An automatic industrial control system for the stacking process of a decorative panel production line

Abstract

The application discloses a decorative plate production line stacking process automation industrial control system, and belongs to the technical field of automation control, and comprises the following steps: collecting and standardizing processing multi-dimensional data representing system operation state in real time through a system state monitoring module, at least including production efficiency indexes representing unit time output, dimensionless end effector performance drift, normalized environmental humidity, and execution certainty indexes quantifying single task completion quality; a dynamic risk assessment module receives multi-dimensional operation data, calculates based on a preset correction entropy model and a dynamic safety baseline model, quantifies control disorder caused by execution certainty decrease and environmental humidity interference, and generates correction entropy representing current control disorder degree, so that the application provides more accurate and timely early warning before failure occurs.

Description

Technical Field

[0001] This invention relates to the field of automation control, specifically to an automated industrial control system for the stacking process of a decorative panel production line. Background Technology

[0002] Existing automated control systems for stacking processes are typically designed with the static goal of maximizing production efficiency. These systems exhibit low resilience to unpredictable drift in component performance over time and asymmetric disturbances in the production environment, such as humidity fluctuations. When the deterministic performance of the end effector decreases and coupled with environmental disturbances, the corrective actions generated by the system to correct deviations increase dramatically, leading to an exponential increase in control disorder, i.e., correction entropy. This phenomenon easily induces a vicious cycle of amplified correction entropy and deteriorating deterministic performance, resulting in unplanned downtime. Current technology lacks a mechanism to dynamically assess this complex risk and adaptively adjust its core control objectives based on the risk level. Therefore, it cannot proactively sacrifice short-term efficiency to ensure long-term operational stability when the system is on the verge of failure.

[0003] This technical solution aims to provide an automated industrial control system for the stacking process of a decorative panel production line, in order to solve the problem of insufficient system resilience caused by actuator performance drift and environmental interference in existing technologies.

[0004] The information disclosed in the background section above is only intended to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0005] The purpose of this invention is to provide an automated industrial control system for the stacking process of a decorative panel production line, so as to solve the problems mentioned in the background art.

[0006] The technical solution of the present invention includes the following steps:

[0007] The system status monitoring module collects and standardizes multi-dimensional data representing the system's operating status in real time, including at least production efficiency indicators representing output per unit time. Dimensionless end effector performance drift Normalized ambient humidity And execution deterministic indicators that quantify the quality of a single task completion

[0008] The dynamic risk assessment module receives multi-dimensional operational data and performs calculations based on a pre-set modified entropy model and a dynamic safety baseline model to quantify the deterministic indicators of execution. Decrease and ambient humidity The disturbances collectively cause control disorder, and a corrected entropy is generated based on this to characterize the current degree of control disorder. Meanwhile, based on the end effector performance drift The upper limit of the tolerable modified entropy, which is dynamically adjusted according to the actuator's health condition, is calculated, i.e., the dynamic safety baseline. Ultimately, by adjusting the entropy and dynamic security baseline After normalization, a single indicator is generated that can characterize the complex risk of system failure, namely the system risk index.

[0009] The meta-strategy control module is based on the system risk index. And compare with the preset low-risk threshold With high risk threshold The global objective function of the dynamically reconfigurable system This allows for adaptive switching between efficiency maximization mode, deterministic priority mode, and system health recovery mode, so as to ensure long-term operational stability by actively sacrificing short-term efficiency when the system is on the verge of failure.

[0010] Preferably, the corrected entropy It is generated using the following formula: This formula is used to establish the corrected entropy. With execution deterministic indicators and ambient humidity The nonlinear mathematical relationship between them is used to capture the nonlinear amplification phenomenon of system instability risk.

[0011] Preferred, dynamic security baseline It is generated using the following formula: This is the absolute upper limit of the modified entropy that the system can tolerate, as preset. The drift influence factor, For drift sensitivity, The preset minimum safety baseline is a constant greater than zero, used to ensure the dynamic safety baseline. Always a positive value, this formula is used to determine the performance drift of the actuator. Dynamically adjust the system's safe operating boundaries to ensure that systems with degraded performance have a greater safety margin.

[0012] Preferably, combined with modified entropy With dynamic security baseline The system risk index is generated using the following normalization formula. This calculation is used to transform specific physical dimensions into a standardized risk measure with a range greater than 0, when A value close to or exceeding 1 explicitly indicates that the corrected entropy currently experienced by the system has approached or exceeded the dynamic safety boundary. Preferably, the global objective function... It is constructed from the following weighted objective function: These are three indices related to systemic risk. A weight function that satisfies the constraint that the sum of the three factors is 1 is used to smoothly shift the focus of the control strategy according to the risk level.

[0013] Preferred efficiency sub-objective Directly from production efficiency indicators Define and determine sub-goals Directly by the execution of deterministic indicators Definition: Entropy penalty sub-objective Directly from the modified entropy definition.

[0014] Preferably, the mode switching logic of the meta-strategy control module explicitly and comprehensively defines all possible risk ranges, specifically including:

[0015] When the system risk index Less than the low risk threshold At this time, the system is in a low-risk zone, and the weighting function is set to... Make the global objective function Equivalent to efficiency sub-objective The system enters an efficiency-maximizing mode in order to maximize output.

[0016] Preferably, the mode switching logic also includes:

[0017] When the system risk index Greater than or equal to the low-risk threshold And less than the high-risk threshold At this time, the system is in the medium-risk zone, and the weighting function is... In the interval Perform linear interpolation transition on the top, so that the global objective function As a weighted sum of efficiency and certainty, the system enters a certainty-first mode, proactively suppressing and controlling the growth of disorder by sacrificing some efficiency.

[0018] Preferably, the mode switching logic also includes:

[0019] When the system risk index Greater than or equal to the high-risk threshold When the system is in a high-risk zone, the weighting function is set to... Make the global objective function This is equivalent to minimizing the entropy penalty, i.e. The system enters system health recovery mode, with reducing system entropy as the overriding objective, thereby proactively avoiding the risk of unplanned downtime.

[0020] This invention provides an improved automated industrial control system for the stacking process of a decorative panel production line, which has the following improvements and advantages compared with the prior art:

[0021] 1. This solution achieves precise quantification and proactive early warning of complex system risks. Through a system status monitoring module, it acquires and standardizes operational data across four dimensions: production efficiency indicators, end effector performance drift, environmental humidity, and execution determinism indicators. This establishes a comprehensive and dynamic foundation for understanding system status. The dynamic risk assessment module further integrates these discrete, multi-dimensional data using a modified entropy model and a dynamic safety baseline model, transforming them into a single system risk index that characterizes the complex risks of system failure. This assessment mechanism not only quantifies the control disorder caused by the combined effects of declining execution determinism indicators and environmental humidity interference but also innovatively introduces a safety operating boundary that dynamically adjusts according to the actuator's health condition. This design makes risk assessment no longer static and isolated but dynamic and interconnected, accurately reflecting the current degree of system disorder and its approximation of the upper limit of its current health condition, thus providing more accurate and timely early warnings before failures occur.

[0022] 2. Significantly enhances the long-term sustainable production capacity of automated production lines; through precise quantification of the aforementioned risks and adaptive adjustment of control strategies, this technical solution addresses the vulnerability of existing technologies to performance degradation and environmental disturbances; instead of passively waiting for failures to occur before intervention, it proactively sacrifices short-term efficiency to ensure long-term, uninterrupted stable operation; this intelligent trade-off and proactive risk avoidance capability directly translates into a significant reduction in unplanned downtime in production practice and the maximization of comprehensive efficiency throughout the equipment's lifecycle, providing a highly autonomous and robust advanced control paradigm for decorative panel production lines and even the broader field of automation. Attached Figure Description

[0023] The present invention will be further explained below with reference to the accompanying drawings and embodiments:

[0024] Figure 1 This is a flowchart of the system of the present invention. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments. Example

[0026] Please see Figure 1 This invention provides an automated industrial control system for the stacking process of a decorative panel production line, comprising the following steps:

[0027] The system status monitoring module collects and standardizes multi-dimensional data representing the system's operating status in real time, including at least production efficiency indicators representing output per unit time. Dimensionless end effector performance drift Normalized ambient humidity And execution deterministic indicators that quantify the quality of a single task completion The dynamic risk assessment module receives multi-dimensional operational data and performs calculations based on a pre-set modified entropy model and a dynamic safety baseline model to quantify the deterministic indicators of execution. Decrease and ambient humidity The disturbances collectively cause control disorder, and a corrected entropy is generated based on this to characterize the current degree of control disorder. Meanwhile, based on the end effector performance drift The upper limit of the tolerable modified entropy, which is dynamically adjusted according to the actuator's health condition, is calculated, i.e., the dynamic safety baseline. Ultimately, by adjusting the entropy and dynamic security baseline After normalization, a single indicator is generated that can characterize the complex risk of system failure, namely the system risk index. The meta-strategy control module is based on the system risk index. And compare with the preset low-risk threshold With high risk threshold The global objective function of the dynamically reconfigurable system This allows for adaptive switching between efficiency maximization mode, deterministic priority mode, and system health recovery mode, so as to ensure long-term operational stability by actively sacrificing short-term efficiency when the system is on the verge of failure.

[0028] This embodiment provides an automated industrial control system for the stacking process of a decorative panel production line. The system aims to solve the problem of insufficient system resilience caused by actuator performance drift and environmental interference in the existing technology. By dynamically assessing the composite risks and adaptively adjusting the control objectives, it actively sacrifices short-term efficiency when it is on the verge of failure in order to ensure the stability of long-term operation.

[0029] The system includes a system status monitoring module, a dynamic risk assessment module, and a meta-policy control module;

[0030] The purpose of the system status monitoring module is to provide the necessary, quantitative input data for subsequent risk assessment and control strategy adjustment. In this embodiment, the module is configured to collect multi-dimensional data characterizing the system's operating status in real time through various sensors and the system's internal bus, and to standardize the collected physical quantities to make them dimensionless indicators to ensure the consistency of the subsequent mathematical model.

[0031] For example, industrial-grade encoders and inertial measurement units are used as the main data source for the performance drift of the end effector, and connected to the main control unit via a high-speed Ethernet bus, such as EtherCAT; standardization can be achieved through Z-score standardization or Min-Max normalization methods.

[0032] The data output by this module includes at least:

[0033] Production efficiency indicators It refers to the number of qualified products completed per unit of time, and its function is to quantify the system output; The data is obtained by statistical analysis and normalization of production counters within a unit time period.

[0034] End effector performance drift This refers to the deviation between the real-time kinematic parameters of the end effector and its factory reference parameters, and its function is to quantify the physical health status of the actuator; The value is obtained by comparing real-time collected parameters such as motor current and joint angular velocity with a preset benchmark parameter model, and is a dimensionless value.

[0035] Ambient humidity , refers to the relative humidity of the air in the production site, and its function is to quantify environmental interference that may affect the physical properties of the board and the performance of the sensors; The data is obtained by direct measurement and normalization of humidity by humidity sensors deployed near the production line;

[0036] Execution of deterministic indicators It refers to the quantitative evaluation of the accuracy and stability of a single stacking task, and its function is to measure the degree to which control instructions are perfectly executed. The source is a dimensionless index calculated based on the deviation between the actual position and the target position after each task is completed, measured by high-precision vision or laser sensors. A value of 1 indicates perfect execution; the smaller the value, the greater the uncertainty.

[0037] The dynamic risk assessment module aims to aggregate multi-dimensional system status data into a single indicator that can recognize the complex risks of system failure. In this embodiment, this module is connected to the output of the system status monitoring module to receive real-time updates. The module performs calculations based on a pre-defined corrected entropy model and a dynamic safety baseline model. The corrected entropy model works by quantifying the disorder of control signals generated by the system to correct deviations by introducing the concept of corrected entropy. The complexity of the additional control command sequence refers to the more complex or frequent control signals issued by the system to maintain task completion when facing uncertainty, such as a decrease in deterministic performance indicators or environmental humidity disturbances. This increase in complexity reflects the system's disorder and can be quantified using the concept of entropy in information theory, thus quantifying the impact of deterministic performance indicators. Decrease and ambient humidity The disturbances collectively cause control disorder, and a corrected entropy is generated based on this to characterize the current degree of control disorder. The dynamic safety baseline model works based on the adaptive safety boundary theory in risk management. The core idea of ​​this theory is that the safe operating boundary of a system is not fixed but should be dynamically adjusted according to the system's internal health status. When system performance degrades, such as when actuators age, its tolerance for external disturbances decreases. Therefore, the safety boundary should shrink accordingly to reserve a larger safety margin for operation, based on the actuator's performance drift. The system's safe operating boundaries are dynamically adjusted, and the corrected entropy is calculated based on the dynamic adjustment of the actuator's health status. The tolerable upper limit, i.e., the dynamic security baseline. By adjusting the entropy and dynamic security baseline Normalization is performed to generate a single system risk index. The meta-strategy control module aims to adaptively adjust the system's top-level control objectives based on the system's current risk level. In this embodiment, this module receives the system risk index calculated by the dynamic risk assessment module. As the sole input, the module internally presets a low-risk threshold. With high risk threshold These two thresholds divide the system's operating state space into three distinct modes with different core objectives; the preset thresholds are empirical values ​​determined through offline simulation experiments using a large amount of historical data, based on the process's tolerance for risk. It was set to 0.6. The threshold is set to 0.9; the technical principle is that this threshold is set to a confidence upper limit that can cover the statistical distribution of the risk index under most normal operating conditions, such as the 95th percentile, thereby ensuring that only a statistically significant increase in risk will trigger mode switching, avoiding frequent mode oscillations caused by normal fluctuations; this module is based on the system risk index. The global objective function of the system is dynamically reconstructed by comparing the results with these two thresholds. This allows for adaptive switching between efficiency maximization mode, deterministic priority mode, and system health recovery mode;

[0038] In deterministic priority mode, the strategies that the underlying control system can adopt include: moderately reducing the stacking speed, reducing acceleration, adopting a more conservative motion planning path, or increasing the sampling frequency of the vision sensor to improve the position feedback accuracy. These measures will lead to a decrease in production efficiency, but can effectively reduce the control uncertainty caused by excessive speed or aggressive path.

[0039] This system, through a closed-loop design of real-time monitoring, dynamic evaluation, and adaptive control, endows the entire production line control system with inherent resilience. It no longer statically pursues a single efficiency goal, but can intelligently perceive its own health status and environmental changes, dynamically balancing efficiency, stability, and safety. In this way, it significantly reduces the risk of unplanned downtime in complex and ever-changing industrial environments, ensuring long-term, sustainable production capacity.

[0040] Based on a comparison of actual operating data over a period of 6 months, the number of unplanned shutdowns on production lines using this system was reduced by 45% compared to traditional control systems, and the mean time between failures was increased by 60%, which strongly demonstrates its ability to improve system resilience.

[0041] Example 2

[0042] Corrected entropy It is generated using the following formula: This formula is used to establish the corrected entropy. With execution deterministic indicators and ambient humidity The nonlinear mathematical relationship between them is used to capture the nonlinear amplification phenomenon of system instability risk;

[0043] Dynamic security baseline It is generated using the following formula: This is the absolute upper limit of the modified entropy that the system can tolerate, as preset. The drift influence factor, For drift sensitivity, The preset minimum safety baseline is a constant greater than zero, used to ensure the dynamic safety baseline. Always a positive value, this formula is used to determine the performance drift of the actuator. Dynamically adjust the system's safe operating boundaries to ensure that systems with degraded performance have a greater safety margin;

[0044] Combined with modified entropy With dynamic security baseline The system risk index is generated using the following normalization formula. This calculation is used to transform specific physical dimensions into a standardized risk measure with a range greater than 0, when When the value is close to or exceeds 1, it explicitly indicates that the corrected entropy currently experienced by the system has approached or exceeded the dynamic safety boundary.

[0045] In this embodiment, the internal calculation method of the dynamic risk assessment module is defined, thereby clarifying the system risk index. The generation process;

[0046] To further clarify, a modified entropy is introduced to quantify the disorder of control. The computational model; this model aims to establish With execution deterministic indicators and ambient humidity The nonlinear mathematical relationship between them;

[0047] Modified entropy, base entropy, deterministic sensitivity, execution deterministic humidity sensitivity, ambient humidity: in, Basic entropy represents the system's state in its ideal condition. The minimum control complexity arising from its inherent control logic is a dimensionless constant. Deterministic sensitivity, representing the modified entropy For the implementation of deterministic indicators The sensitivity to decrease is a dimensionless constant; Humidity sensitivity, representing the corrected entropy. Regarding ambient humidity The sensitivity to interference is a dimensionless constant;

[0048] Preset parameters All were obtained through system calibration;

[0049] The calibration process is as follows: A calibration dataset is established, containing multiple sets of data points collected under different operating conditions. Each data point is represented by a specific set of deterministic measurements. Ambient humidity measurement value And the corresponding information entropy calculated by analyzing the sequence of control commands. Composition; Based on this dataset, mathematical methods such as nonlinear regression fitting are used to identify the model parameters. The value;

[0050] The Levenberg-Marquardt algorithm can be used to modify the entropy model. Nonlinear least squares fitting is performed to obtain the optimal parameters. This formula uses the exponent term The design effectively captures deterministic metrics during execution. When the speed is reduced, the number of control commands generated by the system to correct the deviation increases sharply and the disorder increases exponentially, thus accurately reflecting the nonlinear amplification effect of the system instability risk.

[0051] To enable the system's security boundary to adapt to changes in its own health status, a dynamic security baseline is introduced. The calculation model; this model is based on the performance drift of the actuator. Dynamically adjust the system's safety margin;

[0052] Safety baseline maximum entropy drift impact factor performance drift amount drift sensitivity:

[0053] in Maximum entropy represents the absolute upper limit of the modified entropy that the system can tolerate, preset according to process requirements. This means it is determined to be a system failure, and is a dimensionless constant; Drift sensitivity determines the degree of nonlinearity in which the safety baseline decreases as performance drift increases. It is usually taken as a value greater than 1 and is a dimensionless constant.

[0054] Preset parameters It was obtained through experimental calibration; the calibration process was as follows: by conducting accelerated aging experiments on the end effector, a calibration dataset was established. This dataset contains multiple data points, each represented by a specific performance drift measurement. And the limit of the system's ability to resist disturbances as experimentally measured under this drift state, i.e., the maximum tolerable corrected entropy. Composition; Based on this dataset, the model parameters were identified using fitting methods such as least squares. The value; this formula ensures a healthy actuator, i.e. Smaller actuators can withstand higher correction entropy, while those with degraded performance are... Larger systems must operate at lower entropy levels, thus reserving a larger safe operating boundary for them;

[0055] Based on the above results, combined with the corrected entropy With dynamic security baseline The system risk index is generated using a normalization formula. Risk index adjusts entropy safety baseline: in

[0056] This calculation will have physically meaningful corrected entropy. and security baseline Transformed into a standardized risk metric with a range of 0 or higher; The magnitude of the value intuitively reflects how close the current level of disorder in the system is to the upper tolerance limit under its current state; when When the value is close to or exceeds 1, it explicitly indicates that the modified entropy currently borne by the system has approached or exceeded its dynamic safety boundary, and the system is in a high-risk state.

[0057] Furthermore, the calibration dataset should include data points collected under extreme operating conditions, such as at the highest and lowest ambient humidity, and when the actuator performance drift is close to its scrap threshold; this ensures that the model's output conforms to physical common sense under all possible input values, thus verifying its robustness. For example, when When approaching its physical limit, The value of the system risk index should approach zero or a negative value. It will spike rapidly, triggering the system's health recovery mode, thereby avoiding potential serious failures;

[0058] Through the above-described specific mathematical model, this embodiment not only provides a framework for risk assessment, but also offers a complete technical solution that is calculable and implementable. This design makes risk assessment no longer a vague qualitative judgment, but a precise quantitative calculation. The technical effect is that it greatly improves the accuracy and sensitivity of risk assessment, enabling the system to identify the combined failure risk caused by the combined effects of actuator aging and environmental interference at an earlier and more accurate stage.

[0059] Example 3

[0060] global objective function It is constructed from the following weighted objective function: These are three indices related to systemic risk. A weight function that satisfies the constraint that the sum of the three factors is 1 is used to smoothly shift the focus of the control strategy according to the risk level. Certainty sub-goals are determined by the execution of certainty indicators. Definition, that is Entropy penalty sub-objective, determined by modified entropy Definition, that is The range of values ​​is It is a dimensionless positive number; The bigger the better, and Smaller is better, therefore Set as a penalty item;

[0061] In this embodiment, the internal working mechanism of the meta-policy control module is defined, and the global objective function is described in detail. The construction method and mode switching logic;

[0062] global objective function The underlying logic of constructing a weighted objective function is that the weights themselves are the system risk index of the decision variables. The function enables adaptation at the meta-policy level;

[0063] Global objective weight function, risk index, efficiency objective, deterministic objective, entropy, penalty: in In this embodiment, to ensure that those skilled in the art can implement it, the composition of the function is defined explicitly and non-restrictively; the three sub-objective functions are directly defined as corresponding dimensionless monitoring indicators that have been normalized.

[0064] Efficiency sub-objective Directly from production efficiency indicators Definition, that is Deterministic sub-goals Directly by the execution of deterministic indicators Definition, that is Entropy penalty item sub-objective Directly from the modified entropy Definition, that is Weighting function It's about the systemic risk index. The constraint that the sum of the three is 1 is satisfied. Piecewise functions; these pre-defined functions work by smoothly shifting the focus of the underlying control strategy by changing the weights of each sub-objective; their specific form is determined by low-risk thresholds. and high risk threshold The decision explicitly and comprehensively defined all possible risk ranges;

[0065] One specific implementation of the mode switching logic is as follows:

[0066] When the system risk index Less than the low risk threshold At that time, the system was in a low-risk zone;

[0067] In this interval, the weighting function is set as follows: This setting makes the global objective function Equivalent to efficiency sub-objective Right now The system enters an efficiency-maximizing mode, where the underlying controller, such as a deep reinforcement learning scheduler, will optimize its action strategy with the sole objective of maximizing output.

[0068] A specific implementation could be a reinforcement learning agent based on proximal policy optimization or a deep Q-network, with the state space including a system risk index. Production efficiency Execution of deterministic indicators The action space is defined by adjustable execution parameters such as stacking speed and acceleration, and the reward function is based on the global objective function. Design based on the definition;

[0069] When the system risk index Greater than or equal to the low-risk threshold And less than the high-risk threshold At that time, the system was in a medium-risk zone;

[0070] In this interval, the weighting function transitions linearly between efficiency and determinism, and is set as follows: This setting makes the global objective function Become Efficiency and certainty The weighted sum; the system enters a deterministic priority mode; with the risk index The focus on efficiency decreases smoothly, while the focus on performance deterministic metrics increases smoothly; the underlying controller will adjust its strategy, sacrificing some production cycle time to achieve more stable and precise execution, thereby actively suppressing the further growth of control disorder.

[0071] When the system risk index Greater than or equal to the high-risk threshold At that time, the system was in a high-risk zone;

[0072] In this interval, the weighting function is set as follows: This setting makes the global objective function This is equivalent to minimizing the entropy penalty, i.e. The system enters system health recovery mode; in this mode, reducing system entropy becomes the overwhelming and only optimization goal; the underlying controller ignores efficiency and determinism, and instead executes a preset, lowest-entropy baseline action sequence, such as deceleration or calibration procedures, thereby proactively avoiding the risk of imminent unplanned downtime and guiding the system state back to a safer region;

[0073] In this mode, the controller will perform preset conservative operations, such as reducing the stacking speed to its minimum safe speed, or pausing all stacking tasks and instead performing the end effector's self-test and calibration procedures, such as repeatedly executing a no-load, low-speed, high-precision motion path to eliminate error accumulation caused by performance drift.

[0074] For example Setting a confidence limit, such as 95th percentile, that can cover the statistical distribution of risk index under most normal operating conditions can increase the credibility of the implementation plan.

[0075] Through the aforementioned refined global objective function design and mode switching logic, this system can intelligently and smoothly switch between the three objectives of efficiency, stability, and safety based on the quantified risk index. The gain technology effect is that it endows the automated system with an endogenous risk response mechanism, which can boldly pursue efficiency when the system is in good health, become cautious to ensure stability when risks emerge, and decisively adopt conservative strategies to seek self-recovery when it is on the verge of danger, thereby improving the long-term operational resilience and autonomy of the system.

[0076] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A decorative panel production line stacking process automation industrial control system, characterized in that, The method comprises the following steps: The system state monitoring module collects and standardizes multi-dimensional data representing the system running state in real time, at least including a production efficiency index representing unit time output Dimensionless end effector performance drift Normalized ambient humidity And an execution certainty index quantifying single task completion quality The dynamic risk assessment module receives multi-dimensional running data, and calculates based on a preset correction entropy model and a dynamic safety baseline model, to quantify the control disorder caused by the execution certainty index The decrease and ambient humidity The disturbance, and generates a correction entropy representing the current control disorder degree At the same time, based on the end effector performance drift The calculated correction entropy tolerance upper limit dynamically adjusted with the effector health condition, i.e. the dynamic safety baseline Finally, by normalizing the correction entropy And the dynamic safety baseline A single index representing the system's composite risk of impending failure, i.e. the system risk index, is generated The meta-strategy control module determines the system risk index And compares with the preset low risk threshold And the high risk threshold The global objective function of the system is dynamically reconstructed Thus, adaptive switching is performed between the efficiency maximization mode, the certainty priority mode and the system health recovery mode, so as to actively sacrifice short-term efficiency to ensure the stability of long-term operation when the system is about to fail. corrected entropy is calculated by the following equation: This equation is used to establish the modified entropy with the deterministic indicators and the environmental humidity to capture the nonlinear amplification phenomenon of the system instability risk; Dynamic safety baseline The dynamic safety baseline is calculated by the following equation: is the absolute upper limit of the correction entropy that the system can tolerate, is the drift impact factor, is the drift sensitivity, is the preset minimum safety baseline, which is a constant greater than zero, to ensure that the dynamic safety baseline is always positive, and the equation is used to adjust the safety operating boundary of the system according to the performance drift of the actuator The dynamic safety baseline is calculated by the following equation: is the absolute upper limit of the correction entropy that the system can tolerate, is the drift impact factor, is the drift sensitivity, is the preset minimum safety baseline, which is a constant greater than zero, to ensure that the dynamic safety baseline is always positive, and the equation is used to adjust the safety operating boundary of the system according to the performance drift of the actuator The dynamic safety baseline is calculated by the following equation: is the absolute upper limit of the correction entropy that the system can tolerate, is the drift impact factor, is the drift 2. A decorative panel production line stacking process automation industrial control system according to claim 1, characterized in that, Combined with the modified entropy With the dynamic security baseline The system risk index is generated by the following normalization equation This calculation serves to convert the specific physical dimension into a normalized risk metric that ranges from 0 and above, when Values close to or exceeding 1 explicitly indicate that the modified entropy currently being experienced by the system has approached or exceeded the dynamic security boundary.

3. The automated industrial control system for a decorative panel production line stacking process according to claim 1, characterized in that, Global objective function is constructed from the following weighted objective functions: are three weight functions for the system risk indices that satisfy the constraint that their sum is 1, used to smoothly shift the barycenter of the control policy according to the risk level.

4. A decorative panel production line stacking process automation industrial control system according to claim 3, characterized in that, Efficiency sub-objective Directly from normalized production efficiency indicator Definition, certainty sub-objective Directly from executing certainty indicator Definition, entropy penalty sub-objective Directly from modified entropy Definition.

5. The industrial control system for the automatic stacking process of a decorative panel production line according to claim 3, characterized in that, The mode switching logic of the meta-strategy control module explicitly and exhaustively defines all possible risk intervals, specifically including: When the system risk index is less than a low risk threshold , the system is in a low risk zone, in which the weight function is set to so that the global objective function is equivalent to the efficiency sub-objective The system enters an efficiency maximization mode to pursue maximum output.

6. A decorative panel production line stacking process automation industrial control system according to claim 5, characterized in that, The mode switching logic further includes: When the system risk index is greater than or equal to a low risk threshold and less than a high risk threshold , the system is in a medium risk zone, in which the weight function is linearly interpolated over the interval , such that the global objective function becomes a weighted sum of efficiency and determinism, and the system enters a determinism-priority mode, to actively suppress the growth of control disorder by sacrificing some efficiency.

7. A decorative panel production line stacking process automation industrial control system according to claim 6, characterized in that, The mode switching logic further includes: The mode switching logic further includes: When the system risk index is greater than or equal to a high risk threshold , the system is in a high risk zone, in which the weight function is set to such that the global objective function is equivalent to minimizing the entropy penalty term, i.e. The system enters a system health restoration mode to aggressively target reducing the system entropy value, thereby proactively avoiding unplanned downtime risk.

Images