A control method and system for garment hanging production line based on potential energy field propagation

Abstract

This application relates to the field of intelligent garment manufacturing, specifically to a control method and system for a garment hanging production line based on potential energy field propagation. First, a control method for a garment hanging production line based on potential energy field propagation is proposed, including: simulating the garment hanging production line as a network topology model, which includes nodes representing physical entities; obtaining the order insertion information of the order insertion task and the current average potential energy of the garment hanging production line; calculating the initial potential energy of the order insertion based on the order insertion information, wherein the initial potential energy of the order insertion is higher than the average potential energy; obtaining the current potential energy P(v,t) of the order insertion based on the initial potential energy of the order insertion; and determining the current potential energy P(v,t) based on the current potential energy P(v,t) and at least one current potential energy P... w The system controls the direction of movement of the insertion task. Secondly, based on the above, a garment hanging production line control system based on potential energy field propagation is proposed.

Description

Technical Field

[0001] This invention relates to the field of intelligent garment manufacturing, and in particular to a control method and system for garment hanging production lines based on the propagation of potential energy fields. Background Technology

[0002] Suspended production lines, as a highly efficient form of material handling and production organization, significantly improve production efficiency and management level by enabling continuous and automated flow of workpieces (semi-finished garments) between different workstations, and are widely used in the garment manufacturing industry. Existing suspended production line scheduling and control generally employs centralized or distributed control. Centralized control uses a central control system to collect all global data from the production line for global configuration and scheduling; distributed control deploys independent decision-making logic at each sorting node or workstation on the production line, utilizing local information for node control. Both methods demonstrate good performance when handling static or quasi-static scenarios where production plans are relatively stable and change infrequently.

[0003] However, both centralized and distributed solutions exhibit significant drawbacks when production lines experience disruptions (such as the insertion of an urgent task). A central system's global rescheduling, involving large-scale adjustments to all work-in-process and subsequent tasks, can lead to drastic changes in production rhythm. Similarly, simple priority preemption or path selection among distributed nodes can cause rapid shifts in order flow in localized areas. These strategies often disrupt the existing steady state of the production line, resulting in significant fluctuations in production efficiency and product quality.

[0004] Therefore, how to avoid disrupting the existing steady state and reduce fluctuations in production efficiency and product quality when disturbances occur in the production line is a technical problem that urgently needs to be solved in the process control of current garment hanging production lines. Summary of the Invention

[0005] This application first proposes a control method for a garment hanging production line based on potential energy field propagation to solve the aforementioned problems. Secondly, it proposes a control system for the garment hanging production line based on potential energy field propagation. Finally, it proposes a computer device.

[0006] As the first aspect of this application, a control method for a garment hanging production line based on potential energy field propagation is proposed, including, The garment hanging production line is simulated as a network topology model, which includes nodes representing physical entities; Determine the production task potential energy for each of the physical entity nodes that is currently producing, and calculate the average potential energy of the multiple production task potential energies. Obtain the insertion information of the insertion task and the current average potential energy of the garment hanging production line; calculate the initial potential energy of the insertion based on the insertion information, and the initial potential energy of the insertion is higher than the average potential energy. Based on the initial potential energy of the insertion node, the current potential energy P(v,t) of the insertion node is obtained, where the current potential energy P(v,t) of the insertion node is the potential energy of node v at time t. Get the current potential energy P of node w w The node w is the node of the next process of the insertion task, and the current potential energy P w This refers to the potential energy of the insertion task at node w, based on the current potential energy P(v,t) of the insertion task and at least one of the current potential energies P. w Control the direction of travel of the inserted task.

[0007] Optionally, the physical entity includes at least one of a cutting station, a sewing station, a quality inspection station, a packaging station, and various material sorting ports.

[0008] Optionally, the nodes of the physical entities are connected by a suspended path, which is represented by an edge E(u, v) and is assigned a weight d(u, v), which represents at least one piece of information: the physical distance from node u to node v, the standard travel time, and the default transmission delay.

[0009] Optionally, the formula for calculating the initial potential energy of the insertion single unit is: P new (0) = α * urgency + β * customer value + γ * delivery time urgency; Wherein, α, β, and γ are the weights of preset urgency, customer value, and delivery time urgency, respectively.

[0010] Optionally, the formula for calculating the current potential energy P(v,t) of the inserted single unit is: Where P(v, t-Δt) is the potential energy of node v at the previous time t-Δt; P(u, t-Δt) is the potential energy of neighbor node u at the previous time t-Δt; N(v) is the set of neighbor nodes of node v; d(u, v) is the path distance metric from node u to node v; η is the attenuation coefficient, which takes values ​​in the range (0, 1); and δ is the propagation coefficient, which takes values ​​in the range (0, 1).

[0011] Optionally, based on the circulation value A of the optional path w Controlling the direction of the insertion task, the flow value A w The calculation formula is: Among them, (P)w -P v R(Q) represents the potential energy difference between the next process node w and the current node v; d(v, w) represents the path distance from node v to node w; w Let be the flow resistance function, so that the real-time queue length Q of node w is... w This is mapped to a resistance value.

[0012] Optionally, the potential energy field can be visualized as a heat map, which is used to show the priority distribution of different areas on the production line and the dynamic trend of order flow.

[0013] Optionally, the above method further includes receiving real-time feedback information from various parts of the production line and updating the potential energy field based on the feedback information; The feedback information includes at least one of the following: the current location of the order, the completion status of the workstation, and equipment failure information.

[0014] As a second aspect of this application, a garment hanging production line control system based on potential energy field propagation is proposed according to the above method, comprising: The potential energy injection unit is used to acquire insertion information and calculate the initial potential energy of the insertion, wherein the initial potential energy of the insertion is higher than the average potential energy of the current production line. The potential energy field calculation unit is used to calculate the current potential energy P(v,t) of node v, where P(v,t) is the potential energy of node v at time t. The node control unit is used to combine the current potential energy P(v,t) of the insertion node with the current potential energy P of the next node w of each optional path in the next process. w Control the direction of travel of the inserted task.

[0015] As a third aspect of this application, a computer device is proposed according to the above method, the computer device storing computer-executable instructions for causing the computer to execute the above-described control method for a garment hanging production line based on potential energy field propagation.

[0016] The beneficial effects of this application are as follows: 1. By simulating a garment hanging production line as a network topology model and constructing a potential energy field, and utilizing the injection of high-potential-energy order insertion tasks and their propagation and attenuation within the production line network, this method solves key problems such as slow response and poor global coordination in existing technologies when dealing with dynamic disturbances such as emergency order insertions. It achieves global self-organizing optimization of the order flow on the production line. This method enables upstream nodes to proactively "sense" the existence of downstream emergency orders, avoiding or adjusting them, achieving global collaborative optimization and smooth disturbance absorption. This significantly reduces the volatility of the production cycle and improves the stability of the production process.

[0017] 2. By defining physical entities as nodes and hanging paths as weighted edges, an accurate network topology model was constructed, providing an accurate physical basis for the propagation and calculation of the potential energy field, enabling the control logic to truly reflect the actual layout and transmission characteristics of the production line.

[0018] 3. By introducing business attributes such as urgency, customer value, and delivery time urgency to calculate the initial potential energy of order insertion, the quantitative assessment of order priority is realized, ensuring that high-priority orders can drive subsequent routing decisions with a higher-than-average potential energy, guiding the rapid flow of orders.

[0019] 4. By calculating the formula for the current potential energy P(v,t) of the inserted order, the natural evolution process of energy in the physical system is simulated, so that the high potential energy spreads smoothly like ripples. This smooth propagation mechanism avoids the violent fluctuations caused by sudden events in the traditional scheduling method and ensures the steady-state operation of the production line to the greatest extent.

[0020] 5. Through circulation value The calculation introduces a flow resistance function to simulate the increase in resistance when the node queue is too long, realizing a negative feedback mechanism, effectively avoiding local congestion, ensuring that orders can dynamically select the optimal path, and improving the robustness of the system.

[0021] 6. The potential energy field is transformed into a visualized heat map, which intuitively shows the priority distribution and order flow trend of each area on the production line. This enhances the interpretability of the system, makes it easier for managers to intuitively understand the production status and intervene, and improves management efficiency.

[0022] 7. By updating the potential energy field through real-time feedback information, the system can respond instantly to dynamic changes such as order location, workstation status, and equipment failure, ensuring the real-time performance and accuracy of control. Attached Figure Description

[0023] Figure 1 This is a flowchart illustrating a control method for a garment hanging production line based on potential energy field propagation, as described in this embodiment.

[0024] Figure 2 This is a schematic diagram of the structure of a garment hanging production line control system based on potential energy field propagation in one embodiment.

[0025] Figure 3 This is a schematic diagram of the structure of a computer device provided in an embodiment.

[0026] in: 10. Processor; 20. Memory; 30. Input device; 40. Output device. Detailed Implementation

[0027] The present application will be further described in detail below with reference to the accompanying drawings.

[0028] As the first aspect of this specific embodiment, such as Figure 1 The flowchart illustrates a control method for a garment hanging production line based on potential energy field propagation, comprising: The garment hanging production line is simulated as a network topology model, which includes nodes representing physical entities; Determine the production task potential energy for each of the physical entity nodes that is currently producing, and calculate the average potential energy of the multiple production task potential energies. Obtain the insertion information of the insertion task and the average potential energy, calculate the initial potential energy of the insertion based on the insertion information, and the initial potential energy of the insertion is higher than the average potential energy; Based on the initial potential energy of the insertion node, the current potential energy P(v,t) of the insertion node is obtained, where the current potential energy P(v,t) of the insertion node is the potential energy of node v at time t. Get the current potential energy P of node w w The node w is the node of the next process of the insertion task, and the current potential energy P w This refers to the potential energy of the insertion task at node w, based on the current potential energy P(v,t) of the insertion task and at least one of the current potential energies P. w Control the direction of travel of the inserted task.

[0029] By abstracting the network topology model of a garment hanging production line as a dynamic "potential energy field," and utilizing the injection of high-potential energy (typically representing urgent orders) and its propagation and attenuation within the production line network, global self-organizing optimization of the order flow on the production line is achieved. This solves the problems of slow response, poor global coordination, and crude disturbance absorption faced by existing technologies when dealing with dynamic disturbances such as urgent order insertions. This method breaks through the traditional scheduling paradigm, integrating field theory concepts from physics with engineering control ideas to construct a virtual system that can simulate the characteristics of physical fields. This virtual system is then combined with the physical entity of the production line to achieve refined and adaptive control of the production flow. In this way, the production line can respond quickly, adaptively, and smoothly to dynamic disturbances such as urgent order insertions, ensuring both keen perception and effective transmission of disturbances while avoiding drastic impacts on the steady state of production, thus achieving a globally optimal production flow in a dynamically changing environment.

[0030] The potential energy field consists of the production task potential energy, the initial potential energy of the inserted order, and the current potential energy. As a global and continuous information medium, the potential energy field smoothly transmits the demand information of high-priority orders to upstream nodes of the production line in the form of a "field." This information transmission mechanism allows upstream workstations to "sense" the existence of downstream urgent orders in advance, thus proactively avoiding, diverting, or adjusting their routing direction, achieving global collaborative optimization. This propagation method allows high potential energy (representing urgent order demand) to spread smoothly along the production line network like ripples, gradually attenuating with distance and time, simulating the natural evolution of energy in a physical system. This smooth propagation mechanism avoids the drastic fluctuations caused by sudden events in traditional scheduling methods.

[0031] It should be noted that the concept of "potential energy" described in this application does not refer to physical electric potential energy or gravitational potential energy, but rather to an abstract, virtual metric used to quantify order priority and urgency. It follows the basic laws of physical field propagation, but its specific values ​​and evolution rules are defined by business logic and engineering models. This abstraction allows complex production scheduling problems to be transformed into a more intuitive and manageable physical field evolution problem, thereby achieving efficient adaptive flow control.

[0032] Regarding the network topology model for simulating a garment hanging production line, the network topology model is a directed weighted graph G=(V,E), where nodes V represent physical entities on the production line. In some implementations, physical entities include at least one of cutting stations, sewing stations, quality inspection stations, packaging stations, and various material sorting ports. Edges E represent hanging paths connecting these nodes, such as hanging tracks from sewing station A to quality inspection station B. Each edge E(u,v) is assigned a weight d(u,v) for subsequent potential gradient normalization. This weight encodes at least one piece of information, including the physical distance from node u to node v, standard travel time, and default transmission delay. The assignment method for each edge E(u,v) typically employs a min-max normalization method, linearly mapping the distance values ​​to the [0,1] interval. The specific implementation of this method is well known to those skilled in the art and will not be elaborated here. The physical distance is obtained from the factory's overhead crane system layout drawings or can be measured directly. The standard travel time is read from the process configuration database of the Production Management Information System (MES). The default transmission delay is based on the average transmission time of the path, taken from historical data. It should be noted that in subsequent implementations, d(u, v) refers to the weights encoding the physical distance from node u to node v, as shown later. The calculation refers to the weights that encode the physical distance from node u to node v.

[0033] By defining physical entities as nodes and hanging paths as weighted edges, an accurate network topology model is constructed, providing an accurate physical basis for the propagation and calculation of the potential energy field, enabling the control logic to truly reflect the actual layout and transmission characteristics of the production line.

[0034] Define a production task potential P that dynamically decays over time for each order i being produced in the garment hanging production line. i (t), production task potential energy P i (t) represents the potential energy of the production tasks distributed across the physical entity nodes in the network topology model. Its initial value is P. i (0) Determined by preset business rules, P i (0) = α1 * urgency + β1 * order value, where α1 and β1 are business parameters for preset urgency and customer value, respectively, used to weigh the impact of urgency and order value on the initial potential of production tasks. The values ​​of α1 and β1 are between 0 and 1.

[0035] When an urgent order is placed, the initial potential value P for that order is set based on its business attributes (such as urgency, customer value, delivery time requirements, etc.). new (0), P new (0) is designed to be higher than the average potential energy level on the current production line so that this urgent order can enter the system with high priority and be processed first. Specifically, P can be calculated using a weighted summation method. new (0) = α * Urgency + β * Customer Value + γ * Delivery Time Urgency. Urgency typically indicates the extent of impact / loss if not addressed, and can be scored from 1 to 10. In a specific implementation: VIP urgent orders or overdue orders correspond to 10 points; regular urgent orders correspond to 8 points; standard orders correspond to 5 points; inventory replenishment corresponds to 3 points; and pre-production or stock preparation corresponds to 1 point. Customer value is determined based on customer level, historical contribution, strategic significance, etc., as defined by the marketing department. In a specific implementation: strategic partners or VIP customers correspond to 10 points; long-term partners or customers with ≥50 orders per year correspond to 8 points; ordinary members or existing customers correspond to 5 points; new customers correspond to 3 points; and individual or one-time customers correspond to 1 point. The urgency of delivery can be defined as the remaining time until the delivery date. In a specific implementation: when the remaining time until the delivery date is less than or equal to 1 day, the urgency score is 10; when the remaining time until the delivery date is 1-2 days (inclusive), the urgency score is 8; when the remaining time until the delivery date is 3-5 days, the urgency score is 5; when the remaining time until the delivery date is more than 5 days, the urgency score is 3; when the remaining time until the delivery date is not specified, the urgency score is 1.

[0036] α, β, and γ are business parameters for preset urgency, customer value, and delivery time urgency, respectively, used to adjust the weight of different business attributes in potential energy calculation. The values ​​of α, β, and γ range from 0 to 1.

[0037] Then the initial potential energy P of this insertion was... new (0) The starting node injected into the corresponding production line network topology model marks the entry of an emergency order. The starting node is determined according to the process route of the order insertion task. It usually refers to the first station (process) node that the task needs to pass through in the network topology model, such as the cutting station or the first sewing station.

[0038] Average potential energy refers to the potential energy P of each production task at each node of each physical entity in the garment hanging production line under the current state. i The average value of (t).

[0039] By introducing business attributes such as urgency, customer value, and delivery time urgency to calculate the initial potential energy of order insertion, the quantitative assessment of order priority is realized, ensuring that high-priority orders can drive subsequent routing decisions with a higher-than-average potential energy, guiding the rapid flow of orders.

[0040] In some implementations, a highly engineered simplified model is used to describe the propagation and decay of potential energy. A propagation model is constructed, incorporating decay and propagation coefficients to control the degree of decay and diffusion rate of potential energy along the network, thereby simulating how potential energy propagates between network nodes and dissipates naturally over time.

[0041] The formula for calculating the current potential energy P(v,t) of the insertion unit is as follows: Where P(v, t-Δt) is the potential energy of node v at the previous time t-Δt; P(u, t-Δt) is the potential energy of the neighbor node u at the previous time t-Δt; η is a decay coefficient with a value range of (0, 1). It simulates the physical process of potential energy naturally dissipating over time; for example, the priority of an urgent order gradually decreases over time, or its impact on other areas of the production line gradually weakens. δ is the propagation coefficient, which also takes values ​​in the range (0, 1). It controls the speed and intensity of potential energy diffusion along the network, reflecting the efficiency of information or influence transmission in the production line; N(v) is the set of neighboring nodes of node v, that is, all upstream nodes directly connected to node v; d(u, v) is the path distance metric from node u to node v, used to standardize the potential gradient.

[0042] The advantage of the above calculation method lies in its minimal computational load. It typically only needs to be performed within a local subgraph affected by the newly injected high potential energy, eliminating the need for global, high-precision numerical simulation of the entire production line network, thus ensuring real-time performance. In this implementation, a potential energy propagation and attenuation calculation is performed once upon receiving an order injection. In other implementations, the calculation can be performed periodically. Of course, other critical events, such as order completion or workstation equipment failure, will also trigger the calculation.

[0043] It should be noted that the current potential energy P(v, t) of the insertion task is the potential energy at node v and time t, obtained based on the initial potential energy. When the insertion task moves from the initial node to the next node, the parameters of the initial potential energy are directly used to calculate the current potential energy. When the insertion task reaches a subsequent node, and the previous node is not the initial node, since the source of the node is the initial node, the current potential energy P(v, t) is obtained indirectly using the initial potential energy.

[0044] By calculating the formula for the current potential energy P(v,t) of the insertion order, the natural evolution process of energy in the physical system is simulated, so that the high potential energy spreads smoothly like ripples. This smooth propagation mechanism avoids the violent fluctuations caused by sudden events in traditional scheduling methods and ensures the steady-state operation of the production line to the greatest extent.

[0045] In one embodiment, node control units are deployed at each branch or junction of the production line. These node control units are physical execution units that implement local decisions; they can be distributed and lightweight decision-making units with real-time sensing and processing capabilities. Each node control unit can acquire the potential energy value P carried by the currently processed order in real time. order The current potential energy P of the next node w on each optional path to the next process. w ; and the real-time queue length Q of the next node w. w This information is used to make decisions about the route.

[0046] In some implementations, when a garment (representing an order) arrives at a sorting node v, the node's control unit evaluates all possible edges for the next process in real time. This refers to the next node w that can be reached from the current node v. For each optional edge, a flow value A is calculated. w This value takes into account both the potential energy gradient and the flow resistance, and the flow value A is chosen. w The optimal path, serving as the direction of order movement, is defined as follows: Among them, (P) w -Pv The potential difference between the next process node w and the current node v is represented by the local potential gradient. d(v, w) is the path distance from node v to node w, which is used to standardize the potential gradient to prevent nodes that are too far apart from being over-biased due to a slightly larger potential difference, thus introducing unnecessary long-distance detours. (P w -P v Dividing d(v, w) by d(v, w) yields the potential energy gradient per unit distance, which actually characterizes the intensity of the change in potential energy along the path and is a dimensionless parameter. R(Q w ) is the flow resistance function, which measures the real-time queue length Q of the next node w. w This is mapped to a monotonically increasing resistance value. Real-time queue length Q w Specifically, it refers to the queuing status of the next node w, used to quantify the congestion level or load state of node w. In some implementations, a linear function R(Q) is used. w )=k1×Q w +k0, where k1 is the drag coefficient and k0 is the reference drag. The queue length has been mapped to a dimensionless drag value with the same dimension as the potential energy gradient.

[0047] The above function simulates the increased resistance to order flow when the queue at the next node becomes too long, thus implementing a negative feedback mechanism to avoid local congestion. The decision rule is to select the flow value A. w The longest path is used as the order's direction of travel. This decision-making mechanism, based on local information and overall situational awareness, ensures that orders can dynamically select the optimal path.

[0048] In some implementations, the potential energy field is visualized as a heat map, which is used to show the priority distribution of different areas on the production line and the dynamic trends of order flow.

[0049] Heat maps visually display the priority distribution of different areas on the production line and the dynamic trends of order flow, enabling managers to clearly understand the production status and potential bottlenecks. In some implementations, managers can intervene in production scheduling in a highly intuitive and physically intuitive way by adjusting virtual potential energy, injecting at least one of the following parameters: intensity, propagation coefficient, or resistance. This achieves intelligent manufacturing management through human-machine collaboration. This "what you see is what you get" control method greatly enhances the system's usability and controllability, and improves management efficiency.

[0050] In one embodiment, factors such as equipment utilization, worker workload balancing, production costs, and product quality can be incorporated into the calculation of the potential energy field or process decision-making to achieve multi-factor optimization. Specifically, cost- or quality-related factors can be added to the calculation of the initial potential energy P0. In other embodiments, the circulating value A can be included. w The calculation incorporates a penalty term related to equipment utilization rate to guide order flow to less utilized equipment, thereby achieving load balancing. Furthermore, a multi-objective decision-making algorithm can be employed, combining potential energy gradient and flow resistance with other objective functions for comprehensive evaluation to select the optimal process path. This setup improves the robustness of the control results.

[0051] In some embodiments, the above method further includes receiving real-time feedback information from various parts of the production line, receiving real-time status information automatically reported by sensors and the MES system from various parts of the production line, and updating the potential energy field based on the feedback information. The feedback information includes at least one of the following: the current location of the order, the completion status of the workstation, and equipment fault information. The potential energy field of the nodes in the network is updated based on the aforementioned real-time feedback information. Simultaneously, the queue length Q can also be monitored in real time. w The change in Q, and thus the dynamic adjustment of the flow resistance function R(Q) w This creates a closed-loop feedback mechanism, enabling the system to adjust its routing strategy in real time to respond to dynamic changes on the production line.

[0052] By updating the potential energy field with real-time feedback information, the system can respond instantly to dynamic changes such as order location, workstation status, and equipment failure, ensuring the real-time performance and accuracy of control.

[0053] The solutions provided by the above embodiments can construct an adaptive and stable flow control system for garment hanging production lines, thereby significantly improving production efficiency and response speed when dealing with order insertions. The adaptive flow control system for garment hanging production lines based on potential energy field propagation proposed in this application can solve the specific technical problems faced by current garment hanging production lines in handling dynamic disturbances such as emergency order insertions.

[0054] As a second aspect of this specific embodiment, such as Figure 2 As shown, a garment hanging production line control system based on potential energy field propagation is proposed according to the above method, including: The potential energy injection unit is used to acquire insertion information and calculate the initial potential energy of the insertion, wherein the initial potential energy of the insertion is higher than the average potential energy of the current production line. The potential energy field calculation unit is used to calculate the current potential energy P(v,t) of node v, where P(v,t) is the potential energy of node v at time t. The node control unit is used to combine the current potential energy P(v,t) of the insertion node with the current potential energy P of the next node w of each optional path in the next process. w Control the direction of travel of the inserted task.

[0055] The potential energy injection unit is the starting point of the entire system, deployed at the interface layer of the Production Management Information System (MES), and is responsible for receiving urgent order insertion events from the Order Management System (OMS). Upon receiving a new urgent order insertion event, the potential energy injection unit calculates an initial "priority potential energy" value P0 based on the order's business attributes. This initial potential energy value is designed to be significantly higher than the average potential energy level on the current production line to ensure it can effectively drive subsequent routing decisions and guide the rapid flow of orders. The potential energy injection unit then injects this high potential energy into the starting node of its corresponding production line network topology model, marking the entry of the urgent order.

[0056] The potential energy field calculation unit is a core computational unit responsible for maintaining the network topology model of the entire overhead crane production line. This model is a directed weighted graph G=(V,E), where nodes V represent physical entities on the production line, and edges E represent the overhead crane paths connecting these nodes. The potential energy field calculation unit periodically performs potential energy propagation and decay calculations, or triggers calculations upon receiving critical events (such as new order injection, order completion, or changes in workstation status). Its core task is to simulate how potential energy propagates between network nodes and dissipates naturally over time. Typically, this calculation only needs to be performed within a local subgraph affected by newly injected high potential energy, eliminating the need for global, high-precision numerical simulations of the entire production line network. This reduces computational load, lowers system hardware requirements, and lowers costs while ensuring real-time performance.

[0057] Node control units are deployed at various branching or confluence points of the production line, and can be distributed. They are lightweight decision-making units that enable local decision-making, possessing real-time sensing and processing capabilities. Each node control unit can acquire the following key information in real time: the potential energy value P carried by the order currently being processed. order The current potential energy P of the next node w on each optional path to the next process. w ; and the real-time queue length Q of the next node w. w This information forms the basis for routing decisions.

[0058] In one embodiment, the control system further includes a data transmission unit. This unit is responsible for efficiently and with low latency synchronizing the latest node potential energy values ​​calculated by the potential energy field calculation unit, as well as real-time queue status information from each node control unit, to all relevant node control units. Simultaneously, the data transmission unit is also responsible for collecting feedback information such as order completion and status changes from the node control units and transmitting it to the potential energy field calculation unit, forming a dynamic closed-loop control system. To ensure the real-time performance and reliability of data transmission, the data transmission unit is implemented through a data bus. The data bus can employ low-latency, high-throughput communication protocols such as Industrial Ethernet and MQTT from the communications field.

[0059] To ensure low latency, high throughput, and high reliability of the data transmission unit under massive order flow and high frequency status updates, a distributed message queue (such as Kafka) or an in-memory database (such as Redis) can be used as the core component of the data transmission unit. Kafka can be used for high-throughput order status streaming transmission scenarios, while Redis can be implemented in low-latency real-time read and write scenarios of potential values.

[0060] The node control unit can serve as an edge computing unit, performing data preprocessing and routing decisions locally, reducing reliance on a central server and lowering communication latency. The potential energy field calculation unit can also be deployed on an edge server, enabling computation closer to the data source and further improving real-time performance. To ensure data consistency and timely decision-making, efficient data synchronization and conflict resolution mechanisms need to be designed.

[0061] In one embodiment, the control system also includes a display unit for showing a heat map reflecting the priority distribution and dynamic trends of order flow in different areas of the production line. Managers can interact with the graphical interface on the display unit (by clicking or swiping) to intuitively adjust virtual "potential energy" injection intensity, propagation coefficient, or resistance parameters, intervening in production scheduling in a highly intuitive and physically intuitive way. This "what you see is what you get" control method greatly enhances the system's usability and controllability, realizing intelligent manufacturing management through human-machine collaboration.

[0062] Through the above implementation methods, this invention achieves a high response speed. The potential energy injection unit only needs to perform simple business attribute calculations and potential energy injection operations. The computational load of the potential energy field calculation unit is minimal, and it typically operates within the affected local subgraph, avoiding complex global calculations. The node control unit makes routing decisions based on local sensor data and simple mathematical operations. The entire decision-making process can be completed in milliseconds, and the response latency can typically be reduced to less than 100 milliseconds. This contrasts sharply with the minute-level response latency of existing centralized scheduling systems, enabling the system to respond instantly to urgent order insertion requests and ensuring that high-priority orders can quickly enter the production process.

[0063] As a third aspect of this specific embodiment, a computer device is proposed. For example... Figure 3 The computer device shown includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system).

[0064] like Figure 3 As shown, processor 10 can be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip can be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device can be a complex programmable logic device (CLP), a field-programmable gate array (FPGA), a general-purpose array logic (GPRS), or any combination thereof.

[0065] The memory 20 stores instructions executable by at least one processor 10 to cause the at least one processor 10 to perform the method shown in the above embodiments.

[0066] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0067] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0068] The computer device also includes an input device 30 and an output device 40. The processor 10, memory 20, input device 30, and output device 40 can be connected via a bus or other means.

[0069] Input device 30 can receive input numerical or character information, and generate key signal inputs related to user settings and function control of the computer device, such as a touchscreen, keypad, mouse, trackpad, touchpad, joystick, one or more mouse buttons, trackball, joystick, etc. Output device 40 may include display devices, auxiliary lighting devices (e.g., LEDs), and haptic feedback devices (e.g., vibration motors). The aforementioned display devices include, but are not limited to, liquid crystal displays, light-emitting diodes, displays, and plasma displays. In some alternative embodiments, the display device may be a touchscreen.

[0070] The computer device also includes a communication interface for communicating with other devices or communication networks.

[0071] The methods described above in the computer device according to embodiments of the present invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code originally stored on a remote storage medium or a non-transitory machine-readable storage medium and subsequently stored on a local storage medium after being downloaded via a network. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that the computer, processor, microprocessor controller, or programmable hardware includes storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0072] A portion of this invention can be applied to computer program products, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer device include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer device can be any available computer-readable storage medium or communication medium accessible to a computer.

[0073] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the exemplary embodiments according to this application. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0074] The above description is only a preferred embodiment of this application. All equivalent changes and modifications made within the scope of the patent of this application shall fall within the scope of this application.

Claims

1. A control method for a garment hanging production line based on potential energy field propagation, characterized in that, include: The garment hanging production line is simulated as a network topology model, which includes nodes representing physical entities; Determine the production task potential energy for each of the physical entity nodes that is currently producing, and calculate the average potential energy of the multiple production task potential energies. Obtain the insertion information of the insertion task and the average potential energy, calculate the initial potential energy of the insertion based on the insertion information, and the initial potential energy of the insertion is higher than the average potential energy; Based on the initial potential energy of the insertion node, the current potential energy P(v,t) of the insertion node is obtained, where the current potential energy P(v,t) of the insertion node is the potential energy of node v at time t. Get the current potential energy P of node w w The node w is the node of the next process of the insertion task, and the current potential energy P w This refers to the potential energy of the insertion task at node w, based on the current potential energy P(v,t) of the insertion task and at least one of the current potential energies P. w Control the direction of travel of the inserted task; The nodes of the physical entities are connected by suspended paths, which are represented by edges E(u, v) and are assigned a weight d(u, v). The weight d(u, v) represents at least one piece of information, namely, the physical distance from node u to node v, the standard travel time, and the default transmission delay. The formula for calculating the current potential energy P(v,t) of the inserted single unit is: Where P(v, t-Δt) is the potential energy of node v at the previous time t-Δt; P(u, t-Δt) is the potential energy of neighbor node u at the previous time t-Δt; N(v) is the set of neighbor nodes of node v; d(u, v) is the path distance metric from node u to node v; η is the attenuation coefficient, which takes values ​​in the range (0, 1); and δ is the propagation coefficient, which takes values ​​in the range (0, 1). Circulation value A based on optional paths w Controlling the direction of the insertion task, the flow value A w The calculation formula is: Among them, (P) w -P v R(Q) represents the potential energy difference between the next process node w and the current node v; d(v, w) represents the path distance from node v to node w; w Let be the flow resistance function, so that the real-time queue length Q of node w is... w This is mapped to a resistance value.

2. The control method for garment hanging production line based on potential energy field propagation according to claim 1, characterized in that, The physical entities include at least one of the following: cutting station, sewing station, quality inspection station, packaging station, and various material sorting ports.

3. The control method for garment hanging production line based on potential energy field propagation according to claim 1, characterized in that, The formula for calculating the initial potential energy of the insertion is: P new (0) = α * urgency + β * customer value + γ * delivery time urgency; Wherein, α, β, and γ are the weights of preset urgency, customer value, and delivery time urgency, respectively.

4. The control method for garment hanging production line based on potential energy field propagation according to claim 1, characterized in that, The potential energy field is visualized as a heat map, which is used to show the priority distribution of different areas on the production line and the dynamic trend of order flow.

5. The control method for garment hanging production line based on potential energy field propagation according to claim 1, characterized in that, It also includes receiving real-time feedback information from various parts of the production line and updating the potential energy field based on the feedback information; The feedback information includes at least one of the following: the current location of the order, the completion status of the workstation, and equipment failure information.

6. A garment hanging production line control system based on potential energy field propagation, characterized in that, The method for controlling a garment hanging production line based on potential energy field propagation as described in any one of claims 1 to 5 includes: The potential energy injection unit is used to acquire insertion information and calculate the initial potential energy of the insertion, wherein the initial potential energy of the insertion is higher than the average potential energy of the current production line. The potential energy field calculation unit is used to calculate the current potential energy P(v,t) of node v, where P(v,t) is the potential energy of node v at time t. The node control unit is used to combine the current potential energy P(v,t) of the insertion node with the current potential energy P of the next node w of each optional path in the next process. w Control the direction of travel of the inserted task.

7. A computer device, characterized in that: The computer device stores computer-executable instructions, which are used to cause the computer to execute the garment hanging production line control method based on potential energy field propagation as described in any one of claims 1 to 5.

Images