Automatic production line monitoring control management method and system

Abstract

The invention discloses an automatic production line monitoring control management method and system, and particularly relates to the field of production line monitoring, and the method comprises the steps: calculating the flow distribution in a preset time period and the resource gap value of each edge node through the topological structure and historical data of a target production line; furthermore, the resource allocation allocated to each edge node is dynamically adjusted, and continuous optimization circulation is carried out. According to the automatic production line monitoring control management method and system, dynamic resource scheduling from high-load nodes to low-load nodes is achieved by predicting flow distribution changes, local response delay caused by uneven loads is effectively relieved, and the fluctuation standard deviation of the resource utilization rate is reduced; resource gap calculation is coordinated through a bilevel programming algorithm, and the problem that the resource utilization rate fluctuates too much is remarkably solved; and by dynamically correcting global model parameters, adaptive evolution of a scheduling strategy along with topological change is ensured, and the stability in a complex production scene is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of production line monitoring, and more specifically, to an automated production line monitoring, control and management method and system. Background Art

[0002] With the in-depth application of industrial automation technology, the efficient monitoring and precise control of production lines are particularly important; traditional automated production line monitoring and control systems mainly adopt a centralized architecture, which consists of sensors, programmable logic controllers and a central monitoring server distributed at each work station. The device status data is collected by distributed sensors, and after primary processing by the programmable logic controller, it is uploaded to the central server for unified analysis and decision-making; however, when facing the production scenario of multiple varieties and small batches, this traditional architecture exposes technical bottlenecks such as high data processing latency, lag in response to abnormal working conditions, and insufficient ability for multi-dimensional production data correlation analysis, making it difficult to meet the requirements of dynamic adjustment and refined management and control in complex production processes.

[0003] To break through the performance limitations of the traditional architecture, a monitoring system based on distributed edge nodes is proposed; by deploying edge computing nodes at each key work station of the production line, local preprocessing and real-time control are performed on the sensor data collected in real time, and only the key feature data is uploaded to the central platform, while receiving the global scheduling instructions of the central platform.

[0004] However, in actual use, there are still some disadvantages. For example, when the production line is reorganized and the data traffic distribution changes, some edge nodes have processing queue congestion due to a sharp increase in load, while the idle node resources are not effectively scheduled, ultimately leading to local response delays; the resource scheduling lacks a mechanism to dynamically perceive the changes in the production line topology, and there is a lack of fine-grained resource coordination ability between edge nodes, resulting in excessive fluctuations in the overall resource utilization rate of the system, restricting the stability guarantee in complex production scenarios. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art, the present invention provides an automated production line monitoring, control and management method and system, through the following solutions to solve the problems raised in the above background art.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] An automated production line monitoring, control and management method, comprising:

[0008] S1: Real-time capture the physical connection status and position coordinate information of each device in the target production line, and generate topology vector data representing the topology structure of the target production line;

[0009] S2: Calculate the traffic distribution within a preset time period using a prediction model based on the topological vector data and historical data;

[0010] S3: Calculate the resource gap values of each edge node within the preset time period according to the traffic distribution and the load status of the target edge nodes. The resource gap values include computing resource requirements and network bandwidth requirements;

[0011] S4: Dynamically adjust the resource instance configuration allocated to each edge node based on the resource gap values;

[0012] S5: Generate a task allocation plan using a decision model and perform task scheduling based on the task allocation plan;

[0013] S6: Execute a continuous optimization loop, which at least includes:

[0014] Monitor the resource utilization rate of each edge node, recycle idle resources and use them to update the calculation of the resource gap values;

[0015] Update the prediction model and the decision model based on the synchronization of model parameters among edge nodes.

[0016] Preferably, in S1, the topological vector data includes:

[0017] Real-time scan the device space coordinates through sensors pre-deployed on the production line, and construct a three-dimensional topological model based on the point cloud registration algorithm;

[0018] And calculate the device displacement using a sliding window mechanism. When the displacement variance of consecutive N sampling periods exceeds a preset threshold, trigger a topology update event and generate an incremental topological change vector, where N is a positive integer dynamically adjusted according to the production rhythm. The incremental topological change vector is used to update the topological vector data in real time.

[0019] Preferably, in S2, the prediction model is a spatio-temporal neural network;

[0020] The prediction model receives the device connection relationship and spatial position information in the topological vector data and outputs a traffic distribution with a confidence evaluation value;

[0021] The confidence evaluation value is used to dynamically adjust the weight of the calculation of the resource gap values.

[0022] Preferably, in S3, a two-layer programming algorithm is used to calculate the resource gap values of each edge node within the preset time period. The upper layer programming determines the computing resource requirement ratio, and the lower layer programming solves the network bandwidth constraint conditions to obtain a multi-objective optimization solution that coordinates computing and network resources as the resource gap value.

[0023] Preferably, in step S5, the task scheduling includes:

[0024] The input information of the decision-making model is configured as the real-time updated topological vector data, the predicted traffic distribution, and the real-time load status and available resource information of each edge node;

[0025] Based on the input information, generate the task allocation scheme by optimizing one or more objective functions, where the objective functions are used to jointly optimize at least two of the following: minimizing the end-to-end processing delay of tasks, maximizing the load balancing degree among edge nodes, and maximizing the overall resource utilization rate of the system;

[0026] The task allocation scheme is used to specify the allocation and migration paths of tasks among edge nodes to actively direct the computing load from high-load nodes to low-load nodes.

[0027] Preferably, in step S5, the task scheduling further includes:

[0028] Deploy a task processing queue with multi-dimensional priority labels at the target edge node, where the multi-dimensional priority labels are determined based at least on the task urgency and migration efficiency;

[0029] And when it is detected that the depth of the task processing queue exceeds the threshold, preferentially migrate specific tasks to other nodes according to the multi-dimensional priority labels.

[0030] To achieve the above object, the present invention provides the following technical solution: An automated production line monitoring and control management system, including a system operation database, a system central processing module, and a user information terminal. Implementing the above-mentioned automated production line monitoring and control management method includes:

[0031] Dynamic topology structure acquisition module: Real-time capture the physical connection status and position coordinate information of each device in the target production line, and generate topological vector data representing the topological structure of the target production line;

[0032] Traffic distribution prediction module: Based on the topological vector data and historical data, use a prediction model to calculate the traffic distribution within a preset time period;

[0033] Resource demand assessment module: According to the traffic distribution and the load status of the target edge node, calculate the resource gap value of each edge node within the preset time period, where the resource gap value includes computing resource demand and network bandwidth demand;

[0034] Collaborative scheduling module: Dynamically adjust the resource instance configuration allocated to each edge node according to the resource gap value;

[0035] Task dynamic scheduling execution module: Generates a task allocation plan using a decision-making model and executes task scheduling based on the task allocation plan;

[0036] Closed-loop optimization module: Executes a continuous optimization loop, which at least includes:

[0037] Monitors the resource utilization rate of each edge node, reclaims idle resources and uses them to update the calculation of the resource gap value;

[0038] Updates the prediction model and the decision-making model based on the synchronization of model parameters between edge nodes;

[0039] The system operation database includes all data texts of an automated production line monitoring and control management system, and real-time collects information texts output by each module. The system central processing module is used for information text instructions output by each module in the central control system, and the user information terminal is an information output device that receives an automated production line monitoring and control management system.

[0040] Preferably, the closed-loop optimization module updates the prediction model and the decision-making model based on the synchronization of model parameters between edge nodes, including:

[0041] Constructs a federated learning architecture between edge nodes, and updates the global model parameters using a parameter aggregation strategy based on model contribution degree based on the scheduling decisions or local data training results of each edge node.

[0042] Technical effects and advantages of the present invention:

[0043] 1. The present invention captures the physical connection status and displacement changes of devices in real time, generates an incremental topological change vector, and accurately predicts the change of traffic distribution by processing the device topological relationship, realizing the dynamic scheduling of resources from high-load nodes to low-load nodes, effectively alleviating the local response delay caused by uneven load, and reducing the standard deviation of fluctuations in resource utilization rate;

[0044] 2. The present invention coordinates the calculation of multi-objective resource gaps through a two-layer programming algorithm, realizes fine-grained optimization of the task migration path, and significantly improves the problem of excessive fluctuations in resource utilization rate;

[0045] 3. The present invention dynamically corrects the global model parameters to ensure that the scheduling strategy adapts and evolves with topological changes, improving the stability in complex production scenarios. Description of the Drawings

[0046] Figure 1 It is a flowchart of the implementation of an automated production line monitoring and control management method provided according to an embodiment of the present application.

[0047] Figure 2It is a system structure block diagram of an automated production line monitoring, control and management system provided according to an embodiment of the present application. Detailed implementation manners

[0048] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0049] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit the present application. As used in the specification of the present application, the singular forms "a", "an", "the", "above-mentioned", "the said" and "this" are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term " / and / " used in the present application refers to and includes any or all possible combinations of one or more of the listed items; in the description of the embodiments of the present application, unless otherwise stated, the meaning of "a plurality" is two or more.

[0050] As shown in the attached Figure 1 For an automated production line monitoring, control and management method, first, based on the topological structure and historical data of the target production line, calculate the traffic distribution and the resource gap values of each edge node within a preset time period, and then dynamically adjust the resource configuration allocated to each edge node and perform continuous optimization cycles. Specifically, it includes the following steps:

[0051] S1: Real-time capture the physical connection status and position coordinate information of each device in the target production line, and generate topological vector data representing the topological structure of the target production line;

[0052] S2: Based on the topological vector data and historical data, use a prediction model to calculate the traffic distribution within a preset time period;

[0053] S3: According to the traffic distribution and the load status of the target edge node, calculate the resource gap values of each edge node within the preset time period, and the resource gap values include computing resource requirements and network bandwidth requirements;

[0054] S4: According to the resource gap values, dynamically adjust the resource instance configuration allocated to each edge node;

[0055] S5: Use a decision model to generate a task allocation plan, and perform task scheduling based on the task allocation plan;

[0056] S6: Execute a continuous optimization loop, which at least includes:

[0057] Monitor the resource utilization rate of each edge node, recycle idle resources and use them to update the calculation of the resource gap value;

[0058] Update the prediction model and the decision model based on the model parameter synchronization among edge nodes.

[0059] Specifically, in S1, the spatial coordinates of the equipment are scanned in real time by sensors pre-deployed on the production line, and a three-dimensional topological model is constructed based on the point cloud registration algorithm; and the sliding window mechanism is used to calculate the equipment displacement. When the displacement variance of N consecutive sampling periods exceeds the preset threshold, a topology update event is triggered and an incremental topological change vector is generated, and the incremental topological change vector is used to update the topological vector data in real time.

[0060] In this embodiment, a millimeter-wave radar array, UWB positioning tags cooperating with a base station or other high-precision sensors are pre-deployed at key positions on the production line. The key positions in this embodiment include but are not limited to the end of a movable reconfiguration robotic arm, fixed monitoring points, etc., to scan the spatial coordinates of each key device on the production line in real time, where the key devices include but are not limited to robots, conveyor controllers, vision detection units, etc.; at the same time, through an industrial standard communication protocol, a connection is established with the programmable logic controller or its upper computer of the key devices on the production line to collect structured data packets containing the unique identifier of the device, real-time three-dimensional coordinates, and the connection port status of the network interface in real time.

[0061] For the coordinate acquisition noise caused by electromagnetic interference or physical occlusion existing in the industrial field of multiple embodiments, the sliding average filtering algorithm is used to process the original coordinate data to eliminate instantaneous jumps and high-frequency noise; and to adapt to the change of the device moving speed under different operating states of the production line, the size of the filtering window can be adaptively adjusted according to the historical moving speed or current acceleration of the device. If it is detected that the device is in a high-speed moving state, the filtering window is appropriately reduced to ensure real-time performance; if the device is relatively stationary or moving slowly, the filtering window is increased to obtain a smoother and more accurate coordinate estimate.

[0062] The construction process of the three-dimensional topological model can be specifically decomposed as follows: perform voxel grid filtering on the device coordinate information that has been cleaned and filtered, set the voxel size to regularize the data and reduce the computational complexity; use the RANSAC algorithm to remove the background interference point clouds of fixed or slowly moving objects such as conveyor belts; through the ICP algorithm, achieve the initial spatial alignment of the RGB-D depth point cloud and the millimeter-wave radar point cloud; extract the key geometric features of the device surface, including detecting stable three-dimensional feature corner points using the Harris3D algorithm and calculating the fast point feature histogram to describe the local surface normal vector information of each point; if the variance of the device displacement calculated within the preset sliding time window exceeds the preset threshold, trigger the incremental topological update process, and the updated result is encapsulated into a structured incremental topological change vector.

[0063] It should be noted that this embodiment also includes a dynamic adjustment mechanism. Based on the production line beat cycle obtained in real time from controllers such as PLCs, the size of the point cloud sampling and analysis window is dynamically calculated. In this embodiment, the value of 200 milliseconds divided by the production line beat cycle is calculated using the ceiling function to ensure that the window can cover at least two production cycles to capture the complete dynamics.

[0064] Specifically, in S2, the prediction model is a spatio-temporal neural network; the prediction model receives the device connection relationship and spatial position information in the topological vector data and outputs a traffic distribution with a confidence evaluation value; the confidence evaluation value is used to dynamically adjust the weight of the calculation of the resource gap value.

[0065] It should be noted that in the spatio-temporal neural network, a graph convolutional network is constructed to process the topological vector data between devices. Further, each key device on the production line is used as a node of the graph, and the physical connection between devices is used as an edge to establish an adjacency matrix. The eigenvector of the adjacency matrix node includes the topological vector data and the traffic mean reflecting its historical load situation, while the weight w of the edge ij is jointly determined by the actual bandwidth BW of the connection link ij and the physical distance between devices, and is specifically expressed as:

[0066]

[0067] where α represents the distance influence factor, p i and p jdenoted as the physical distance between devices i and j; further, the physical connection relationship between devices is converted into graph embedding vectors for each device, and a global topological feature vector is generated through graph pooling operations. For the spatial position coordinate information, a three-dimensional sine position encoding scheme is adopted to map the (x, y, z) coordinates of each device into high-dimensional feature vectors, so as to calculate the confidence evaluation value through the structure of a dual output head, where the main output head is responsible for predicting the future traffic distribution of each edge node, and the auxiliary output head calculates the confidence value in parallel. The calculation of the confidence evaluation value includes the cosine similarity between the current prediction result and the historical traffic pattern, the degree of uncertainty of the internal feature representation of the model estimated by methods such as Monte Carlo sampling, and the logical verification result of the integrity of the input data.

[0068] In this embodiment, the weight coefficient is adjusted based on the calculated confidence. When the confidence is in the interval [0.9, 1.0], the weight coefficient is set to 1.2, indicating a high degree of trust in the prediction result and it can be directly used for aggressive resource pre-allocation. When the confidence is in the interval [0.7, 0.9), the weight is 1, and resources are allocated according to the normal process while starting the monitoring of standby resources. If the confidence drops to the interval [0.5, 0.7), the weight coefficient is adjusted down to 0.8, reducing the resource allocation amount accordingly and triggering the manual review process. When the confidence is below 0.5, the weight coefficient is further reduced to 0.5, switching to the resource allocation mode based on the historical average.

[0069] Specifically, in S3, a two-layer programming algorithm is used to calculate the resource gap value of each edge node within the preset time period. The upper layer programming determines the proportion of computing resource requirements, and the lower layer programming solves the network bandwidth constraint conditions to obtain a multi-objective optimization solution that coordinates computing and network resources as the resource gap value.

[0070] In this embodiment, the upper layer programming objective of the two-layer programming algorithm is to minimize the overall computing resource gap, that is, the sum of CPU requirements and memory requirements, and a constraint condition is imposed that the allocation ratio of CPU and memory resources on a single edge node must be maintained within a preset range, and the preset range is set to 0.5 ≤ CPU:memory ≤ 2.0. This embodiment uses the Lagrangian relaxation algorithm to relax the coupling constraints between nodes and iteratively update the Lagrangian multipliers until the convergence condition is reached, thereby obtaining the optimal solution of computing resource requirements; further, the lower layer programming objective is the optimization of network resources. In this embodiment, the objective of the lower layer programming is set to maximize the bandwidth utilization rate of the entire network, and the constraint conditions include that the upper limit of the bandwidth that each physical link in the network can carry must not be exceeded, and the end-to-end transmission delay of critical service data streams must be strictly controlled within a preset threshold.

[0071] It should be noted that the traffic distribution data predicted and generated in S2 is used for logical regional division and mapping the divided regions to the corresponding subnets in the network topology; the traffic peaks of each subnet serve as the bandwidth demand constraints for the lower-layer planning; meanwhile, the historical load data of the edge nodes is used to initialize the resource configuration baseline for the upper-layer planning.

[0072] Specifically, in S4, a resource pooling engine is constructed based on the resource gap value to allow high-load nodes to borrow idle computing units of low-load nodes through a secure channel and dynamically adjust the resource configuration of containerized instances.

[0073] Furthermore, containerization technology is adopted to abstract the computing resources and storage resources on each edge node into schedulable virtual units and label their load status as idle or occupied; based on the resource gap values of each edge node generated in S3, the types and scales of resources to be allocated are calculated.

[0074] Even further, a resource adjustment protocol process is designed and executed. When an edge node has a resource demand due to load, it sends a resource request to the resource pool through the message queue protocol, stating the bandwidth, quantity, and tolerable delay of the required resource type; meanwhile, the low-load node reports the available idle resource information to the resource pooling engine, and the resource pooling engine combines the topology vector data generated in S1 to screen out candidate resource-providing nodes that meet the delay constraint.

[0075] Specifically, in S5, the input information of the decision model is configured as the real-time updated topology vector data, the predicted traffic distribution, and the real-time load status and available resource information of each edge node; in this embodiment, based on the physical connection status and location coordinate information of each device in S1, combined with the network link bandwidth parameters, the delay values between each node are generated to form a global delay matrix for scheduling decision-making; using the traffic prediction result output in S2, the task type distribution, data scale, and time distribution characteristics within a preset time period are obtained; the CPU utilization rate, memory occupancy rate, network bandwidth margin, and container instance health status are collected in real time by a lightweight agent deployed on the edge node and encapsulated and reported in JSON format; the data is fused in real time through a unified data bus, and the data update frequency is set to once per second and divided into three partitions, corresponding to topology data, traffic prediction, and node status respectively, and pushed to the decision model to ensure low latency and high consistency of the input information.

[0076] Furthermore, based on the input information, the task allocation scheme is generated by optimizing one or more objective functions, which are used to jointly optimize at least two of the following: minimizing the end-to-end processing delay of tasks, maximizing the load balancing degree among edge nodes, and maximizing the overall resource utilization rate of the system; the task allocation scheme is used to specify the allocation and migration paths of tasks among edge nodes to actively direct the computing load from high-load nodes to low-load nodes; in this embodiment, the preliminary task allocation scheme is solved by mixed integer programming, and the constraint conditions include the maximum number of hops between nodes ≤ 3 and the upper limit of the resource capacity of a single node; and the NSGA-II multi-objective genetic algorithm is used to iteratively optimize the coarse-grained scheme, with the task migration path as the gene encoding, generating new solutions through crossover and mutation operations, and screening the optimal solutions based on the Pareto front, focusing on adjusting the task migration paths of high-load nodes to reduce local hotspots.

[0077] Furthermore, a task processing queue with multi-dimensional priority tags is deployed at the target edge node, and the multi-dimensional priority tags are determined based on at least the task urgency and migration efficiency; and when it is detected that the depth of the task processing queue exceeds the threshold, specific tasks are preferentially migrated to other nodes according to the multi-dimensional priority tags; in this embodiment, each task is assigned multi-dimensional priority tags when entering the edge node, including the urgency dynamically calculated according to the task deadline, the migration efficiency inversely proportional to the migration cost, and the relevance measuring the context dependence strength between the task and the current node.

[0078] As shown in the Figure 2 accompanying drawings, an automated production line monitoring and control management system includes a system operation database, a system central processing module, and a user information terminal, and further includes:

[0079] Dynamic topology structure acquisition module: It captures the physical connection status and position coordinate information of each device in the target production line in real time and generates topology vector data representing the topology structure of the target production line;

[0080] Flow distribution prediction module: Based on the topology vector data and historical data, it calculates the flow distribution within a preset time period using a prediction model;

[0081] Resource demand assessment module: According to the flow distribution and the load status of the target edge node, it calculates the resource gap values of each edge node within the preset time period, and the resource gap values include computing resource requirements and network bandwidth requirements;

[0082] Collaborative scheduling module: According to the resource gap values, it dynamically adjusts the resource instance configuration allocated to each edge node;

[0083] Task Dynamic Scheduling Execution Module: Generates a task allocation plan using a decision-making model and executes task scheduling based on the task allocation plan;

[0084] Closed-loop Optimization Module: Executes a continuous optimization loop, which at least includes:

[0085] Monitors the resource utilization rate of each edge node, reclaims idle resources and uses them to update the calculation of the resource gap value;

[0086] Updates the prediction model and the decision-making model based on the synchronization of model parameters among edge nodes;

[0087] In this embodiment, executing the resource dynamic optimization loop includes: monitoring the resource gap value and triggering an idle resource recovery mechanism, and feeding back the recovered resources to the resource demand assessment module; constructing a federated learning architecture among edge nodes, and updating the global model parameters using a parameter aggregation strategy based on model contribution degree based on the scheduling decisions or local data training results of each edge node.

[0088] It should be noted that the topological vector data of the dynamic topology structure acquisition module drives the traffic prediction of the traffic distribution prediction module. The resource gap assessment of the resource demand assessment module depends on the prediction results of the traffic distribution prediction module. The resource allocation plan of the collaborative scheduling module is controlled by the assessment parameters of the resource demand assessment module. The scheduling decision of the task dynamic scheduling execution module synchronously receives the resource network status of the collaborative scheduling module and the prediction features of the traffic distribution prediction module. The optimization process of the closed-loop optimization module corrects the model parameters of the traffic distribution prediction module and the task dynamic scheduling execution module in real time. Each step forms a multi-layer closed-loop coupling architecture through data flow and control flow;

[0089] The system operation database includes all data texts of an automated production line monitoring and control management system and collects information texts output by each module in real time. The system central processing module is used for the information text instructions output by each module in the central control system. The user information terminal is an information output device that receives an automated production line monitoring and control management system.

[0090] It should be noted that the central processor of the system is the core computing and control unit of an automated production line monitoring, control and management system; it includes one or more processing cores, which are connected to various parts within the entire system through various interfaces and lines; by running or executing instructions, programs, code sets or instruction sets stored in the system operation database, and being able to call the data stored therein, thus performing various functions of an automated production line monitoring, control and management system, including operations such as topology dynamic parsing algorithms, resource gap prediction models, and low-latency task migration instruction sets, to ensure dynamic reconstruction of virtualized resource topologies based on the load status of edge nodes, establishment and removal of encrypted tunnels for cross-node task migration, and triggering of real-time synchronization and reverse control of digital twins.

[0091] Among them, the communication bus 302 is used to achieve connection and communication between components.

[0092] Among them, the system operation database 303 is used to store a large amount of data related to the monitoring, control and management of an automated production line, including data related to mathematical models established based on spatio-temporal neural networks, deep reinforcement learning decision models, and digital twins, and store a large amount of historical operation data, including differential compression feature dictionaries of task migration, mapping relationships between various priority tags and resource allocation weights, and edge node logs; when the central processor of the system executes various functions, it will frequently call these data from the system operation database, so as to achieve precise control and efficient management of the monitoring, control and management of an automated production line.

[0093] Among them, the user information terminal provides an interface for users to interact with the system by connecting external devices such as a display screen and a camera through standard wired or wireless interfaces.

[0094] Secondly: In the accompanying drawings of the disclosed embodiments of the present invention, only the structures related to the disclosed embodiments are involved, and other structures can refer to the general design. Without conflict, the same embodiment and different embodiments of the present invention can be combined with each other;

[0095] Finally: The above is only the preferred embodiment of the present invention and is not used to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. An automated production line monitoring, control and management method, characterized in that Including: S1: Real-time capture the physical connection status and location coordinate information of each device in the target production pipeline, and generate topological vector data representing the topological structure of the target pipeline; S2: Based on the topological vector data and historical data, use a prediction model to calculate the traffic distribution within a preset time period; S3: According to the traffic distribution and the load status of the target edge nodes, calculate the resource gap values of each edge node within the preset time period, where the resource gap values include computing resource requirements and network bandwidth requirements; S4: Dynamically adjust the resource instance configuration allocated to each edge node according to the resource gap values; S5: Use a decision model to generate a task allocation plan and perform task scheduling based on the task allocation plan; S6: Execute a continuous optimization loop, and the loop at least includes: Monitor the resource utilization rate of each edge node, recycle idle resources and use them to update the calculation of the resource gap values; Update the prediction model and the decision model based on the synchronization of model parameters among edge nodes.

2. The monitoring and control management method of an automated production line according to claim 1, wherein: In S1, the topological vector data includes: Real-time scan the device space coordinates through sensors pre-deployed on the production pipeline, and construct a three-dimensional topological model based on the point cloud registration algorithm; And adopt a sliding window mechanism to calculate the device displacement. When the displacement variance in consecutive N sampling periods exceeds a preset threshold, trigger a topological update event and generate an incremental topological change vector, where N is a positive integer dynamically adjusted according to the production beat, and the incremental topological change vector is used to update the topological vector data in real time.

3. An automated production line monitoring, control and management method according to claim 1, characterized in that: In S2, the prediction model is a spatio-temporal neural network; The prediction model receives the device connection relationship and spatial position information in the topological vector data, and outputs a traffic distribution with a confidence evaluation value; The confidence evaluation value is used to dynamically adjust the weight of the calculation of the resource gap values.

4. An automated production line monitoring and control management method according to claim 1, characterized in that: In S3, a two-layer programming algorithm is used to calculate the resource gap values of each edge node within the preset time period. The upper layer programming determines the computing resource demand ratio, and the lower layer programming solves the network bandwidth constraint conditions to obtain a multi-objective optimization solution that coordinates computing and network resources as the resource gap values.

5. An automated production line monitoring, control and management method according to claim 1, characterized in that: In S5, performing task scheduling includes: The input information of the decision model is configured as the real-time updated topological vector data, the predicted traffic distribution, and the real-time load status and available resource information of each edge node; Based on the input information, generate the task allocation plan by optimizing one or more objective functions, and the objective functions are used to jointly optimize at least two of the following: minimizing the end-to-end processing delay of tasks, maximizing the load balancing degree among edge nodes, and maximizing the overall resource utilization rate of the system; The task allocation plan is used to specify the allocation and migration paths of tasks among edge nodes to actively direct the computing load from high-load nodes to low-load nodes.

6. The automated production line monitoring and control management method according to claim 5, characterized in that: In S5, performing task scheduling further includes: Deploy a task processing queue with multi-dimensional priority tags at the target edge node, and the multi-dimensional priority tags are determined at least based on task urgency and migration efficiency; And when it is detected that the depth of the task processing queue exceeds the threshold, specific tasks are preferentially migrated to other nodes according to the multi-dimensional priority tags.

7. An automated production line monitoring, control and management system, comprising a system operation database, a system central processing module, and a user information terminal. According to the method for monitoring, controlling and managing an automated production line described in any one of claims 1-6 above, it is characterized in that, It further includes: Dynamic topology structure acquisition module: capturing in real time the physical connection status and position coordinate information of each device in the target production pipeline, and generating topology vector data representing the topology structure of the target pipeline; Traffic distribution prediction module: calculating the traffic distribution within a preset time period by using a prediction model based on the topology vector data and historical data; Resource demand assessment module: calculating the resource gap values of each edge node within the preset time period according to the traffic distribution and the load status of the target edge node, where the resource gap values include computing resource requirements and network bandwidth requirements; Collaborative scheduling module: dynamically adjusting the resource instance configuration allocated to each edge node according to the resource gap values; Task dynamic scheduling execution module: generating a task allocation plan by using a decision model and performing task scheduling based on the task allocation plan; Closed-loop optimization module: executing a continuous optimization loop, where the loop at least includes: Monitoring the resource utilization rate of each edge node, recycling idle resources and using them to update the calculation of the resource gap values; Updating the prediction model and the decision model based on the synchronization of model parameters among edge nodes; The system operation database includes all data texts of an automated production line monitoring and control management system, and real-time collects the information texts output by each module. The system central processing module is used for the information text instructions output by each module in the central control system, and the user information terminal is an information output device for receiving an automated production line monitoring and control management system.

8. An automated production line monitoring and control management system according to claim 7, characterized in that: The closed-loop optimization module, updating the prediction model and the decision model based on the synchronization of model parameters among edge nodes includes: Constructing a federated learning architecture among edge nodes, and updating the global model parameters by adopting a parameter aggregation strategy based on model contribution degree according to the scheduling decisions or local data training results of each edge node.

Images