A method for modular optimization of an industrial production process

Abstract

The application provides an industrial production process modularization optimization method, and belongs to the technical field of electric digital data processing.The application firstly constructs a real-time requirement matrix to perform real-time classification on a module;deploys a time-sensitive network architecture to ensure that the transmission delay of a key signal is controllable;introduces an edge computing node to reduce data transmission delay;constructs a low-delay communication network based on industrial 5G technology;implements real-time deviation fluctuation matrix monitoring to capture delay anomalies;applies a real-time adjustment gain matrix to realize adaptive control compensation;establishes a time-deterministic task scheduler to optimize task execution;implements a cross-module synchronous clock mechanism to eliminate time synchronization errors;and constructs a modular real-time optimization engine to realize system self-tuning, thereby solving the problem of real-time control failure caused by communication delay and scheduling uncertainty in modular industrial production.

Description

Technical Field

[0001] This invention belongs to the field of electronic digital data processing technology, and more specifically, relates to a modular optimization method for industrial production processes. Background Technology

[0002] Modularization of industrial production processes is an important development direction for modern intelligent manufacturing. Traditional modular process systems mainly rely on standard industrial communication protocols such as Modbus, PROFINET, and EtherCAT to achieve communication and integration between modules, and coordinate the operation of each module through a central control system. These technologies are widely used in conventional production environments, can meet basic automation needs, and support process parameter monitoring and control.

[0003] However, with the increasing sophistication of industrial production, traditional modular process systems face serious challenges. First, traditional industrial communication protocols suffer from uncertain delays under high loads, causing critical control commands to fail to reach the execution units in a timely manner. Second, centralized computing architectures result in excessively long data transmission paths, increasing processing latency. Third, fixed-gain control strategies cannot dynamically compensate for the impact of latency fluctuations, reducing the accuracy of process parameter control. Finally, insufficient clock synchronization accuracy between modules causes coordination errors in distributed control systems.

[0004] These problems are particularly prominent in industrial scenarios requiring high precision and dynamic response, such as precision chemicals, semiconductor manufacturing, and aerospace component processing. Communication delays and scheduling uncertainties between modules can lead to real-time control failures of critical process parameters, resulting in product quality fluctuations, decreased production efficiency, and even safety accidents. Therefore, there is an urgent need for a modular process optimization method that can effectively solve the problem of real-time control failures. Summary of the Invention

[0005] In view of this, the present invention provides a modular optimization method for industrial production processes, which can solve the technical problem of real-time control failure caused by communication delay and scheduling uncertainty in existing modular industrial production process systems.

[0006] This invention is implemented as follows: It provides a modular optimization method for industrial production processes, including constructing a real-time requirement matrix, classifying each module of the industrial production process into real-time levels, and assigning higher priority to modules with high real-time requirements; deploying a time-sensitive network architecture and implementing deterministic Ethernet technology on the inter-module communication channels; introducing edge computing nodes to allocate real-time deviation matrix calculation tasks to edge servers close to the production site; constructing a low-latency communication network based on industrial 5G technology; implementing real-time deviation fluctuation matrix monitoring; applying a real-time adjustment gain matrix to adaptively compensate process parameter control commands based on control compensation mechanism equations; establishing a time-deterministic task scheduler; implementing a cross-module synchronization clock mechanism; and constructing a modular real-time optimization engine to continuously optimize the real-time adjustment gain matrix parameters through an adaptive feedback optimization function.

[0007] The real-time requirement matrix refers to quantifying the response time requirements of each process module in industrial production into a matrix form, including module identifiers and corresponding maximum allowable response times, which is used for system resource allocation and task priority ranking.

[0008] The real-time deviation matrix refers to the matrix formed by calculating the difference between the actual response time and the theoretical value in the real-time requirement matrix by monitoring the communication and control execution time of each module in real time. It is used to evaluate the real-time performance of the system.

[0009] Among them, the real-time deviation fluctuation matrix refers to a multi-dimensional data structure that records the trend of real-time deviation changes within a certain time window. By statistically analyzing the rate of deviation change and the fluctuation amplitude, the trend of system performance degradation can be predicted.

[0010] Among them, the real-time adjustment gain matrix refers to the adaptive compensation parameter matrix set for each control loop based on the real-time deviation and its fluctuation, which is used to dynamically adjust the control commands to compensate for the impact of communication delay.

[0011] Among them, the control compensation mechanism equation refers to the mathematical expression for calculating the optimal compensation amount based on the communication delay time, the rate of change of process parameters, the system sensitivity coefficient, the response time constant, and the process state variables, and outputs the real-time compensation amount of the control command to ensure that the process parameter control can still be kept within the target range even when communication delay exists.

[0012] The adaptive feedback optimization function is a mathematical function that dynamically adjusts the weights of each parameter in the real-time adjustment gain matrix based on historical error accumulation, current performance indicators, system feedback speed, time weighting factor, and disturbance resistance coefficient, and outputs the optimized gain matrix parameter set.

[0013] The communication delay time refers to the time required for instructions or data to be transmitted from the source module to the target module in the industrial control network, which is obtained by monitoring the time-sensitive network architecture; the process parameter change rate refers to the speed at which key process parameters change over time in the industrial production process, which is calculated from the process parameter sequence collected by the real-time data bus.

[0014] Among them, the system sensitivity coefficient refers to the degree of response of process parameters to changes in control commands, which is obtained by analyzing the response curve of process parameters through edge computing nodes; the response time constant refers to the characteristic time required for the process system to reach a steady state in response to the control signal, which is provided by the real-time requirement matrix.

[0015] Among them, process state variables refer to the set of key parameters describing the current process state, which are collected from each process module through a low-latency communication network; historical error accumulation value refers to the weighted accumulation of system control errors over a period of time, which is calculated from the real-time deviation fluctuation matrix.

[0016] This invention establishes a complete real-time control and assurance system through a series of innovative technologies, including constructing a real-time requirement matrix, deploying a time-sensitive network architecture, and introducing edge computing nodes. This method enables precise quantification of the real-time requirements of process modules and allocates network and computing resources accordingly, ensuring that modules with high real-time requirements receive priority processing.

[0017] By implementing this invention, industrial production systems can effectively reduce the uncertainty of communication delays between modules, controlling the transmission delay of critical signals within a preset threshold. The real-time deviation fluctuation matrix monitoring mechanism can promptly capture delay fluctuations, triggering adaptive compensation based on the control compensation mechanism equation, thus reducing the negative impact of delays on process control accuracy. Simultaneously, the time-deterministic task scheduler and the cross-module synchronization clock mechanism jointly ensure the coordination and determinism of distributed control.

[0018] Based on the above technical means, the present invention successfully solves the technical problem of real-time control failure caused by communication delay and scheduling uncertainty in modular industrial production processes. It enables the system to achieve reliable real-time control of highly dynamic and high-precision process parameters while maintaining the flexibility of the modular architecture, providing a practical technical solution for modern high-end manufacturing. Attached Figure Description

[0019] Figure 1 This is a flowchart of the method of the present invention.

[0020] Figure 2 This is a diagram analyzing the real-time requirements of the modules in Example 2.

[0021] Figure 3 This is a graph showing the real-time performance deviation fluctuation of the communication link in Example 2.

[0022] Figure 4 This is a comparison of the gain matrix before and after optimization in Example 2. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings.

[0024] like Figure 1 The diagram shown is a flowchart of a modular optimization method for industrial production processes provided by this invention. This method includes the following steps:

[0025] S01. Construct a real-time requirement matrix to classify the real-time requirements of each module in the industrial production process and assign higher priority to modules with high real-time requirements.

[0026] S02. Deploy a time-sensitive network architecture and implement deterministic Ethernet technology on the inter-module communication channel to ensure that the transmission delay of critical signals does not exceed a preset threshold.

[0027] S03. Introduce edge computing nodes to allocate real-time deviation matrix calculation tasks to edge servers closer to the production site to reduce data transmission latency;

[0028] S04. Construct a low-latency communication network based on industrial 5G technology to establish a unified real-time data bus for communication between all modules;

[0029] S05. Implement real-time deviation fluctuation matrix monitoring to capture communication delay fluctuations between modules and trigger a compensation mechanism when the delay exceeds the threshold.

[0030] S06. Apply real-time adjustment of the gain matrix and adaptively compensate the process parameter control commands based on the control compensation mechanism equation to reduce the impact of communication delay on process control accuracy.

[0031] S07. Establish a time-deterministic task scheduler, construct modular process control tasks into a directed acyclic graph structure, and allocate deterministic time slots for critical process control processes based on the minimum delay critical path algorithm.

[0032] S08. Implement a cross-module synchronization clock mechanism to ensure that all modules share a unified time reference based on a precise time protocol, thereby eliminating time synchronization errors.

[0033] S09. Construct a modular real-time optimization engine, and continuously optimize the gain matrix parameters through an adaptive feedback optimization function to achieve system self-tuning.

[0034] The real-time requirement matrix refers to quantifying the response time requirements of each process module in industrial production into a matrix form, including module identifiers and corresponding maximum allowable response times, which is used for system resource allocation and task priority ranking.

[0035] The real-time deviation matrix refers to the matrix formed by calculating the difference between the actual response time and the theoretical value in the real-time requirement matrix by monitoring the communication and control execution time of each module in real time. It is used to evaluate the real-time performance of the system.

[0036] Among them, the real-time deviation fluctuation matrix refers to a multi-dimensional data structure that records the trend of real-time deviation changes within a certain time window. By statistically analyzing the rate of deviation change and the fluctuation amplitude, the trend of system performance degradation can be predicted.

[0037] Among them, the real-time adjustment gain matrix refers to the adaptive compensation parameter matrix set for each control loop based on the real-time deviation and its fluctuation, which is used to dynamically adjust the control commands to compensate for the impact of communication delay.

[0038] Among them, Time-Sensitive Networking (TSN) architecture refers to a deterministic network technology architecture that follows the IEEE 802.1TSN standard family. It ensures the determinism and low latency of critical data stream transmission through mechanisms such as time synchronization, traffic shaping, and frame preemption.

[0039] Among them, deterministic Ethernet technology refers to a set of technologies that achieve deterministic transmission delay on the basis of standard Ethernet, including time-aware schedulers, bandwidth reservation mechanisms, and traffic priority management functions.

[0040] Edge computing nodes refer to computing devices deployed close to the data source, responsible for performing latency-sensitive real-time computing tasks, avoiding additional latency caused by data transmission to remote servers.

[0041] Among them, industrial 5G technology refers to the fifth-generation mobile communication technology optimized for industrial application scenarios, which has ultra-reliable low-latency communication capabilities and supports millisecond-level end-to-end communication latency.

[0042] Among them, the Precision Time Protocol refers to the high-precision time synchronization protocol defined by the IEEE 1588 standard, which can achieve nanosecond-level clock synchronization accuracy between network devices.

[0043] The control compensation mechanism equation refers to the mathematical expression for calculating the optimal compensation amount based on communication delay time, process parameter change rate, system sensitivity coefficient, response time constant, and process state variables. It outputs the real-time compensation amount of the control command, ensuring that process parameter control remains within the target range even with communication delay. Specifically, communication delay time refers to the time required for commands or data to be transmitted from the source module to the target module in the industrial control network, obtained through monitoring by a time-sensitive network architecture; process parameter change rate refers to the speed at which key process parameters change over time during industrial production, calculated from the process parameter sequence acquired by the real-time data bus; system sensitivity coefficient refers to the degree of response of process parameters to changes in control commands, obtained by analyzing the process parameter response curve through edge computing nodes; response time constant refers to the characteristic time required for the process system to reach a steady state in response to the control signal, provided by the real-time requirement matrix; and process state variables refer to the set of key parameters describing the current process state, acquired from each process module through a low-latency communication network.

[0044] Among them, the directed acyclic graph structure refers to the mathematical structure that decomposes the process control task into nodes and directed edges, where nodes represent control tasks and directed edges represent dependencies between tasks.

[0045] Among them, the minimum delay critical path algorithm refers to the algorithm that finds the longest path from the source node to the target node in a directed acyclic graph to ensure that critical control tasks are given priority scheduling.

[0046] Among them, the deterministic time slot refers to the fixed time interval pre-allocated in the time deterministic task scheduler, which is used to ensure that the execution of critical tasks is not interfered with by other tasks.

[0047] Among them, the adaptive feedback optimization function refers to a mathematical function that dynamically adjusts the weights of each parameter in the real-time adjustment gain matrix based on the historical cumulative error value, current performance index, system feedback speed, time weighting factor, and disturbance resistance coefficient, and outputs the optimized gain matrix parameter set; the historical cumulative error value refers to the weighted accumulation of system control errors over a period of time, calculated from the real-time deviation fluctuation matrix; the current performance index refers to the performance evaluation value of the process control system at its current operation, calculated by the modular real-time optimization engine based on process quality parameters; the system feedback speed refers to the rate at which the control system responds to deviations, obtained through the rate of change of the real-time deviation matrix; the time weighting factor refers to the coefficient that assigns different weights to data at different time points in the optimization calculation, provided by the time deterministic task scheduler; the disturbance resistance coefficient refers to the quantitative index of the system's ability to resist external disturbances, obtained by analyzing the fluctuation patterns in the real-time deviation fluctuation matrix.

[0048] The specific implementation of the above steps is described in detail below. Step S01 is implemented by constructing a real-time requirement matrix for industrial production process modules using the Analytic Hierarchy Process (AHP). First, response time requirement data for each process module is collected, including module identifiers and maximum allowable response times. Then, a judgment matrix is ​​established, and the real-time requirements of each module are compared pairwise to calculate eigenvalues ​​and eigenvectors, obtaining the real-time weight of each module. Next, based on the weights, the modules are divided into three real-time levels: high real-time modules (response time requirement less than 10 milliseconds), medium real-time modules (response time requirement between 10 and 100 milliseconds), and low real-time modules (response time requirement greater than 100 milliseconds). Finally, a real-time requirement matrix is ​​formed, with high real-time modules assigned priority values ​​of 9-10, medium real-time modules assigned priority values ​​of 5-8, and low real-time modules assigned priority values ​​of 1-4. The purpose of this step is to achieve a reasonable allocation of system resources, ensuring that key modules receive sufficient computing and network resources.

[0049] The specific implementation of step S02 involves deploying a time-sensitive network architecture based on the IEEE 802.1TSN standard family. First, network topology design is performed, identifying critical data flow paths and marking communication links between high-real-time modules. Then, a time-aware shaper based on IEEE 802.1Qbv is configured, dividing the network cycle into eight time slots, with four dedicated time slots reserved for high-real-time data flows. Next, the IEEE 802.1Qbu frame preemption mechanism is implemented, allowing high-priority data frames to interrupt the transmission of low-priority data frames, ensuring that the transmission delay of high-real-time signals does not exceed a preset threshold of 1 millisecond. Then, an IEEE 802.1Qci flow-based ingress strategy is configured to limit bandwidth usage by non-critical data flows. Finally, an IEEE 802.1Qch round-robin queuing and forwarding mechanism is deployed to achieve deterministic data transmission, ensuring network jitter is less than 100 microseconds. This step ensures deterministic latency characteristics in communication between critical modules, supporting high-real-time industrial control applications.

[0050] The specific implementation of step S03 is based on introducing edge computing nodes using a heterogeneous computing architecture. First, at least three edge servers are deployed according to the factory's physical layout, ensuring that the physical distance between each high-real-time module and the nearest edge server does not exceed 100 meters. Then, edge node computing resources are configured, with each node equipped with at least an 8-core processor, 16GB of memory, and a hard real-time operating system. Next, a resource-aware task allocation algorithm is developed to prioritize the allocation of real-time deviation matrix calculation tasks to edge nodes with a computing load below 50%. Then, a task migration strategy based on computing affinity is implemented; when the edge node load exceeds 80%, non-critical computing tasks are automatically migrated to the cloud. Finally, a bidirectional data caching mechanism is established to achieve incremental data synchronization between edge nodes and the central server, reducing redundant data transmission by 95%. This step effectively reduces data round-trip transmission latency and improves the system's real-time response capabilities by delegating latency-sensitive computing tasks to the edge.

[0051] The specific implementation of step S04 involves constructing a low-latency communication network based on industrial 5G technology. First, 5G base stations are deployed to achieve full coverage within the factory area, with a base station spacing of no more than 200 meters. Then, 5G network slicing is configured, establishing independent URLLC (Ultra-Reliable Low-Latency Communication) slices for industrial control traffic, reserving at least 20% of network resources. Next, wireless resource scheduling optimization is implemented, employing a semi-persistent scheduling mechanism to reduce signaling overhead and ensure uplink scheduling latency is less than 0.5 milliseconds. Then, a real-time data bus based on a distributed bus architecture is established, using a publish / subscribe model to achieve data exchange between modules, supporting data transmission priority allocation and quality of service assurance. Finally, a network quality monitoring mechanism is configured to monitor end-to-end latency in real time, triggering link switching when the latency exceeds 3 milliseconds. This step provides a unified low-latency data exchange platform for communication between all modules, achieving millisecond-level communication performance.

[0052] The specific implementation of step S05 involves monitoring the real-time deviation fluctuation matrix. First, distributed monitoring probes are deployed, with timestamp collection points arranged on the communication links between modules, and a sampling frequency of no less than 1000Hz. Then, the real-time deviation matrix is ​​calculated, and the actual response time is compared with the theoretical value in the real-time requirement matrix to form a deviation dataset. Next, an exponentially weighted moving average model is constructed to calculate the deviation change trend within a 30-second sliding window and identify abnormal fluctuation patterns. Then, a threshold-based alarm mechanism is implemented; when the communication delay deviation exceeds a set threshold (1 millisecond for high real-time modules, 10 milliseconds for medium real-time modules, and 50 milliseconds for low real-time modules), the corresponding compensation mechanism is triggered. Finally, a historical fluctuation database is built, storing at least 7 days of fluctuation data to support long-term performance analysis and optimization. This step, by capturing real-time communication delay fluctuations between modules, provides a data foundation for subsequent compensation and optimization.

[0053] The specific implementation of step S06 involves applying a real-time adjustment gain matrix for control compensation. First, a mathematical model is established based on the control compensation mechanism equation, with inputs including communication delay time, process parameter change rate, system sensitivity coefficient, response time constant, and process state variables. Then, the optimal compensation amount is calculated, and feedforward compensation is applied to the process parameter control commands to offset the impact of communication delay. Next, adaptive gain adjustment is implemented, dynamically updating the compensation parameters based on the real-time deviation matrix, with the gain adjustment range being 0.8 to 1.2 times the nominal value. Then, a model predictive control framework is established to predict the impact of communication delay on process parameters and generate compensation strategies in advance. Finally, a control effect evaluation mechanism is implemented to calculate the improvement in control accuracy before and after compensation, achieving at least a 90% accuracy improvement for high real-time modules. This step reduces the negative impact of communication delay on process control accuracy through intelligent compensation algorithms, improving the overall system performance.

[0054] The specific implementation of step S07 involves establishing a time-deterministic task scheduler. First, the dependencies in the process control flow are analyzed, mapping modular process control tasks to a directed acyclic graph structure, where nodes represent control tasks and directed edges represent dependencies. Then, a topological sorting algorithm is applied to determine the task execution order, avoiding resource conflicts and deadlocks. Next, task optimization based on the minimum latency critical path algorithm is implemented to identify critical paths affecting the overall system response time, assigning the highest execution priority to tasks on these critical paths. Then, a deterministic time slot allocation mechanism is constructed, dividing the system scheduling cycle (typically 10 milliseconds) into multiple time slots, reserving at least 40% of time resources for critical process control flows. Finally, a real-time scheduling strategy based on rate monotonicity is implemented to ensure that high-frequency periodic tasks receive the highest priority, ensuring scheduling feasibility. This step, through the deterministic task scheduling mechanism, ensures the timely execution of critical control tasks and reduces system uncertainty.

[0055] The specific implementation of step S08 involves implementing a cross-module clock synchronization mechanism. First, an IEEE 1588 precise time protocol network is deployed, selecting network devices that support hardware timestamps as the infrastructure. Then, a master-slave clock hierarchy is configured, selecting the most stable edge node as the master clock source and other nodes as slave clocks. Next, a precise time synchronization algorithm is implemented, achieving nanosecond-level clock synchronization accuracy by measuring network path latency and clock skew, ensuring a synchronization error of less than 100 nanoseconds. A clock skew monitoring mechanism is then established, periodically comparing the local time of each module with the master clock reference time and recording the skew trend. Finally, time synchronization redundancy is implemented, configuring at least one backup master clock source that automatically switches when the master clock source fails, ensuring high availability of the time synchronization service. This step, by establishing a unified time reference, eliminates time synchronization errors between modules, providing a time basis for deterministic control.

[0056] The specific implementation of step S09 involves constructing a modular real-time optimization engine. First, an adaptive feedback optimization function is designed, taking into input historical error accumulation values, current performance indicators, system feedback speed, time weighting factors, and disturbance resistance coefficients, and outputting an optimized set of gain matrix parameters. Then, parameter optimization based on a genetic algorithm is implemented, simulating an evolutionary process to find the optimal combination of gain matrix parameters. The population size is set to 50, and the number of generations is no less than 20. Next, a performance evaluation framework is established, defining a multi-objective evaluation function that includes control accuracy, response time, and stability to quantify the overall system performance. Then, an online learning mechanism is implemented, continuously adjusting the optimization model parameters based on historical operating data to adapt to process changes. The initial learning rate is set to 0.05, gradually decreasing to 0.01 as system stability improves. Finally, an optimization effect verification process is established, comparing the degree of improvement in real-time indicators before and after optimization to ensure a system performance improvement of at least 20%. This step, through continuous optimization of real-time adjustment of gain matrix parameters, achieves system self-tuning, improving the real-time control capability and production efficiency of the overall industrial production process.

[0057] The mathematical model or calculation process involved in this invention will be described in detail below.

[0058] The real-time requirement matrix construction process in step S01 involves the Analytic Hierarchy Process (AHP) calculation, specifically as follows:

[0059] W = [w1, w2, ..., w n ] T ;

[0060] In the formula, W is the module real-time weight vector; w i Let be the real-time weight of the i-th module, where i = 1, 2, ..., n; and n be the total number of modules.

[0061] The weight vector calculation process is as follows:

[0062] A = [a ij ] n×n ;

[0063] In the formula, A is the judgment matrix; a ij Let a be the ratio of the real-time importance of module i to that of module j. ij =1 / a ji a ii =1.

[0064] AW=λ max W;

[0065] In the formula, λ max To determine the largest eigenvalue of matrix A.

[0066]

[0067] In the formula, CI is a consistency index used to evaluate the degree of consistency of the judgment matrix.

[0068]

[0069] In the formula, CR is the consistency ratio; RI is the random consistency index, whose value is obtained by looking up a table based on the matrix order. For example, when n=3, RI=0.58; when n=4, RI=0.90. When CR<0.1, the matrix is ​​considered to have satisfactory consistency.

[0070] The real-time performance classification standard is as follows:

[0071]

[0072] In the formula, L i T represents the real-time performance level of module i; i This represents the maximum allowed response time for module i, in milliseconds.

[0073] The priority allocation rule is as follows:

[0074]

[0075] In the formula, P i Let be the priority value of module i; H be the set of high real-time modules; M be the set of medium real-time modules; and L be the set of low real-time modules. This formula normalizes the weights within each real-time level, ensuring that high real-time modules receive a priority of 9–10, medium real-time modules receive a priority of 5–8, and low real-time modules receive a priority of 1–4.

[0076] The final real-time requirement matrix is ​​represented as follows:

[0077] R = [r] ij ] n×2 ;

[0078] In the formula, R is the real-time requirement matrix; r i1 r is the identifier for module i; i2 The priority value P of module i i .

[0079] The calculation process for the real-time deviation fluctuation matrix in step S05 is as follows:

[0080] D = [d ij ] n×m ;

[0081] In the formula, D is the real-time deviation matrix; d ij Let be the real-time deviation value of the i-th module at the j-th sampling time; n is the total number of modules; m is the number of sampling points.

[0082]

[0083] In the formula, t ij Let i be the actual response time of the i-th module at the j-th sampling time; This represents the theoretical maximum allowable response time for the i-th module in the real-time requirement matrix.

[0084] The real-time deviation fluctuation matrix is ​​calculated using an exponentially weighted moving average model:

[0085] V = [v ij ] n×k ;

[0086] In the formula, V is the real-time deviation fluctuation matrix; v ij Let be the deviation fluctuation value of the i-th module in the j-th time window; k is the number of time windows.

[0087] v ij =α·d i，m-k+j +(1-α)·v i，j-1 ;

[0088] In the formula, α is a smoothing factor, with a value range of [0.1, 0.3], and is generally assumed to be 0.2; v i，0 The initial value is usually d. i，m-k .

[0089] Volatility trend calculation:

[0090] Δv ij =v ij -v i，j-1 ;

[0091] In the formula, Δv ij Let be the rate of change of the i-th module in the j-th time window.

[0092] Criteria for judging abnormal fluctuations:

[0093]

[0094] In the formula, A i θ is a flag indicating abnormal fluctuations in module i. i The deviation threshold for module i is determined based on the real-time performance level: 1 millisecond for high real-time modules, 10 milliseconds for medium real-time modules, and 50 milliseconds for low real-time modules; δ i The threshold for the rate of change of fluctuation of module i is usually set to θ. i 10% to 20%.

[0095] The control compensation mechanism equation in step S06 is expressed as follows:

[0096] C(t) = C0(t) + ΔC(t);

[0097] In the formula, C(t) is the compensated control command; C0(t) is the original control command; and ΔC(t) is the compensation amount.

[0098] Compensation amount calculation:

[0099]

[0100] In the formula, G is the real-time adjustment gain matrix; τ is the communication delay time vector; s is the vector of process parameter change rates; s is the vector of system sensitivity coefficients; T c X is the response time constant vector; X is the process state variable vector; f is the compensation function.

[0101] The real-time adjustment gain matrix is ​​expressed as:

[0102] G = [g ij ] n×n ;

[0103] In the formula, g ij Let G be the compensation gain coefficient of the i-th control loop for the j-th process parameter. For independent control loops, G is usually a diagonal matrix, i.e., g ij =0 (i≠j).

[0104] The specific form of the compensation function is as follows:

[0105]

[0106] In the formula, φ(X) is the process state adjustment function, which is used to adjust the compensation amount according to the current process state.

[0107]

[0108] In the formula, x i Let i be the state variable of the i-th process; Let β be the standard operating point of the i-th process state variable; i q represents the influence coefficient of the i-th state variable; q represents the number of state variables.

[0109] Adaptive gain adjustment:

[0110] g ii (t+1)=g ii (t)·(1+γ·sign(e)·|e| α );

[0111] In the formula, e is the control error; γ is the learning rate, ranging from [0.01, 0.1]; α is the nonlinearity factor, ranging from [0.5, 1.5], usually taken as 1; sign is the sign function. Gain value g ii The adjustment range is [0.8, 1.2] times the nominal value.

[0112] The minimum delay critical path algorithm in step S07 involves calculating the critical path in a directed acyclic graph:

[0113] G = (V, E);

[0114] In the formula, G is a directed acyclic graph; V is a set of nodes representing control tasks; and E is a set of directed edges representing dependencies between tasks.

[0115] Earliest start time calculation:

[0116]

[0117] In the formula, ES(v j ) is node v j The earliest start time; t(v i ) is node v i The execution time for the source node v. s ES(v s ) = 0.

[0118] Latest start time calculation:

[0119]

[0120] In the formula, LS(v i ) is node v i The latest start time for sink node v. t LS(v t ) = ES(v t ).

[0121] Time margin calculation:

[0122] Slack(v i ) = LS(v i )-ES(v i );

[0123] In the formula, Slack(v i ) is node v i The time margin is zero. Nodes on the critical path have a time margin of 0.

[0124] Deterministic time slot allocation is based on a rate monotonicity algorithm:

[0125]

[0126] In the formula, U represents processor utilization; C i T is the execution time of task i; i Let be the period of task i. The system is schedulable when the above conditions are met.

[0127] Time slot allocation priority:

[0128]

[0129] In the formula, P i This represents the scheduling priority of task i; the shorter the period, the higher the priority.

[0130] The adaptive feedback optimization function in step S09 is expressed as follows:

[0131] G new =G old +ΔG;

[0132] In the formula, G new G is the optimized gain matrix. old This represents the gain matrix before optimization; ΔG is the gain adjustment amount.

[0133] Gain adjustment calculation:

[0134]

[0135] In the formula, η is the learning rate, with an initial value of 0.05, which gradually decreases to 0.01 as the system stability increases; Let J be the gradient of the performance index J with respect to the gain matrix G.

[0136] Performance metric functions:

[0137] J(G)=w1J1(G)+w2J2(G)+w3J3(G)+w4J4(G)+w5J5(G);

[0138] In the formula, J1(G) is the control accuracy index; J2(G) is the response time index; J3(G) is the stability index; J4(G) is the robustness index; J5(G) is the energy consumption index; and w1 to w5 are weighting coefficients, satisfying...

[0139] Calculation of each sub-indicator:

[0140]

[0141] In the formula, e(t) is the control error; T is the evaluation time window.

[0142]

[0143] In the formula, Let be the response time of the i-th critical process parameter; n is the number of critical process parameters.

[0144] J3(G)=λ max (A-BG);

[0145] In the formula, λ max (A-BG) is the real part of the largest eigenvalue of the system state matrix A-BG, used to evaluate system stability.

[0146]

[0147] In the formula, ΔJ(G, Δp) j ) represents the system parameter p j Change Δp j The resulting changes in performance indicators; m is the number of system parameters.

[0148]

[0149] In the formula, u(t) is the control input; R is the positive definite weight matrix.

[0150] The parameter optimization process based on genetic algorithms includes:

[0151] 1. Encoding: Encode the non-zero elements of the gain matrix G as chromosomes.

[0152] 2. Fitness function: Where ∈ represents a small positive number to prevent the denominator from being zero.

[0153] 3. Selection: Individuals are selected using a roulette wheel method, and the selection probability is directly proportional to the fitness.

[0154] 4. Crossover: Use arithmetic crossover, G new =αG1+(1-α)G2, where α∈[0,1] is the cross coefficient.

[0155] 5. Mutation: with probability p m Perform Gaussian mutation on the chromosomes. Where N(0, σ) 2 () is a variable with a mean of 0 and a variance of σ. 2 Gaussian random variables.

[0156] Genetic algorithm parameter settings: population size 50, at least 20 generations, crossover probability p c =0.8, mutation probability p m =0.1, standard deviation of variation σ =0.05.

[0157] Optionally, the time-sensitive network architecture configuration in step S02 involves frame transmission delay calculation:

[0158] D total =D prop +D trans +D proc +D queue ;

[0159] In the formula, D total D is the total transmission delay; prop The propagation delay is related to the link length and the signal propagation speed; D trans Transmission delay is equal to the frame size divided by the link bandwidth; D proc To address latency, it is related to the processing capacity of the network equipment; D queue Queuing delay is related to network load and scheduling algorithm.

[0160] Optional, calculation of key performance indicators for time-sensitive networks:

[0161] J net =max(D total )-min(D total );

[0162] In the formula, J net Network jitter represents the range of variation in transmission delay; TSN networks require it to be less than 100 microseconds.

[0163] Optionally, the industrial 5G network slice resource allocation calculation in step S04:

[0164] R URLLC =α·R total ;

[0165] In the formula, R URLLC The amount of resources allocated to a URLLC slice; R total α represents the total network resources; α is the resource allocation ratio, which is at least 0.2.

[0166] Optionally, the precise time protocol synchronization error calculation in step S08:

[0167]

[0168] In the formula, ΔT is the clock offset; δ is the inherent bias between the master and slave clocks; t1 is the timestamp of the master clock sending the synchronization message; t2 is the timestamp of the slave clock receiving the synchronization message; t3 is the timestamp of the slave clock sending the delay request; t4 is the timestamp of the master clock receiving the delay request; ∈ is the measurement error, which is usually less than 10 nanoseconds.

[0169] Optional clock synchronization accuracy requirements:

[0170] |ΔT|<100ns;

[0171] In the formula, |ΔT| is the absolute value of the clock offset, which the system requires to be less than 0.1 microseconds.

[0172] Specifically, the principle of this invention is as follows: The core principle of this invention in solving the real-time control failure problem of modular systems in industrial production processes lies in constructing a multi-layered real-time assurance mechanism. This mechanism eliminates the impact of communication delays and scheduling uncertainties on the control system through synergistic effects. First, the real-time requirement matrix quantifies and classifies each module according to its response time requirements, providing a scientific basis for system resource allocation and ensuring that limited resources prioritize the needs of critical modules. Second, the combination of a time-sensitive network architecture and deterministic Ethernet technology achieves network-level latency determinism, keeping data transmission delays within a predictable range.

[0173] In terms of computing architecture, this invention introduces edge computing nodes, deploying latency-sensitive computing tasks near the data source, significantly reducing data transmission paths and fundamentally lowering processing latency. The application of industrial 5G technology provides a high-bandwidth, low-latency wireless channel for inter-module communication, enhancing system deployment flexibility. The real-time deviation matrix and real-time deviation fluctuation matrix constitute the system performance monitoring layer, achieving closed-loop control by capturing latency fluctuations and triggering compensation mechanisms.

[0174] The innovation of this invention lies in the design of the real-time adjustment gain matrix and control compensation mechanism equations. Based on multi-dimensional data such as communication delay time, process parameter change rate, and system sensitivity coefficient, it calculates the optimal compensation amount, enabling control commands to adaptively compensate for the impact of communication delay. This control strategy, based on a combination of prediction and compensation, can maintain the accuracy of process parameter control even in the presence of communication delay.

[0175] The time-deterministic task scheduler constructs process control tasks as a directed acyclic graph structure, identifies critical control flows using the minimum-delay critical path algorithm, and allocates deterministic time slots to them, ensuring uninterrupted execution. The cross-module synchronization clock mechanism achieves nanosecond-level clock synchronization through a precise time protocol, solving the timing problem of collaborative control in distributed systems.

[0176] Finally, the modular real-time optimization engine continuously adjusts system parameters through an adaptive feedback optimization function, enabling the system to self-adjust as the environment changes and maintain optimal real-time control performance. This multi-level, closed-loop optimization architecture conforms to the principles of cybernetics and can effectively solve real-time control problems in industrial production.

[0177] The following provides a specific embodiment 1 of the present invention, and the specific implementation of each step in this embodiment 1 is described in detail below.

[0178] The specific implementation of step S01 involves constructing a real-time requirement matrix for industrial production process modules using the Analytic Hierarchy Process (AHP). First, response time requirement data for each process module is collected, including module identifiers and maximum permissible response times. Then, a judgment matrix A = [a...] is established. ij ] n×n In the formula, A is the judgment matrix, a ij Let a be the ratio of the real-time importance of module i to that of module j. ij =1 / a ji a ii =1. Next, calculate the eigenvalues ​​and eigenvectors to obtain the module real-time weight vector W = [w1, w2, ..., w...]. n ] T AW = λ max W, where λ max To determine the largest eigenvalue of matrix A, a consistency index is calculated to ensure the consistency of the determination matrix. and consistency ratio In the formula, RI is the random consistency index, obtained by looking up a table based on the matrix order, and CR < 0.1 is required. Then, based on the weights, the modules are divided into three real-time levels: In the formula L i T represents the real-time performance level of module i. i This represents the maximum allowed response time for module i. Finally, allocation is based on priority rules. Form the real-time requirement matrix R = [r ij ] n×2 In the formula r i1 r is the identifier for module i. i2 The priority value P of module i i H represents the set of high real-time modules, M represents the set of medium real-time modules, and L represents the set of low real-time modules. This priority allocation rule ensures that high real-time modules receive a priority of 9-10, medium real-time modules receive a priority of 5-8, and low real-time modules receive a priority of 1-4. This step uses the analytic hierarchy process (AHP) to accurately quantify the real-time requirements of each module, achieving a reasonable allocation of system resources and ensuring that critical modules receive sufficient computing and network resources.

[0179] The specific implementation of step S02 involves deploying a time-sensitive network architecture based on the IEEE 802.1TSN standard family. First, network topology design is performed, identifying critical data flow paths and marking communication links between high-real-time modules. Then, a time-aware shaper based on IEEE 802.1Qbv is configured, dividing the network cycle into eight time slots, with four dedicated time slots reserved for high-real-time data flows. Next, the IEEE 802.1Qbu frame preemption mechanism is implemented, allowing high-priority data frames to interrupt the transmission of low-priority data frames. Frame transmission delay is calculated using formula D. total =D prop +D trans +D proc +D queue In the formula D total For the total transmission delay, D prop The propagation delay is related to the link length and the signal propagation speed, D. trans The transmission delay is equal to the frame size divided by the link bandwidth, D. proc To address latency, which is related to the processing capacity of network devices, D queue Queuing delay is related to network load and scheduling algorithm. By controlling each delay component, the transmission delay of high-real-time signals is ensured to not exceed a preset threshold of 1 millisecond. Network jitter calculation uses J... net =max(D total )-min(D total ), where J net To account for network jitter, representing the range of transmission delay variation, ensure it is less than 100 microseconds. Then, configure an IEEE 802.1Qci flow-based ingress policy to limit bandwidth usage by non-critical data flows. Finally, deploy an IEEE 802.1Qch round-robin queuing mechanism to achieve deterministic data transmission. This step utilizes time-sensitive networking technology to ensure deterministic latency characteristics in communication between critical modules, supporting high real-time industrial control applications.

[0180] The specific implementation method of step S03 is the same as described above, and will not be repeated in detail here.

[0181] The specific implementation of step S04 involves constructing a low-latency communication network based on industrial 5G technology. First, 5G base stations are deployed to achieve full coverage within the factory area, with a base station spacing of no more than 200 meters. Then, 5G network slicing is configured to establish independent URLLC (Ultra-Reliable Low-Latency Communication) slices for industrial control traffic, with resource allocation using formula R. URLLC =α·R total In the formula R URLLC The amount of resources allocated to a URLLC slice, R totalThe total network resources are defined as follows: α represents the resource allocation ratio, which is at least 0.2, meaning at least 20% of network resources are reserved. Next, wireless resource scheduling optimization is implemented, employing a semi-persistent scheduling mechanism to reduce signaling overhead and ensure uplink scheduling latency is less than 0.5 milliseconds. Then, a real-time data bus based on a distributed bus architecture is established, using a publish / subscribe model to achieve data exchange between modules, supporting data transmission priority allocation and quality of service assurance. Finally, a network quality monitoring mechanism is configured to monitor end-to-end latency in real time, triggering link switching when the latency exceeds 3 milliseconds. This step provides a unified low-latency data exchange platform for communication between all modules, achieving millisecond-level communication performance.

[0182] The specific implementation of step S05 involves monitoring the real-time deviation fluctuation matrix. First, distributed monitoring probes are deployed, with timestamp collection points arranged on the communication links between modules, and a sampling frequency of no less than 1000Hz. Then, the real-time deviation matrix D = [d ij ] n×m In the formula, D is the real-time deviation matrix, d ij Let be the real-time deviation value of the i-th module at the j-th sampling time, where n is the total number of modules and m is the number of sampling points. The real-time deviation value is calculated as follows: In the formula t ij Let be the actual response time of the i-th module at the j-th sampling time. This represents the theoretical maximum allowable response time for the i-th module in the real-time requirement matrix. Next, the real-time deviation fluctuation matrix V = [v...] is constructed. ij ] n×k In the formula, V is the real-time deviation fluctuation matrix, v ij Let v be the deviation fluctuation value of the i-th module in the j-th time window, and k be the number of time windows. An exponentially weighted moving average model is used to calculate v. ij =α·d i，m-k+j +(1-α)·v i，j-1 In the formula, α is a smoothing factor, with a value range of [0.1, 0.3], and is generally assumed to be 0.2. The fluctuation trend is calculated as Δv. ij =v ij -v i，j-1 In the formula, Δv ij Let be the rate of change of the i-th module in the j-th time window. Then, implement a threshold-based alarm mechanism, with the abnormal fluctuation judgment criterion being... In the formula A i θ is the indicator of abnormal fluctuations in module i. i The deviation threshold for module i is determined based on the real-time performance level: 1 millisecond for high real-time modules, 10 milliseconds for medium real-time modules, and 50 milliseconds for low real-time modules. δ i The threshold for the rate of change of fluctuation of module i is usually set to θ. iThe deviation is 10% to 20%. When the communication delay deviation exceeds a set threshold, a corresponding compensation mechanism is triggered. Finally, a historical fluctuation database is built, storing at least 7 days of fluctuation data to support long-term performance analysis and optimization. This step provides a data foundation for subsequent compensation and optimization by capturing inter-module communication delay fluctuations in real time.

[0183] The specific implementation of step S06 involves applying a real-time adjustment gain matrix for control compensation. First, a mathematical model is established based on the control compensation mechanism equation. The control command is calculated using the formula C(t) = C0(t) + ΔC(t), where C(t) is the compensated control command, C0(t) is the original control command, and ΔC(t) is the compensation amount. The compensation amount is calculated as follows: In the formula, G is the real-time adjustment gain matrix, and τ is the communication delay time vector. Let s be the vector of process parameter change rates, s be the vector of system sensitivity coefficients, and T be... c Let X be the response time constant vector, X be the process state variable vector, and f be the compensation function. The real-time adjustment gain matrix is ​​represented as G = [g ij ] n×n In the formula g ij Let G be the compensation gain coefficient of the i-th control loop for the j-th process parameter. For independent control loops, G is usually a diagonal matrix, i.e., g ij =0 (i≠j). The specific form of the compensation function is: In the formula, φ(X) is the process state adjustment function, calculated as follows: In the formula x i Let i be the state variable of the i-th process. Let β be the standard operating point of the i-th process state variable. i Let be the influence coefficient of the i-th state variable, and q be the number of state variables. Then, adaptive gain adjustment is implemented using formula g. ii (t+1)=g ii (t)·(1+γ·sign(e)·|e| α In the formula, e is the control error, γ is the learning rate (range [0.01, 0.1]), α is the nonlinearity factor (range [0.5, 1.5], usually taken as 1), and sign is the sign function. Gain value g ii The adjustment range is [0.8, 1.2] times the nominal value. A model predictive control framework is then established to predict the impact of communication delay on process parameters and generate compensation strategies in advance. Finally, a control effect evaluation mechanism is implemented to calculate the improvement in control accuracy before and after compensation, achieving at least a 90% accuracy improvement for high real-time modules. This step reduces the negative impact of communication delay on process control accuracy through intelligent compensation algorithms, improving the overall system performance.

[0184] The specific implementation of step S07 involves establishing a time-deterministic task scheduler. First, the process control flow dependencies are analyzed, mapping modular process control tasks to a directed acyclic graph structure G = (V, E), where G is the directed acyclic graph, V is the set of nodes representing control tasks, and E is the set of directed edges representing the dependencies between tasks. Then, a topological sorting algorithm is applied to determine the task execution order, avoiding resource conflicts and deadlocks. Next, task optimization based on the minimum delay critical path algorithm is implemented to calculate the earliest start time. In the formula ES(v j ) is node v j The earliest start time, t(v i ) is node v i The execution time for the source node v. s ES(v s =0. Calculate the latest start time. In the formula, LS(v i ) is node v i The latest start time for sink node v. t LS(v t ) = ES(v t ). Calculate the time margin Slack(v) i ) = LS(v i )-ES(v i ), where Slack(v i ) is node v i The time margin is zero. Nodes on the critical path have a time margin of 0. Identify the critical path that affects the overall system response time and assign the highest execution priority to tasks on the critical path. Then, construct a deterministic time slot allocation mechanism, dividing the system scheduling cycle (typically 10 milliseconds) into multiple time slots, reserving at least 40% of time resources for critical process control flows. Finally, implement a real-time scheduling strategy based on rate monotonicity, ensuring processor utilization meets... In the formula, U represents processor utilization, and C... i Let T be the execution time of task i. i Let be the period of task i. The system is schedulable when the above conditions are met. The task scheduling priority is calculated as follows: In the formula P i The scheduling priority of task i is determined by its shorter cycle, ensuring that high-frequency periodic tasks receive the highest priority and guaranteeing scheduling feasibility. This step, through a deterministic task scheduling mechanism, ensures the timely execution of critical control tasks and reduces system uncertainty.

[0185] The specific implementation of step S08 involves implementing a cross-module clock synchronization mechanism. First, an IEEE 1588 precise time protocol network is deployed, selecting network devices that support hardware timestamps as the infrastructure. Then, a master-slave clock hierarchy is configured, selecting the edge node with the highest stability as the master clock source, and the other nodes as slave clocks. Next, a precise time synchronization algorithm is implemented, with clock offset calculated using the formula... In the formula, ΔT represents the clock offset, δ represents the inherent bias between the master and slave clocks, t1 is the timestamp of the master clock sending the synchronization message, t2 is the timestamp of the slave clock receiving the synchronization message, t3 is the timestamp of the slave clock sending the delay request, t4 is the timestamp of the master clock receiving the delay request, and ∈ represents the measurement error, typically less than 10 nanoseconds. The system requires a clock synchronization accuracy of |ΔT| < 100 ns, where |ΔT| is the absolute value of the clock offset. By measuring network path delay and clock offset, nanosecond-level clock synchronization accuracy is achieved, ensuring a synchronization error of less than 100 nanoseconds. A clock offset monitoring mechanism is then established to periodically compare the local time of each module with the master clock reference time and record the offset trend. Finally, time synchronization redundancy is implemented, configuring at least one backup master clock source that automatically switches when the master clock source fails, ensuring high availability of the time synchronization service. This step, by establishing a unified time reference, eliminates time synchronization errors between modules, providing a time basis for deterministic control.

[0186] The specific implementation of step S09 involves constructing a modular real-time optimization engine. First, an adaptive feedback optimization function is designed, and the gain matrix optimization uses the iterative formula G. new =G old +ΔG, where G new G is the optimized gain matrix. old This is the gain matrix before optimization, where ΔG is the gain adjustment amount. The gain adjustment amount is calculated as follows: In the formula, η is the learning rate, initially 0.05, which gradually decreases to 0.01 as the system stability increases. Let J be the gradient of the performance index J with respect to the gain matrix G. The performance index function is J(G) = w1J1(G) + w2J2(G) + w3J3(G) + w4J4(G) + w5J5(G), where J1(G) is the control accuracy index, J2(G) is the response time index, J3(G) is the stability index, J4(G) is the robustness index, J5(G) is the energy consumption index, and w1 to w5 are weighting coefficients, satisfying the following... The calculations for each sub-indicator are as follows: (Control accuracy indicators) (Response time metric), J3(G) = λ max (A-BG) (Stability Indicators) (Robustness index) (Energy consumption index). Then, parameter optimization based on a genetic algorithm is implemented, with the fitness function being... In the formula, ∈ represents a small positive number to prevent the denominator from being zero. The individual is selected using a roulette wheel method, and the arithmetic crossover operation is G. new =αG1 + (1-α)G2, where α∈[0,1] is the crossover coefficient. The Gaussian mutation operation is... In the formula, N(0, σ) 2 () is a variable with a mean of 0 and a variance of σ. 2 The Gaussian random variable. Genetic algorithm parameter settings: population size 50, at least 20 generations, crossover probability p. c =0.8, mutation probability p m =0.1, standard deviation of variation σ = 0.05. Next, a performance evaluation framework is established, defining a multi-objective evaluation function that includes control accuracy, response time, and stability to quantify the overall system performance. Then, an online learning mechanism is implemented, continuously adjusting and optimizing model parameters based on historical operating data to adapt to process changes. The initial learning rate is set at 0.05, gradually decreasing to 0.01 as system stability improves. Finally, an optimization effect verification process is established to compare the degree of improvement in real-time indicators before and after optimization, ensuring that system performance is improved by at least 20%. This step, through continuous optimization of real-time adjustment of gain matrix parameters, achieves system self-tuning, improving the real-time control capability and production efficiency of the overall industrial production process.

[0187] To better understand and implement this invention, a specific application scenario is provided below as Example 2: In a smart manufacturing laboratory, researchers implemented a modular real-time optimization method for industrial production processes on a 6-axis industrial robot control system. This robot control system consists of multiple functional modules, including a motion planning module, a trajectory generation module, a joint control module, a vision perception module, a force feedback module, and a running status monitoring module. Due to communication delays between the system modules, the robot's control precision is insufficient when performing high-precision assembly tasks, especially in situations requiring coordinated vision and force feedback control, where the response delay severely impacts operational efficiency.

[0188] First, the researchers constructed a real-time requirement matrix using the analytic hierarchy process (AHP). By analyzing and evaluating the response time requirements of each module, a judgment matrix was established as shown in Table 1.

[0189] Table 1. Matrix for Judging the Importance of Real-Time Performance of Each Module

[0190]

[0191] The calculated weight vector is W = [0.042, 0.093, 0.362, 0.172, 0.276, 0.055]. TThe consistency ratio CR = 0.026 < 0.1, meeting the consistency requirements. Response time analysis determined that joint control and force feedback are high real-time modules (response time requirements of 0.5 ms and 2 ms respectively), visual perception and trajectory generation are medium real-time modules (response time requirements of 15 ms and 30 ms respectively), and motion planning and running status monitoring are low real-time modules (response time requirements of 100 ms and 200 ms respectively). The final real-time requirement matrix is ​​shown in Table 2.

[0192] Table 2 Results of the Real-Time Requirements Matrix

[0193] Module identifier Real-time performance level Maximum allowable response time (ms) Priority value Joint control high 0.5 9.57 Force feedback high 2 9.43 Visual perception middle 15 7.26 Trajectory generation middle 30 5.74 Exercise planning Low 100 1.43 Operational status monitoring Low 200 1.57

[0194] Figure 2 This paper compares the real-time requirements of six different modules in an industrial robot control system. The charts use a dual Y-axis design, with blue bars representing the maximum allowable response time (in milliseconds, logarithmic scale) for each module and red line graphs representing priority values. Modules are arranged from highest to lowest real-time performance: joint control, force feedback (high real-time), visual perception, trajectory generation (medium real-time), motion planning, and operational status monitoring (low real-time). The real-time performance level of each module is clearly marked in the charts (using different colored boxes), and the inverse relationship between response time and priority is shown. The researchers then deployed a time-sensitive network architecture based on the IEEE 802.1TSN standard. The network topology design is shown in Table 3.

[0195] Table 3 TSN Network Configuration Parameters

[0196]

[0197]

[0198] Next, three edge computing nodes were deployed, located near the industrial robot control cabinet, vision system, and force feedback system, respectively, with a maximum physical distance of 30 meters. The edge node computing resource configuration is shown in Table 4.

[0199] Table 4 Edge Computing Node Configuration

[0200]

[0201] Researchers used industrial 5G networks to build a low-latency communication network, configured URLLC network slicing, reserved 30% of network resources for control traffic, and achieved communication performance with an end-to-end average latency of 0.8 milliseconds.

[0202] During implementation, the system monitored and collected real-time deviation data of the communication links between modules in real time, generating a real-time deviation matrix. The deviation fluctuation matrix was calculated using an exponentially weighted moving average model (smoothing factor α = 0.2), revealing significant periodic delay fluctuations in the communication link from joint control to force feedback, with a peak deviation of 0.8 milliseconds, exceeding the 0.5 millisecond threshold. Figure 3 The graph illustrates the real-time performance deviation fluctuations of four key communication links in the system. The horizontal axis represents time (seconds), and the vertical axis represents communication latency (milliseconds). Different colored curves represent communication links between different modules: joint control → force feedback (red), visual perception → trajectory generation (green), trajectory generation → joint control (blue), and force feedback → force control execution (purple). The graph uses dashed lines to mark the latency thresholds for each link, and highlights the portion of the "joint control → force feedback" link that exceeds the threshold with a red semi-transparent area.

[0203] To address this issue, researchers applied real-time adjustment of the gain matrix for control compensation. Based on the system identification results, the initial gain matrix is ​​constructed as shown in Table 5:

[0204] Table 5 Initial Gain Matrix

[0205]

[0206]

[0207] By establishing a time-deterministic task scheduler, researchers mapped robot control tasks to a directed acyclic graph structure, identifying the critical path as: visual perception → trajectory generation → joint control → force feedback → force control execution. Resources were prioritized for control tasks on the critical path, reserving 50% of time resources for these critical tasks. Cross-module clock synchronization was achieved using the IEEE 1588 precise time protocol, with synchronization accuracy consistently within 75 nanoseconds.

[0208] Finally, a modular real-time optimization engine was constructed, and a genetic algorithm was used to optimize the gain matrix parameters. The population size was set to 50, the number of generations to 30, the crossover probability to 0.8, and the mutation probability to 0.1. The optimization results showed that the gain coefficient of joint 3 control was adjusted from 1.12 to 1.16, the gain coefficient of force control Fz was adjusted from 1.20 to 1.25, and other parameters were also adjusted accordingly. Figure 4 A side-by-side bar chart was used to compare the changes in the gain matrix parameters before and after optimization. The horizontal axis represents the nine control parameters, and the vertical axis represents the gain coefficient values. Blue bars represent the values ​​before optimization, and red bars represent the values ​​after optimization, with the specific values ​​marked above each bar. The percentage change in parameters (green indicates an increase) is indicated between the two sets of bars.

[0209] The system performance test results are shown in Table 6:

[0210] Table 6 Performance Comparison Before and After System Optimization

[0211] Performance indicators Before optimization After optimization Improvement range Average control accuracy error (mm) 0.28 0.06 78.6％ Maximum control accuracy error (mm) 0.65 0.15 76.9％ Average response time (ms) 12.5 4.8 61.6％ Maximum response time (ms) 25.3 8.2 67.6％ System stability indicators 0.76 0.92 21.1％ Tracking error (mm) 0.42 0.11 73.8％ Force control error (N) 0.58 0.16 72.4％ Anti-interference capability index 0.63 0.87 38.1％

[0212] Traditional real-time control methods for industrial robots mainly rely on increasing hardware performance, simplifying control algorithms, or reducing system complexity to meet real-time requirements. However, these methods often come at the cost of sacrificing system functionality and control accuracy. For example, common communication optimization methods include using a hard real-time operating system, using fieldbus, and simplifying the control model. While these methods can improve real-time performance to some extent, they cannot effectively address communication latency issues in modular systems, especially in complex systems where different modules have different real-time requirements.

[0213] In contrast, the modular real-time optimization method for industrial production processes of this invention solves this problem through several innovative means: First, it quantifies the real-time requirements of each module using the analytic hierarchy process (AHP) to achieve precise resource allocation; second, it constructs a deterministic communication infrastructure using time-sensitive networking and edge computing technologies; third, it introduces a real-time deviation fluctuation matrix monitoring and real-time adjustment gain matrix compensation mechanism, which not only monitors communication delays but also intelligently compensates for their impact; finally, it achieves continuous self-adjustment of the system through adaptive feedback optimization. Implementation results show that this method significantly improves the real-time performance and control accuracy of industrial control systems without increasing hardware costs, achieving a reduction of approximately 75% in control errors and a shortening of response time by approximately 65%, providing a systematic solution for the modular and real-time optimization of industrial production processes.

[0214] It should be noted that the variables involved in this invention are explained in detail in Tables 7 and 8 below.

[0215] Table 7. Variable Explanation Table (Part 1)

[0216]

[0217]

[0218] Table 8. Variable Explanation Table (Part Two)

[0219]

[0220]

[0221] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. A modular optimization method for industrial production processes, characterized in that, This includes constructing a real-time requirement matrix, classifying each module of the industrial production process into real-time levels, and assigning higher priority to modules with high real-time requirements. Deploy a time-sensitive network architecture and implement deterministic Ethernet technology on the inter-module communication channels; introduce edge computing nodes to distribute real-time deviation matrix calculation tasks to edge servers close to the production site; build a low-latency communication network based on industrial 5G technology; and implement real-time deviation fluctuation matrix monitoring. The gain matrix is ​​adjusted in real time, and adaptive compensation for process parameter control commands is performed based on the control compensation mechanism equation; a time-deterministic task scheduler is established. Implement a cross-module synchronous clock mechanism; construct a modular real-time optimization engine, and continuously optimize the real-time performance by adjusting the gain matrix parameters through an adaptive feedback optimization function; The control compensation mechanism equation is expressed as follows: ； In the formula, The control command is after compensation; These are the original control commands; For compensation amount; in, ; In the formula, Adjust the gain matrix in real time; This is a communication delay time vector; This is a vector representing the rate of change of process parameters; This is the system sensitivity coefficient vector; For the response time constant vector; A vector of process state variables; For compensation functions; in, ; In the formula, For the first The control loop for the first The compensation gain coefficient for each process parameter, for an independent control loop. It is usually a diagonal matrix, that is ; in, ; In the formula, This is a process state adjustment function used to adjust the compensation amount according to the current process state, specifically expressed as: ； In the formula, For the first One process state variable; For the first Standard operating point for each process state variable; For the first The influence coefficients of each state variable; The number of state variables; The adaptive gain adjustment is represented as follows: ； In the formula, To control errors; The learning rate has a range of values. ; It is a non-linear factor, and its value range is... ; It is a symbolic function.

2. The modular optimization method for industrial production processes according to claim 1, characterized in that, The real-time requirement matrix refers to quantifying the response time requirements of each process module in industrial production into a matrix form, including module identifiers and corresponding maximum allowable response times, which is used for system resource allocation and task priority ranking.

3. The modular optimization method for industrial production processes according to claim 2, characterized in that, The real-time deviation matrix is ​​a matrix formed by calculating the difference between the actual response time and the theoretical value in the real-time requirement matrix by monitoring the communication and control execution time of each module in real time. It is used to evaluate the real-time performance of the system.

4. The modular optimization method for industrial production processes according to claim 3, characterized in that, The real-time deviation fluctuation matrix refers to a multi-dimensional data structure that records the trend of real-time deviation changes within a certain time window. By statistically analyzing the rate of deviation change and the fluctuation amplitude, the trend of system performance degradation can be predicted.

5. The modular optimization method for industrial production processes according to claim 4, characterized in that, The real-time adjustment gain matrix refers to the adaptive compensation parameter matrix set for each control loop based on real-time deviations and fluctuations, used to dynamically adjust control commands to compensate for the effects of communication delays.

6. The modular optimization method for industrial production processes according to claim 5, characterized in that, The control compensation mechanism equation is a mathematical expression that calculates the optimal compensation amount based on communication delay time, process parameter change rate, system sensitivity coefficient, response time constant, and process state variables, and outputs the real-time compensation amount of the control command to ensure that the process parameter control can still be kept within the target range even when communication delay exists.

7. The modular optimization method for industrial production processes according to claim 6, characterized in that, The adaptive feedback optimization function is a mathematical function that dynamically adjusts the weights of each parameter in the real-time adjustment gain matrix based on historical error accumulation, current performance indicators, system feedback speed, time weighting factor, and disturbance resistance coefficient, and outputs the optimized gain matrix parameter set.

8. The modular optimization method for industrial production processes according to claim 7, characterized in that, The communication delay time refers to the time required for instructions or data to be transmitted from the source module to the target module in the industrial control network, which is obtained by monitoring the time-sensitive network architecture; the process parameter change rate refers to the speed at which key process parameters change over time in the industrial production process, which is calculated from the process parameter sequence collected by the real-time data bus.

9. The modular optimization method for industrial production processes according to claim 8, characterized in that, The system sensitivity coefficient refers to the degree of response of process parameters to changes in control commands, which is obtained by analyzing the process parameter response curve through edge computing nodes; the response time constant refers to the characteristic time required for the process system to reach a steady state in response to the control signal, which is provided by the real-time requirement matrix.

10. The modular optimization method for industrial production processes according to claim 9, characterized in that, Process state variables refer to the set of key parameters describing the current process state, which are collected from each process module through a low-latency communication network; historical error accumulation refers to the weighted accumulation of system control errors over a period of time, which is calculated from the real-time deviation fluctuation matrix.

Images