient temperature, or system structure. The dynamic response is immediately reflected or has significant time lag and inertia. The scale of change refers to the range of dynamic behavior of the influencing variable itself, including the rate of change of the variable value and the magnitude of fluctuation within its effective range. For core influencing variables with strong effects, rapid changes, and sensitive responses, such as heating power, high-granularity modeling is adopted, for example, using simulation step sizes on the order of milliseconds or seconds, using differential equations based on physical laws to describe its dynamic process, and considering the response lag of sensors and the dynamic characteristics of actuators. For influencing variables with weak effects, slow changes, or long response lags, such as ambient temperature and the efficiency of equipment that has been aging for a long time, coarse-granular modeling is adopted, for example, using simulation step sizes on the order of minutes or even longer, using simple linear regression models to describe the dynamic process. For influencing variables related to specific events, such as starting a cooling operation, it is modeled as a discrete event trigger, which switches to a preset state or enables preset parameters when the event occurs.

[0028] Preferably, operational data is used to fit the influence relationship between different types of influencing variables and the mold temperature response. Specifically, for fine-grained core influencing variables, dynamic system identification is used to fit transfer functions or state-space equations. For example, ARMAX, state-space models, etc., are used to identify dynamic models containing first- or second-order lags from power-temperature data. For medium- and coarse-grained variables, support vector machine regression may be used to establish a static or quasi-static mapping from input variables to the rate of change of temperature output. Then, corresponding multi-granularity simulation units are constructed. The fine-grained simulation unit is a solver of a set of differential equations, which needs to receive real-time power at a high frequency, such as 100 times per second, and output the predicted medium temperature at the same high frequency. The event-level simulation unit is a rule judge used to listen for operation events. When an event is triggered, it immediately outputs a new target value or switches to a new control mode parameter group. The coarse-grained simulation unit is a simple linear corrector that calculates correction coefficients based on slowly changing inputs at relatively long intervals, such as every 5 minutes, and passes them to other components. Multi-granularity simulation units work collaboratively under the scheduling of the digital twin engine, enabling them to quickly and precisely simulate core dynamics while efficiently and flexibly handling events and slowly varying parameters. This achieves the best balance between simulation accuracy and computational efficiency, enabling real-time adaptive control and analysis.

[0029] Furthermore, step S100 also includes, when the influencing variable is equipment parameter, analyzing the influence relationship between the change amplitude and change rate of the influencing variable and the mold temperature response, and constructing a fine-grained simulation unit using parameter-level and amplitude-level granularity; when the influencing variable is operation parameter, analyzing the correspondence between the operation behavior type, action object and duration and the mold temperature controller state change, and constructing an operation behavior simulation unit using event-level granularity; when the influencing variable is operating condition parameter, analyzing the thermal load intensity, change rhythm and coupling relationship between multiple operating condition parameters, and constructing an operating condition simulation unit using medium-grained or fine-grained granularity that reflects the load state and interaction characteristics.

[0030] Preferably, when the influencing variable is the equipment parameter, the effective working range and physical response limit of the equipment parameter are analyzed, and the influence relationship between the change amplitude and rate of change and the mold temperature response is established through energy conservation, heat transfer, etc. Parameter-level granularity refers to accurately representing the specific value and state of the equipment parameter itself in the model. For example, the heater's "rated power 30kW", "current actual output power 22.5kW", and "thermal efficiency decay coefficient 0.95". Amplitude-level granularity refers to accurately simulating the entire process details of the parameter's dynamic change in the model. It not only simulates "power changing from 20kW to 25kW", but also simulates the intermediate process of its increase at a rate of 2kW / s, as well as the differential contribution of each step to the temperature. Fine-grained simulation unit modeling is usually based on physical differential equations and solved by continuous numerical integration with a very small time step to capture subtle changes in the equipment dynamics. In each simulation step, the fine-grained simulation unit calculates the small change in the heating rod temperature based on the precise instantaneous value of the current input power.

[0031] Preferably, when the influencing variable is the operating parameter, the analysis focuses on the correspondence between the operating behavior type "set temperature", "start / stop", "switch PID mode" or "cleaning command", the target and duration of the operation and the state change of the temperature controller. When a specific operating event occurs, an operating behavior simulation unit is constructed. Its core is a state machine / rule mapping. When an operating event is received, the preset logic is immediately executed, the target temperature state variable is modified, and an event requiring temperature increase may be triggered to be sent to the controller. It is only responsible for issuing instructions to change the system target or mode.

[0032] Preferably, when the influencing variable is the operating condition parameter, the power of the heat removed or added from the mold by the external process, the time law of the change of thermal load, and the interaction of different operating condition parameters with temperature are analyzed. Medium-grained or fine-grained operating condition simulation units that reflect the load state and interaction characteristics are used. Specifically, when a certain operating condition parameter changes drastically and is closely coupled with the temperature response, fine-grained modeling is used to establish its dynamic differential equation and its instantaneous thermal disturbance to the system is calculated at high frequency. When some operating condition parameters change relatively slowly or the effects can be aggregated, medium-grained modeling is used. For example, an equivalent thermal resistance / thermal capacity network is used to approximate the complex thermal behavior of the mold, and a statistical model or the average value after filtering is used to represent its influence.

[0033] Step S200: Obtain the control variables and control constraints related to the temperature control of the mold temperature controller. Based on the control target and sample data, and in combination with the control constraints, configure the adaptive control mechanism of the control variables. The adaptive control mechanism includes fixed control, mapping compensation control, and computational control.

[0034] Step S200 further includes determining the target temperature for the mold temperature controller, analyzing the dynamic characteristics of the influence of the control variables on the mold temperature using sample data, wherein the dynamic characteristics include sensitivity, response time delay, and coupling relationship; classifying the control variables into steady-state baseline parameters, rule-driven parameters, and dynamic core parameters based on the analysis results of the dynamic characteristics and the allowable state range defined by the control constraints; and configuring differentiated adaptive control mechanisms for different categories of control variables under the control constraints, wherein a fixed control mechanism is configured for the steady-state baseline parameters, a rule mapping compensation mechanism is configured for the rule-driven parameters, and a model prediction calculation control mechanism is configured for the dynamic core parameters.

[0035] Preferably, the control variables related to the temperature control of the mold temperature controller are obtained, and the target temperature of the mold temperature controller is determined. For example, the mold temperature is controlled at 180℃±1℃. The dynamic characteristics of the influence of the control variables on the mold temperature are analyzed using sample data, including sensitivity, response lag, and coupling relationship. Sensitivity represents the specific change in mold temperature caused by changing the control variable by one unit. For example, if the heating power increases by 1kW, the steady-state temperature of the mold may rise by 5℃, which is high sensitivity. Response lag represents the time elapsed from the change of the control variable to the start of an observable response in the mold temperature. For example, if the temperature sensor starts to change after 3 seconds when the heating power is changed, it indicates a response lag. Coupling relationship represents the effect of a change in one control variable on other variables or the effect of being affected by other variables. For example, the heating power and the opening of the cooling water valve are strongly coupled. When the heating power is increased, it may be necessary to pre-adjust the cooling water valve simultaneously, otherwise oscillation may occur. Finally, the analysis results of the dynamic characteristics are obtained.

[0036] Preferably, control constraints are obtained, namely, the allowable operating range of safety, quality, and equipment, such as the heater surface temperature not exceeding 300℃ and the mold temperature change rate not exceeding 5℃ / second. Combined with the analysis results of dynamic characteristics, the control variables are classified into steady-state baseline parameters, rule-driven parameters, and dynamic core parameters. Steady-state baseline parameters refer to parameters whose impact on temperature fluctuations is extremely weak or whose changes are much slower than the main control cycle, such as the slight decrease in efficiency caused by long-term aging of the heater or the viscosity change of heat transfer oil after long-term use. Rule-driven parameters refer to parameters whose optimal values ​​have a clear mapping relationship with the current operating conditions, process stage, or specific events, such as the optimal PID parameter set corresponding to molds of different materials or the optimal base speed of the circulating pump when switching between the preheating and production stages. Dynamic core parameters refer to parameters that are highly sensitive to temperature deviations, respond rapidly, and whose optimal values ​​must be calculated online in real time to cope with rapidly changing disturbances and coupled effects, such as the real-time set value of heating power and the real-time opening of the cooling water regulating valve, which need to be adjusted quickly and accurately at all times to offset real-time disturbances caused by melt injection and environmental fluctuations.

[0037] Preferably, under the condition of satisfying the control constraints, differentiated adaptive control mechanisms are configured for different categories of control variables. Specifically, the steady-state baseline parameters change extremely slowly and have little impact on short-term control. A fixed control mechanism is configured for the steady-state baseline parameters, which are periodically calibrated and updated based on maintenance data or long-term trend analysis, i.e., maintained at a fixed value or fixed curve for a considerable period of time. A rule mapping compensation mechanism is configured for rule-driven parameters, which uses domain knowledge and historical data to solidify the summable experience, achieve fast and accurate feedforward compensation, and establish a condition-action rule mapping table. When the system state or external event meets specific conditions, it is automatically triggered and switched to the corresponding preset parameter value. A dynamic core parameter is configured with... The system employs a model-based predictive computation control mechanism. This mechanism uses a built-in multi-granularity digital twin model as a predictor, combined with current real-time monitoring data, to perform real-time optimization. Specifically, based on the current system state and the digital twin model, it predicts the specific temperature changes over a future period while maintaining the current control. Under the premise of satisfying all constraints, it calculates multiple future control action sequences to ensure that the predicted temperature trajectory most smoothly and accurately approaches the target while minimizing energy consumption. Then, the first step of the future control action sequence is sent to the corresponding physical device. New data is collected and the calculation is repeated in the next control cycle. This proactively coordinates multiple coupled variables to achieve globally optimal control, thereby comprehensively improving the control accuracy, response speed, and energy efficiency of the temperature controller.

[0038] Furthermore, step S200 also includes, based on sample data, identifying parameters among the control variables that have a weak impact on mold temperature fluctuations or whose response time lag is much greater than that of the main dynamic cycle, and classifying them as steady-state baseline parameters; based on sample data, identifying parameters among the control variables whose changes have a clear mapping relationship with specific working conditions, process stages, or external events, and whose control values ​​can be determined based on preset rules or empirical models, and classifying them as rule-driven parameters; based on sample data, identifying parameters among the control variables that are sensitive to temperature deviations, respond rapidly, and whose optimal control values ​​need to be calculated online to offset real-time disturbances and coupling effects, and classifying them as dynamic core parameters.

[0039] Preferably, correlation analysis or disturbance analysis is performed on the sample data to calculate the influence coefficient. Simultaneously, the dominant time constant from the parameter to the temperature response is estimated through step response testing. Parameters whose temperature changes caused by fluctuations within the normal range are far less than the system's allowable temperature control accuracy, or whose temperature changes only occur after a period far exceeding the main dynamic cycle time, are classified as steady-state baseline parameters. Cluster analysis is used to analyze the sample data to classify parameters whose adjustment timing and direction are mapped to certain observable, discrete state transitions, and whose control values ​​can be directly determined by looking up tables, formulas, or empirical rules, as rule-driven parameters. Data analysis is performed on the sample data to confirm that the parameter has high sensitivity gain and short time constant / hour lag. Successful control cases in historical data are analyzed to assess the complexity of control. Parameters whose small adjustments to the control variables can cause significant and rapid temperature changes, and whose optimal control values ​​need to be calculated online using the latest system state model and predicted future disturbances to offset real-time disturbances and coupling effects, are classified as dynamic core parameters.

[0040] Step S300: The real-time monitoring data of the temperature controller is simulated and mapped using the digital twin model. Based on the interactive processing of multi-granularity simulation units, the control deviation characteristics of the current allowable state are identified, and the corresponding control compensation target parameters are located based on the control deviation characteristics.

[0041] Step S300 further includes: extracting change features from the collected real-time monitoring data to obtain feature information reflecting the trend, magnitude, and rate of change of the mold temperature; identifying influencing variables whose degree of change reaches the control analysis threshold based on the feature information; mapping the real-time monitoring data and change features to the corresponding multi-granularity simulation unit according to the identified influencing variable category, performing simulation processing of the influencing variables, and obtaining the temperature control influence result of the influencing variables on the mold temperature control process; based on the comparative analysis between the temperature control influence result and the preset temperature control target, determining whether the current mold temperature controller operating state meets the temperature control target, and generating a control deviation feature to characterize the deviation state of the current operating state if the temperature control target is not met.

[0042] Preferably, real-time monitoring data streams from the mold temperature controller are continuously collected, such as mold temperature, heating power, flow rate, and ambient temperature. Change characteristics are extracted to obtain feature information reflecting the trend, amplitude, and rate of change of the mold temperature. Specifically, the change trend is determined by calculating the first derivative or linear fitting slope of the key signal within a recent time window to determine whether it is "continuously rising," "continuously falling," or "tending to stabilize." The change amplitude is determined by calculating the difference between the maximum and minimum values ​​of the key signal in the recent period, or the absolute deviation from its set value / average value, to determine the severity of the fluctuation. The change rate is determined by calculating the instantaneous change rate or the average change rate of the key signal in the short term, to determine the speed of change. Based on historical data, a control analysis threshold is preset. Influencing variables whose change amplitude or rate exceeds the control analysis threshold are identified based on the feature information and marked as target variables requiring simulation analysis.

[0043] Preferably, based on the identified categories of influencing variables, real-time monitoring data and extracted change features are mapped to corresponding multi-granularity simulation units in the digital twin model to perform simulation processing of the influencing variables. That is, based on the received real-time monitoring data and change features, the influence of the variable on the thermodynamic state of the entire system under its current state of continuous change is simulated in a virtual environment. At the same time, the simulation unit interacts with the heater unit and the mold unit to complete the coupled simulation, predicts and outputs the future trajectory of the mold temperature, and serves as the temperature control effect result of the influencing variable on the mold temperature regulation process. This may be a predicted temperature-time curve or a predicted temperature-time curve. The results of temperature control impact are compared and analyzed with the preset temperature control target to determine whether the current operating status of the mold temperature controller meets the temperature control target. If all temperature control targets can be met, the current operating status is determined to be healthy and no control intervention is required. If the temperature control target cannot be met, such as the predicted temperature will exceed the tolerance zone or the heating rate will exceed the limit, the current status is determined to be unhealthy. Structured control deviation features are generated to characterize the deviation behavior pattern of the mold temperature relative to the control target. The control deviation feature set includes at least the amplitude feature reflecting the degree of temperature deviation, the rate of change feature reflecting the temperature change trend, the response feature reflecting the dynamic behavior of the system, and the constraint proximity feature reflecting the control boundary state. Among them, different control deviation features are used to indicate the control responsibility attribution of different types of control parameters.

[0044] Furthermore, step S300 also includes: based on the control deviation characteristics, analyzing the influence correlation between the control deviation characteristics and each control variable in the multi-granularity simulation unit, screening control variables that have a major causal correlation with the current control deviation characteristics, and forming a set of control compensation candidate parameters; judging the effectiveness of the set of control compensation candidate parameters according to the current operating allowable state and control constraints, and eliminating control variables that do not meet safety constraints or stability constraints; and determining at least one control compensation target parameter from the control variables that meet the requirements to eliminate or alleviate the control deviation characteristics.

[0045] Preferably, the control deviation characteristics are used as input, and a digital twin model composed of multi-granularity simulation units is used to conduct virtual sensitivity tests or attribution analyses. That is, the candidate control variables are slightly adjusted, and the predicted deviation correction magnitude is quickly re-simulated and observed. By analyzing the Jacobian matrix between each simulation unit, the correction ability weight of each control variable to the current specific type of deviation characteristics is quantitatively calculated, the influence correlation between the control deviation characteristics and each control variable is determined, and the control variables with the main causal correlation with the current control deviation characteristics are screened to form a set of control compensation candidate parameters.

[0046] Preferably, based on the current permissible operating conditions and control constraints, including safety constraints, stability constraints, and production process constraints, an effectiveness judgment is made. This involves determining whether adjusting each parameter in the candidate set of control compensation parameters, according to its maximum correction potential, violates the control constraints. Control variables that do not meet safety or stability constraints are eliminated. For example, the candidate parameter "heating power" is used to compensate for a -1.5℃ deviation, and calculations require increasing it from 80% to 95%, but the constraint stipulates that "the long-term operating power of the heater must not exceed 90%", so this option is eliminated. Similarly, the candidate parameter "cooling water valve" requires reducing it from 50% to 10%, but the constraint stipulates that "the minimum opening of the cooling water valve must not be less than 15% to prevent blockage and local overheating", so this option is eliminated. From the control variables that meet the requirements, at least one control compensation target parameter is determined based on correction efficiency, response speed, energy consumption cost, or parameter synergy to eliminate or mitigate control deviation characteristics. This ensures comprehensive optimization across safety, effectiveness, and rapid response dimensions, enabling robust and efficient control decisions.

[0047] Step S400: Using the adaptive control mechanism corresponding to the control compensation target parameter matching, quantitative compensation control analysis of the control parameters is performed according to the monitoring data to obtain the control strategy.

[0048] Step S400 further includes: matching adaptive control mechanisms based on the parameter category and dynamic influence characteristics of the control compensation target parameters to determine the corresponding adaptive control mechanism; under the adaptive control mechanism, based on real-time collected monitoring data and control constraints, quantitatively analyzing the compensation direction, compensation amplitude, and parameter update rate of the control compensation target parameters to generate parameter adjustment quantitative data as the control strategy; wherein, when there are multiple control compensation target parameters, the parameter adjustment quantitative data of multiple control compensation target parameters are combined by control timing analysis to obtain the control strategy and perform adaptive control of the mold temperature controller.

[0049] Preferably, based on the parameter category of the target parameter for regulation and compensation, and the dynamic influence characteristics such as sensitivity, response lag, and coupling strength, a corresponding adaptive regulation mechanism is determined for each parameter category. Specifically, if it is a steady-state baseline parameter, a fixed regulation mechanism is matched; if it is a rule-driven parameter, a rule mapping compensation mechanism is matched; and if it is a dynamic core parameter, a model prediction and operation regulation mechanism is matched. Then, under the adaptive regulation mechanism, the compensation direction, compensation amplitude, and parameter update rate of the target parameter for regulation and compensation are quantitatively analyzed using real-time collected monitoring data and regulation constraints as input. Specifically, the compensation direction determines whether the parameter increases or decreases, such as increasing the heating power or decreasing the cooling water valve to compensate for insufficient heating; the compensation amplitude is the calculated value or percentage that needs to be adjusted, such as the optimal heating power should be linearly increased from the current 75% to 82% within the next 10 seconds; and the parameter update rate refers to the speed at which the adjustment is executed, such as an immediate step or a gradual change according to a specific slope. This generates quantitative data on parameter adjustment as a regulation strategy.

[0050] Preferably, if the adjustment of multiple parameters occurs simultaneously, they may interfere with each other or even cause oscillations. When there are multiple control and compensation target parameters, the quantitative data of parameter adjustment of multiple control and compensation target parameters are analyzed and combined using control timing analysis. That is, the dynamic characteristics and coupling relationship of each parameter are analyzed, and the adjustment order, parallel relationship or effective time of multiple control and compensation target parameters are coordinated to adjust their parameter control priority and adjustment effect. Finally, a time-lined, coordinated action sequence is generated and sent to the mold temperature controller as a control strategy for adaptive control to ensure that the control target is achieved quickly, smoothly and accurately, thereby improving the accuracy, energy efficiency and high response efficiency of mold temperature controller control.

[0051] In the above text, refer to Figure 1 The adaptive control method for mold temperature controller based on digital twins according to embodiments of the present invention is described in detail. Next, reference will be made to... Figure 2 A digital twin-based adaptive control system for mold temperature controllers is described according to an embodiment of the present invention.

[0052] The adaptive control system for mold temperature controllers based on digital twins according to embodiments of the present invention addresses the technical problems in existing technologies where mold temperature controller control relies on fixed parameters and experience-based adjustments, making it difficult to adapt to dynamically changing operating conditions, resulting in low control accuracy, slow response, and poor energy efficiency. It achieves the technical effect of improving the accuracy, energy efficiency, and high response efficiency of mold temperature controller control through multi-granularity simulation driven by digital twins. Figure 2 As shown, the adaptive control system for mold temperature controller based on digital twin includes: an influencing variable analysis module 10, a control mechanism configuration module 20, a target parameter positioning module 30, and a compensation control analysis module 40.

[0053] The influencing variable analysis module 10 is used to analyze the influencing variables of the mold temperature controller during the control process, construct a multi-granularity simulation unit, and embed it into the digital twin model as a built-in adjustment module for operation simulation. The influencing variables include equipment parameters, operating parameters, and working condition parameters. The control mechanism configuration module 20 is used to acquire the control variables and control constraints related to the temperature control of the mold temperature controller. Based on the control target and sample data, combined with the control constraints, it configures the adaptive control mechanism of the control variables. The adaptive control mechanism includes fixed control, mapping compensation control, and computational control. The target parameter positioning module 30 is used to simulate and map the real-time monitoring data of the mold temperature controller through the digital twin model. Based on the interactive processing of the multi-granularity simulation unit, it identifies the control deviation characteristics of the current allowable state and locates the corresponding control compensation target parameter based on the control deviation characteristics. The compensation control analysis module 40 is used to match the corresponding adaptive control mechanism with the control compensation target parameter, perform quantitative compensation control analysis of the control parameters according to the monitoring data, and obtain the control strategy.

[0054] The specific configuration of the influencing variable analysis module 10 will be described in detail below. The influencing variable analysis module 10 further includes: collecting the operating data of the mold temperature controller during the temperature control process, and analyzing the influencing variables affecting the mold temperature change based on the operating data; classifying the influencing variables according to their physical properties and dynamic change characteristics; and constructing a multi-granularity simulation unit based on the classified influencing variables and fitting the influence relationship according to the operating data.

[0055] The specific configuration of the influencing variable analysis module 10 will be described in detail below. The influencing variable analysis module 10 further includes: for the classified influencing variables, analyzing the characteristics and scale of the effect of each type of influencing variable on the mold temperature change in combination with the running data, and determining the modeling granularity corresponding to different types of influencing variables; based on the running data, fitting the influence relationship between different types of influencing variables and the mold temperature response, and constructing a multi-granularity simulation unit corresponding to the modeling granularity.

[0056] The following will describe the specific configuration of the influencing variable analysis module 10 in detail. The influencing variable analysis module 10 further includes: for equipment parameters, analyzing the relationship between the magnitude and rate of change of the influencing variable and the mold temperature response, and constructing fine-grained simulation units using parameter-level and amplitude-level granularity; for operation parameters, analyzing the correspondence between the operation behavior type, target, and duration and the mold temperature controller state changes, and constructing operation behavior simulation units using event-level granularity; for operating condition parameters, analyzing the thermal load intensity, change rhythm, and coupling relationship between multiple operating condition parameters, and constructing operating condition simulation units using medium-grained or fine-grained granularity reflecting load state and interaction characteristics.

[0057] The specific configuration of the control mechanism configuration module 20 will be described in detail below. The control mechanism configuration module 20 further includes: determining the target temperature of the mold temperature controller; analyzing the dynamic characteristics of the influence of the control variables on the mold temperature using sample data, wherein the dynamic characteristics include sensitivity, response time delay, and coupling relationship; classifying the control variables into steady-state baseline parameters, rule-driven parameters, and dynamic core parameters based on the analysis results of the dynamic characteristics and the allowable state range defined by the control constraints; and configuring differentiated adaptive control mechanisms for different categories of control variables under the control constraints, wherein a fixed control mechanism is configured for the steady-state baseline parameters, a rule mapping compensation mechanism is configured for the rule-driven parameters, and a model prediction calculation control mechanism is configured for the dynamic core parameters.

[0058] The following will describe in detail the specific configuration of the control mechanism configuration module 20. The control mechanism configuration module 20 further includes: based on sample data, identifying parameters in the control variables that have a weak impact on mold temperature fluctuations or whose response time lag is much greater than the main dynamic cycle, and classifying them as steady-state baseline parameters; based on sample data, identifying parameters in the control variables whose changes have a clear mapping relationship with specific working conditions, process stages, or external events, and whose control values ​​can be determined based on preset rules or empirical models, and classifying them as rule-driven parameters; based on sample data, identifying parameters in the control variables that are sensitive to temperature deviations, respond rapidly, and whose optimal control values ​​need to be calculated online to offset real-time disturbances and coupling effects, and classifying them as dynamic core parameters.

[0059] The specific configuration of the target parameter positioning module 30 will be described in detail below. The target parameter positioning module 30 further includes: extracting change features from the collected real-time monitoring data to obtain feature information reflecting the trend, magnitude, and rate of change of the mold temperature; identifying influencing variables whose degree of change reaches the control analysis threshold based on the feature information; mapping the real-time monitoring data and change features to the corresponding multi-granularity simulation unit according to the identified influencing variable category, performing simulation processing of the influencing variables, and obtaining the temperature control influence result of the influencing variables on the mold temperature control process; based on the comparative analysis between the temperature control influence result and the preset temperature control target, determining whether the current mold temperature controller operating state meets the temperature control target, and generating a control deviation feature to characterize the deviation state of the current operating state if the temperature control target is not met.

[0060] The specific configuration of the target parameter positioning module 30 will be described in detail below. The target parameter positioning module 30 further includes: analyzing the influence correlation between the control deviation characteristics and various control variables in a multi-granularity simulation unit based on the control deviation characteristics; screening control variables that have a major causal correlation with the current control deviation characteristics to form a set of control compensation candidate parameters; judging the effectiveness of the set of control compensation candidate parameters according to the current operating allowable state and control constraints, and eliminating control variables that do not meet safety or stability constraints; and determining at least one control compensation target parameter from the control variables that meet the requirements to eliminate or alleviate the control deviation characteristics.

[0061] The specific configuration of the compensation and control analysis module 40 will be described in detail below. The compensation and control analysis module 40 further includes: matching adaptive control mechanisms based on the parameter category and dynamic influence characteristics of the control and compensation target parameters to determine the corresponding adaptive control mechanism; under the adaptive control mechanism, based on real-time collected monitoring data and control constraints, quantitatively analyzing the compensation direction, compensation amplitude, and parameter update rate of the control and compensation target parameters to generate parameter adjustment quantitative data as the control strategy; wherein, when there are multiple control and compensation target parameters, the parameter adjustment quantitative data of multiple control and compensation target parameters are combined through control timing analysis to obtain the control strategy and perform adaptive control of the mold temperature controller.

[0062] The adaptive temperature control system for mold temperature controllers based on digital twins provided in this invention can execute the adaptive temperature control method for mold temperature controllers based on digital twins provided in any embodiment of this invention, and has the corresponding functional modules and beneficial effects of the method.

[0063] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any modifications, equivalent changes, and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A method for adaptive control of mold temperature controller based on digital twin, characterized in that, include: The influencing variables of the mold temperature controller during the control process are analyzed, and a multi-granularity simulation unit is constructed and embedded into the digital twin model as a built-in adjustment module for operation simulation. The influencing variables include equipment parameters, operating parameters, and working condition parameters. The control variables and control constraints related to the temperature control of the mold temperature controller are obtained. Based on the control target and sample data, and combined with the control constraints, an adaptive control mechanism for the control variables is configured. The adaptive control mechanism includes fixed control, mapping compensation control, and computational control. The real-time monitoring data of the mold temperature controller is simulated and mapped using the digital twin model. Based on the interactive processing of multi-granularity simulation units, the control deviation characteristics of the current allowable state are identified, and the corresponding control compensation target parameters are located based on the control deviation characteristics. By utilizing the adaptive control mechanism that matches the target parameters of the control compensation, quantitative compensation control analysis of the control parameters is performed based on the monitoring data to obtain the control strategy.

2. The adaptive control method for mold temperature controller based on digital twin as described in claim 1, characterized in that, The influencing variables of the mold temperature controller during the control process are analyzed, and a multi-granularity simulation unit is constructed, including: The operating data of the mold temperature controller during the temperature control process is collected, and the variables affecting the mold temperature change are analyzed based on the operating data. Based on the physical properties and dynamic change characteristics of the influencing variables, the influencing variables are classified. Based on the categorized influencing variables, the influencing relationships are fitted according to the operational data to construct multi-granularity simulation units.

3. The adaptive control method for mold temperature controller based on digital twin according to claim 2, characterized in that, Based on the categorized impact variables, the impact relationships are fitted according to the operational data to construct multi-granularity simulation units, including: For the categorized influencing variables, the characteristics and scale of the effects of each type of influencing variable on the mold temperature change are analyzed in conjunction with the operational data, and the modeling granularity corresponding to different types of influencing variables is determined. Based on the operational data, the influence relationship between different types of influencing variables and the mold temperature response is fitted, and a multi-granularity simulation unit corresponding to the modeling granularity is constructed.

4. The adaptive control method for mold temperature controller based on digital twin according to claim 3, characterized in that, Constructing a multi-granularity simulation unit corresponding to the modeling granularity includes: When the influencing variable is equipment parameter, the influence relationship between the magnitude and rate of change of the influencing variable and the mold temperature response is analyzed, and fine-grained simulation units are constructed using parameter-level and amplitude-level granularity. When the influencing variable is an operational parameter, the correspondence between the operational behavior type, the object of action, and the duration and the state change of the mold temperature controller is analyzed, and an operational behavior simulation unit is constructed using event-level granularity. When the influencing variables are operating condition parameters, the analysis focuses on the coupling relationship between thermal load intensity, variation rhythm, and multiple operating condition parameters. Medium-grained or fine-grained operating condition simulation units that reflect load status and interaction characteristics are constructed.

5. The adaptive control method for mold temperature controller based on digital twin according to claim 1, characterized in that, Based on the control objective and sample data, and in conjunction with the control constraints, an adaptive control mechanism for the control variable is configured, including: The target temperature for the mold temperature controller is determined, and the dynamic characteristics of the influence of the control variables on the mold temperature are analyzed using sample data. The dynamic characteristics include sensitivity, response time delay, and coupling relationship. Based on the analysis results of the dynamic characteristics and the allowable state range limited by the control constraints, the control variables are classified into steady-state baseline parameters, rule-driven parameters, and dynamic core parameters. Under the condition of satisfying the regulation constraints, differentiated adaptive regulation mechanisms are configured for different categories of regulation variables, including a fixed regulation mechanism for the steady-state baseline parameters, a rule mapping compensation mechanism for the rule-driven parameters, and a model prediction operation regulation mechanism for the dynamic core parameters.

6. The adaptive control method for mold temperature controller based on digital twin according to claim 5, characterized in that, The regulatory variables are classified into steady-state baseline parameters, rule-driven parameters, and dynamic core parameters, including: Based on sample data, parameters among the control variables that have a weak impact on mold temperature fluctuations or whose response time lag is much greater than that of the main dynamic cycle are identified and classified as steady-state baseline parameters. Based on sample data, identify the changes in control variables that have a clear mapping relationship with specific operating conditions, process stages or external events, and classify the control values ​​as rule-driven parameters that can be determined based on preset rules or empirical models. Based on sample data, parameters that are sensitive to temperature deviations, respond rapidly, and whose optimal control values ​​need to be calculated online to offset real-time disturbances and coupling effects are identified and classified as dynamic core parameters.

7. The adaptive control method for mold temperature controller based on digital twin according to claim 1, characterized in that, The real-time monitoring data of the temperature controller is simulated and mapped using the digital twin model. Based on the interactive processing of multi-granularity simulation units, the control deviation characteristics of the current permissible state are identified, including: The collected real-time monitoring data is subjected to change feature extraction to obtain feature information reflecting the trend, magnitude and rate of change of mold temperature, and the influence variables that reach the control analysis threshold based on the feature information are identified. Based on the identified categories of influencing variables, real-time monitoring data and change characteristics are mapped to corresponding multi-granularity simulation units, and simulation processing of the influencing variables is performed to obtain the temperature control effect results of the influencing variables on the mold temperature regulation process. Based on the comparative analysis between the temperature control impact results and the preset temperature control target, it is determined whether the current operating state of the mold temperature controller meets the temperature control target. If the temperature control target is not met, a control deviation feature is generated to characterize the deviation of the current operating state.

8. The adaptive control method for mold temperature controller based on digital twin according to claim 7, characterized in that, Based on the characteristics of the control deviation, the corresponding control compensation target parameters are located, including: Based on the aforementioned regulation deviation characteristics, the influence relationship between the regulation deviation characteristics and each regulation variable is analyzed in a multi-granularity simulation unit. Regulation variables with major causal correlation with the current regulation deviation characteristics are screened to form a set of candidate parameters for regulation compensation. Based on the current operating conditions and control constraints, the effectiveness of the candidate parameter set for control compensation is assessed, and control variables that do not meet safety or stability constraints are eliminated. From the control variables that meet the requirements, determine at least one control compensation target parameter for eliminating or mitigating the control deviation characteristics.

9. The adaptive control method for mold temperature controller based on digital twin according to claim 1, characterized in that, By utilizing the adaptive control mechanism corresponding to the control compensation target parameter matching, and performing quantitative compensation control analysis of the control parameters based on monitoring data, a control strategy is obtained, including: Based on the parameter category and dynamic influence characteristics of the control and compensation target parameters, an adaptive control mechanism is matched to determine the corresponding adaptive control mechanism; Under the adaptive control mechanism, based on real-time collected monitoring data and control constraints, the compensation direction, compensation amplitude and parameter update rate of the control compensation target parameter are quantitatively analyzed to generate parameter adjustment quantitative data as the control strategy. When there are multiple control and compensation target parameters, the control timing analysis and combination of the parameter adjustment quantification data of multiple control and compensation target parameters are performed to obtain the control strategy and perform adaptive control of the mold temperature machine.

10. A mold temperature controller adaptive control system based on digital twin, characterized in that, The system is used to implement the adaptive control method for mold temperature controller based on digital twin as described in any one of claims 1 to 9, and the system comprises: The influencing variable analysis module is used to analyze the influencing variables of the mold temperature controller during the control process, construct multi-granularity simulation units, and embed them into the digital twin model as a built-in adjustment module for operation simulation. The influencing variables include equipment parameters, operating parameters, and working condition parameters. The control mechanism configuration module is used to acquire the control variables and control constraints related to the temperature control of the mold temperature controller, and configure the adaptive control mechanism of the control variables based on the control target and sample data, combined with the control constraints. The adaptive control mechanism includes fixed control, mapping compensation control, and computational control. The target parameter positioning module is used to simulate and map the real-time monitoring data of the mold temperature controller through the digital twin model, identify the control deviation characteristics of the current allowable state based on the interactive processing of multi-granularity simulation units, and locate the corresponding control compensation target parameter based on the control deviation characteristics. The compensation and control analysis module is used to match the corresponding adaptive control mechanism with the control compensation target parameter, perform quantitative compensation and control analysis of the control parameters according to the monitoring data, and obtain the control strategy.

Images