Intelligent workshop material dynamic pulling control method, system and device

Abstract

The invention provides an intelligent workshop material dynamic pulling control method, system and device, and relates to the technical field of intelligent manufacturing, and the method comprises the steps: firstly, obtaining a basic inventory buffer capacity, an equipment topological graph, production scheduling characteristics, real-time production data and a material warehousing rate of an intelligent workshop; time sequence production features, equipment topological features and production scheduling features are extracted in combination with a multi-modal prediction model, the predicted material consumption rate is output, and the prediction precision is improved; secondly, a real-time inventory water level and a dynamic replenishment threshold value are calculated in combination with a prediction result and equipment operation parameters, production fluctuation and equipment fault risks are dynamically adapted, and inventory overstock or material interruption shutdown caused by a traditional static water level is avoided; and finally, if the real-time stock water level is lower than the dynamic replenishment threshold value, according to the material transportation parameters, constructing a minimum delay path objective function, generating an optimal path, and controlling the automated guided vehicle to execute replenishment, so that timely replenishment is ensured, the stock turnover rate is improved, and the lean level of workshop material management is improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent manufacturing technology, and in particular to a method, system and device for dynamically pulling materials in an intelligent workshop. Background Art

[0002] As manufacturing evolves toward intelligent and lean processes, traditional material management models are no longer able to meet the demands of efficient production. Existing shop floor material management technologies suffer from the following key flaws: First, they employ static inventory levels based on fixed maximum and minimum parameters, making them unable to adapt to fluctuations in production plans or abnormal equipment status, easily leading to inventory backlogs or material shortages and production stoppages. Second, replenishment relies on manual judgment and experience, resulting in delayed responses and a failure to integrate dynamic variables such as equipment status and process failures, leading to untimely or excessive replenishment. Third, they focus on a single dimension, failing to quantify the impact of multiple factors, such as equipment failures and process anomalies, making replenishment strategies disconnected from actual production scenarios. Therefore, data-driven intelligent prediction and dynamic control are urgently needed to address core pain points such as inventory backlogs and material shortages. Summary of the Invention

[0003] The purpose of the present invention is to provide a method, system and device for dynamic pulling control of materials in an intelligent workshop to solve one or more technical problems existing in the prior art and at least provide a beneficial option or create conditions.

[0004] The present invention solves the technical problem as follows: On the one hand, the present invention provides a method for controlling the dynamic pulling of materials in an intelligent workshop, comprising the following steps: Obtain the basic inventory buffer, equipment topology, production scheduling characteristics, real-time production data, and material inflow rate of the smart workshop; the real-time production data includes the current material inventory, equipment operating parameters, and material transportation parameters; the production scheduling characteristics are used to characterize the information of the production tasks and their corresponding product material usage; Utilizing a multimodal prediction model, extracting time-series production features from the real-time production data and extracting equipment topology features from the equipment topology map, and fusing the time-series production features, the equipment topology features, and the production scheduling features through an attention mechanism to output a predicted material consumption rate; Calculate the real-time inventory level and dynamic replenishment threshold based on the predicted material consumption rate, the current material inventory, the material incoming rate, the basic inventory buffer, and the equipment operating parameters; If the real-time inventory level is lower than the dynamic replenishment threshold, a replenishment instruction is generated, and based on the material transportation parameters, a minimum delay path objective function is constructed to generate an optimal path and control the automatic guided vehicle to perform replenishment.

[0005] Furthermore, the equipment topology diagram is used to characterize the process connection and fault propagation weight between the equipment; the equipment topology diagram is constructed based on the production process flow chart, equipment physical layout and historical fault data of the smart workshop; the equipment topology diagram is constructed in a graph structure In the form of Represents a device node, Indicates the process connection relationship between equipment, represents the fault propagation weight between devices, The value of is the probability of cascading impact of equipment failure; Furthermore, the multimodal prediction model includes a long short-term memory network, a graph neural network, and an attention mechanism; The method utilizes a multimodal prediction model to extract time series production features from the real-time production data, extracts equipment topology features from the equipment topology map, and fuses the time series production features, the equipment topology features, and the production scheduling features through an attention mechanism to output a predicted material consumption rate, including the following steps: Extracting the time series production features from the real-time production data using the long short-term memory network; Extracting the device topology features from the device topology graph using the graph neural network; The time series production features, the equipment topology features and the production scheduling features are fused through the attention mechanism to output a predicted material consumption rate.

[0006] Furthermore, the step of calculating the real-time inventory level and dynamic replenishment threshold by combining the predicted material consumption rate, the current material inventory, the material incoming rate, the basic inventory buffer, and the equipment operating parameters includes the following steps: A dynamic risk compensation coefficient is calculated based on the mean time to repair and mean time between failures in the equipment operating parameters; Calculating a dynamic inventory buffer and a dynamic replenishment threshold according to the dynamic risk compensation coefficient and the basic inventory buffer; Calculate the real-time inventory level based on the dynamic inventory buffer, the predicted material consumption rate, the current material inventory, and the material incoming rate; The real-time inventory water level satisfies the following formula: ; in, Indicates the real-time inventory water level; Indicates the current material inventory; Indicates the material entry rate, Indicates the material warehousing time window; represents the predicted material consumption rate, Indicates the material consumption time window; Indicates the dynamic inventory buffer, The product of the dynamic risk compensation coefficient and the basic inventory buffer, wherein the dynamic risk compensation coefficient is calculated based on the mean time to repair and mean time between failures in the equipment operating parameters; The dynamic replenishment threshold satisfies the following formula: ; in, represents the dynamic replenishment threshold, represents the replenishment lead time, represents the mean of the historical material consumption rate, represents the mean time to repair in the equipment operating parameters, Indicates the mean time between failures in the operating parameters of the equipment; Indicates the preset mean time between failures threshold, Indicates the preset mean time to repair threshold.

[0007] Furthermore, the dynamic risk compensation coefficient satisfies the following formula: ; in, represents the dynamic risk compensation coefficient, Indicates the remaining time of the current work order. Represents the process cycle constant; The basic inventory buffer volume satisfies the following formula: ; in, represents the basic inventory buffer amount, Indicates the material breakage tolerance coefficient; represents the replenishment lead time variance; Represents the standard deviation of the historical material consumption rate.

[0008] Furthermore, the minimum delay path objective function satisfies the following formula: ; in, represents the minimum delay path objective function value; Indicates the number of replenishment tasks of the smart workshop; Indicates that the automated guided transport vehicle completes the The time for a replenishment task, Indicates the The deadline for a replenishment task, Indicates the The delay in completing a replenishment task; represents a distance weight coefficient, which is used to adjust the importance of the total travel distance of the automated guided transport vehicle in the minimum delay path objective function value; Indicates the The automated guided vehicle completes the The driving distance of a replenishment task, Indicates the number of the automated guided vehicles; , Indicates the The replenishment task is assigned to The automated guided vehicle performs, Indicates the The replenishment task is not assigned to the The automated guided vehicle is executed.

[0009] Furthermore, the minimum delay path objective function needs to satisfy three constraints, including a first constraint, a second constraint, and a third constraint; The first constraint condition satisfies the following formula: ; in, Indicates the the mission capacity of each of the automated guided vehicles; The second constraint condition satisfies the following formula: ; The second constraint condition indicates that any replenishment task of the smart workshop is only assigned to one of the automated guided vehicles for execution; The third constraint condition satisfies the following formula: ; in, Indicates the The automated guided vehicle begins to execute the The time for a replenishment task; Indicates the The automated guided transport vehicle completes the The time for a replenishment task; Indicates the The location and The distance between the locations of the replenishment tasks; Indicates the The moving speed of each of the automated guided vehicles; Indicates the The number of tasks to be performed by the automated guided vehicle.

[0010] On the other hand, the present invention provides an intelligent workshop material dynamic pulling control system, including a data acquisition module, a material consumption prediction module and a replenishment control module; The data acquisition module is used to obtain the basic inventory buffer, equipment topology, production scheduling characteristics, real-time production data and material inflow rate of the smart workshop; wherein the real-time production data includes the current material inventory, equipment operating parameters and material transportation parameters; the production scheduling characteristics are used to characterize the information of the production task and its corresponding product material usage; The material consumption prediction module is used to use a multimodal prediction model to extract time-series production features from the real-time production data and extract equipment topology features from the equipment topology map, and fuse the time-series production features, the equipment topology features and the production scheduling features through an attention mechanism to output a predicted material consumption rate; The replenishment control module is used to calculate the real-time inventory level and the dynamic replenishment threshold based on the predicted material consumption rate, the current material inventory, the material incoming rate, the basic inventory buffer and the equipment operating parameters; if the real-time inventory level is lower than the dynamic replenishment threshold, a replenishment instruction is generated, and based on the material transportation parameters, a minimum delay path objective function is constructed to generate an optimal path, and the automated guided vehicle is controlled to perform the replenishment.

[0011] On the other hand, the present invention provides a dynamic pulling control device for materials in an intelligent workshop, comprising: an Internet of Things sensing device, an edge computing device, a central decision-making device, and an automatic guided transport vehicle; The IoT sensing device is used to collect real-time production data of the smart workshop; wherein the real-time production data includes current material inventory, equipment operating parameters and material transportation parameters; The edge computing device is deployed with an INT8 quantized multimodal prediction model, and the multimodal prediction model is called through a gRPC interface; The edge computing device is used to obtain the basic inventory buffer, equipment topology map, production scheduling characteristics and material inflow rate of the smart workshop, and use the multimodal prediction model to extract time-series production features from the real-time production data and equipment topology features from the equipment topology map. The time-series production features, equipment topology features and production scheduling features are fused through an attention mechanism to output a predicted material consumption rate; the production scheduling features are used to characterize information about production tasks and their corresponding product material usage; The central decision-making device is used to calculate the real-time inventory level and the dynamic replenishment threshold based on the predicted material consumption rate, the current material inventory, the material incoming rate, the basic inventory buffer and the equipment operating parameters; if the real-time inventory level is lower than the dynamic replenishment threshold, a replenishment instruction is generated, and based on the material transportation parameters, a minimum delay path objective function is constructed to generate an optimal path and control the automatic guided vehicle to perform the replenishment.

[0012] Furthermore, the IoT sensing device includes a line-side warehouse sensing unit, an equipment status sensing unit, and a logistics sensing unit; The line-side warehouse sensing unit is used to obtain the current material inventory; the line-side warehouse sensing unit includes an intelligent material box, and the intelligent material box includes a weighing sensor and an RFID reader; The device status sensing unit is used to collect the device operating parameters; the device status sensing unit is deployed on the production equipment of the smart workshop, and the device status sensing unit includes a vibration sensor and a PLC interface; The logistics perception unit is used to collect the position, speed and carrier capacity of the automatic guided transport vehicle as the material transportation parameters; the logistics perception unit is deployed on the automatic guided transport vehicle, and the logistics perception unit includes a laser radar, a visual SLAM processor and a UWB chip.

[0013] The beneficial effects of the present invention are as follows: the method for dynamic pull control of materials in an intelligent workshop provided by the present invention includes: first, by obtaining the basic inventory buffer, equipment topology, production scheduling characteristics, real-time production data and material warehousing rate of the intelligent workshop, combining the multimodal prediction model to extract the time series production characteristics, equipment topology characteristics and production scheduling characteristics, outputting the predicted material consumption rate, and improving the prediction accuracy; secondly, combining the prediction results with the equipment operating parameters to calculate the real-time inventory water level and the dynamic replenishment threshold, dynamically adapting to production fluctuations and equipment failure risks, and avoiding inventory backlogs or material shortages caused by traditional static water levels; finally, if the real-time inventory water level is lower than the dynamic replenishment threshold, and based on the material transportation parameters, constructing the minimum delay path objective function, generating the optimal path, controlling the automatic guided transport vehicle to perform replenishment, ensuring timely replenishment, improving inventory turnover, and improving the lean level of workshop material management. The present application also provides corresponding devices, systems and vehicles. The beneficial effects of the devices, systems and vehicles are similar to those of the method, so they will not be repeated here.

[0014] Other features and advantages of the present application will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present application. The purposes and other advantages of the present application can be achieved and obtained through the structures particularly pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The accompanying drawings are used to provide a further understanding of the technical solution of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the technical solution of the present invention and do not constitute a limitation to the technical solution of the present invention.

[0016] Figure 1 This is a flow chart of the intelligent workshop material dynamic pulling control method provided by this application; Figure 2 This is the structural diagram of the intelligent workshop material dynamic pulling control system provided by this application; Figure 3 This is a structural diagram of the intelligent workshop material dynamic pulling control device provided in this application. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0018] The present application is further described below in conjunction with the accompanying drawings and specific embodiments. The described embodiments should not be considered as limiting the present application. All other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0019] In the following description, reference is made to “some embodiments”, which describes a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application pertains. The terms used herein are for the purpose of describing the embodiments of this application only and are not intended to limit this application.

[0021] As the manufacturing industry transitions toward intelligent and lean processes, the core objectives of shop floor material management have evolved from ensuring supply to precisely matching demand, reducing inventory costs, and improving production continuity. In both discrete manufacturing (such as automotive parts and consumer electronics) and process manufacturing (such as chemicals and food processing), material management must respond in real time to dynamic factors such as production plan fluctuations, equipment status anomalies, and changes in logistics and transportation. However, traditional material management models, due to technical limitations, struggle to meet these demands. Data-driven intelligent forecasting and dynamic control technologies are urgently needed to address core pain points such as inventory overstock, material shortages, and resource waste.

[0022] Traditional methods use fixed minimum and maximum inventory levels (Min / Max) based on historical average demand. These parameters don't account for temporary adjustments to production plans (such as urgent orders or changes in work order priority) or abnormal fluctuations in equipment status (such as a sudden drop or increase in material consumption due to equipment failure). For example, when a sudden equipment failure halts production, the material consumption rate in the line warehouse decreases, but the static inventory level still triggers replenishment as planned, ultimately leading to inventory backlogs. Conversely, if an urgent work order requires accelerated production, the static inventory level isn't dynamically adjusted upward, which can easily lead to material shortages and production stoppages.

[0023] Secondly, the timing and quantity of replenishment rely on manual judgment (e.g., workers manually placing orders after observing remaining materials in line warehouses), lacking real-time data support. Replenishment quantities are calculated solely based on historical average demand, failing to incorporate dynamic variables such as equipment operating status and process failures (e.g., additional materials required for rework of defective products). For example, when equipment failures extend maintenance time, manual judgment makes it difficult to adjust replenishment strategies in a timely manner. This can lead to material shortages on the production line due to delayed replenishment. Alternatively, because the need for rework of defective products is not considered, replenishment quantities may be insufficient, necessitating a second emergency replenishment, increasing logistics costs.

[0024] Furthermore, traditional methods focus solely on the single dimension of material consumption, failing to quantify the impact of multiple factors, including equipment operating status, logistics, and process anomalies. For example, a failure in equipment A could lead to a material backlog at equipment B. However, traditional methods fail to analyze this impact through equipment topology and continue to replenish equipment B as planned, resulting in inventory redundancy. Alternatively, when automated guided vehicle (AGV) route congestion causes replenishment delays, the route is not dynamically adjusted, further exacerbating the risk of material shortages.

[0025] Therefore, the core problem of existing technologies lies in the static and experience-based management model, which cannot adapt to the needs of the dynamic production environment, resulting in low inventory turnover rate in line warehouses, high proportion of material outage downtime, and a large proportion of stagnant materials, which seriously restricts the production efficiency and cost control of the manufacturing industry.

[0026] In response to the above problems, the embodiments of the present application provide a method, system and device for dynamic pull control of materials in an intelligent workshop. The method obtains the equipment topology map, production scheduling characteristics, real-time production data and the quantity to be stored, and uses a multimodal prediction model that integrates LSTM, GNN and attention mechanism to extract timing, topology and production plan characteristics, and outputs the predicted material consumption rate; combines the equipment operating parameters to calculate the dynamic risk compensation coefficient, and then generates the real-time inventory water level and dynamic replenishment threshold; if the water level is insufficient, calls the minimum delay path objective function to generate the AGV optimal path and control the execution of replenishment. The system adopts the "Internet of Things perception layer-edge computing layer-AI decision layer-execution control layer" architecture, and realizes data collection, preprocessing, prediction and execution through intelligent material boxes, AGV transportation systems and edge computing gateways, effectively reducing line warehouse inventory, reducing material outage and production stoppage time, reducing AGV task response delay, and improving inventory turnover, effectively alleviating the core pain points of traditional material management.

[0027] First, the following will describe in detail the intelligent workshop material dynamic pulling control method provided by the embodiment of the present application with reference to the accompanying drawings. Figure 1 The implementation process of the intelligent workshop material dynamic pulling control method provided by the embodiment of the present application includes but is not limited to the following steps.

[0028] Step S100: Obtain the basic inventory buffer, equipment topology, production scheduling characteristics, real-time production data and material warehousing rate of the smart workshop.

[0029] Among them, real-time production data includes current material inventory, equipment operating parameters and material transportation parameters.

[0030] In step S100, comprehensive collection of multi-dimensional information provides support for subsequent decision-making. The basic inventory buffer is a safety stock benchmark set based on historical production experience and regular demand fluctuations, providing a basic guarantee for coping with unexpected demands in daily production; the equipment topology diagram reflects the process connection relationship and fault propagation risk between the equipment in the workshop, helping to identify the potential impact of equipment abnormalities on material demand; the production scheduling characteristics come from the production planning system, which clarifies the specific needs of the current production tasks and ensures that the material supply is aligned with the production tasks; real-time production data reflects the actual status of the line warehouse, equipment health and material transportation progress in real time; the material warehousing rate records the information of materials that have been issued but not delivered, avoiding duplicate replenishment or insufficient inventory due to omissions. The integration of these data provides a comprehensive and real-time basis for subsequent forecasts and dynamic adjustments.

[0031] In step S200, a multimodal prediction model is used to extract time-series production features from real-time production data and equipment topology features from the equipment topology map. The time-series production features, equipment topology features, and production scheduling features are fused through an attention mechanism to output a predicted material consumption rate.

[0032] In step S200, a multimodal prediction model transforms dispersed production data into forecasts that can guide decision-making. Specifically, the model extracts time-series features from real-time production data that reflect material consumption trends (e.g., recent changes in material consumption rates). It also extracts topological features from the equipment topology map that reflect the impact of equipment anomalies (e.g., how a device failure may cause changes in material demand for associated equipment). Combined with production scheduling characteristics (e.g., the high-priority demand for urgent work orders), these features are dynamically integrated through an attention mechanism to comprehensively determine the material consumption rate over a period of time. This process overcomes the limitations of traditional empirical judgment, making material consumption forecasts more relevant to actual production scenarios and providing a precise demand basis for subsequent dynamic inventory adjustments.

[0033] Step S300 , combining the predicted material consumption rate, current material inventory, material incoming rate, basic inventory buffer and equipment operating parameters, calculates the real-time inventory level and dynamic replenishment threshold.

[0034] In step S300, accurate adjustment of inventory levels is achieved by integrating the forecast results with real-time data. Specific functions include: combining the predicted material consumption rate and the preset time window to calculate the material demand in the future; combining the current inventory (existing materials in the line warehouse) and the amount to be entered (materials in transit) to clarify the total inventory currently available in the line warehouse; and then adjusting the basic inventory buffer through equipment operating parameters (such as equipment failure frequency and maintenance time) to generate a real-time inventory level (i.e., the actual available safety stock). The dynamic replenishment threshold is dynamically set according to the equipment operating status and production demand (such as raising the threshold when the risk of equipment failure is high) to ensure that the inventory can meet production needs while avoiding inventory backlogs caused by excessive replenishment. This process enables inventory management to shift from static response to dynamic adaptation, effectively improving inventory utilization efficiency.

[0035] In step S400, if the real-time inventory level is lower than the dynamic replenishment threshold, a replenishment instruction is generated, and a minimum delay path objective function is constructed based on the material transportation parameters to generate an optimal path and control the automatic guided vehicle to perform the replenishment.

[0036] It should be noted that material transportation parameters include the position, speed and vehicle capacity of the automated guided vehicle.

[0037] In step S400, when the real-time inventory level falls below the dynamic replenishment threshold, the system generates a replenishment instruction and, based on material transportation parameters, constructs a minimum-delay path objective function. Taking into account factors such as task urgency and AGV travel distance, the system generates an optimal replenishment path. Controlling the AGV to execute replenishment along this path not only prioritizes the material needs of urgent work orders (avoiding production halts due to material shortages) but also reduces ineffective AGV travel through route optimization (reducing logistics costs). This step ultimately transforms data predictions and dynamic calculations into actual material transportation actions, ensuring real-time matching of lineside warehouse inventory with production demand, thus ensuring continuous and efficient production.

[0038] In some embodiments of the present application, the equipment topology is used to characterize the process connection and fault propagation weight between the equipment. The equipment topology is constructed based on the production process flow chart of the smart workshop, the physical layout of the equipment, and the historical fault data. The equipment topology is a graph structure. In the form of Represents a device node, Indicates the process connection relationship between equipment, represents the fault propagation weight between devices, The value of is the probability of cascading impact of equipment failure.

[0039] The equipment topology map is a key data foundation for the dynamic pull control of materials in smart workshops. Its core function is to provide an accurate basis for material demand forecasting and replenishment strategy optimization by quantifying the process connections and fault propagation relationships between equipment. Specifically, the equipment topology map is constructed based on the smart workshop's production process flow chart (which clarifies the upstream and downstream process relationships between equipment), the equipment physical layout (which reflects the spatial connections between equipment), and historical fault data (which calculates the probability of cascading impact of equipment failures).

[0040] Device topology diagram with graph structure In the form of Represents equipment nodes, visually identifying each production equipment in the workshop, such as injection molding machines and assembly machines; Indicate the process connection relationship between equipment and clarify the collaboration logic between equipment; represents the fault propagation weight between devices, The value of is the probability of cascading impact of equipment failure. For example, the probability that the failure of equipment A will cause the shutdown of equipment B is 80%. This system quantifies the impact of equipment anomalies on related equipment. Through this structured expression, the system can accurately analyze the potential impact of equipment anomalies (such as failures and repair delays) on material consumption (e.g., downtime of equipment A leading to a material backlog at equipment B, requiring less replenishment to equipment B). This allows for dynamic adjustments to inventory levels and replenishment strategies, avoiding the risks of inventory redundancy and material shortages that arise from traditional methods that ignore equipment connections, effectively improving the predictability and accuracy of material management.

[0041] In some embodiments of the present application, the production scheduling feature is used to characterize the information of the production task and its corresponding product material usage.

[0042] In some embodiments of the present application, the production scheduling features are extracted through a manufacturing execution system (MES) or an enterprise resource planning system (ERP) of a smart workshop.

[0043] Scheduling features extract key production task information through the MES or ERP system, transforming abstract production plans into specific material requirements. This helps ensure accurate material consumption forecasting and dynamic replenishment decisions. Specifically, scheduling features contain core production task information (such as work order priority, planned output, and corresponding product BOM usage). They clearly define key requirements, such as the number of products to be produced, the materials required, and which tasks require priority. By extracting these features, the system can map dynamic changes in production tasks (such as urgent orders and output adjustments) to material management in real time. For example, the high priority feature of urgent work orders increases the weight of their material requirements, ensuring priority replenishment. Product BOM usage features clarify the material quantities required for each product, preventing supply discrepancies caused by BOM mismatches. This process ensures a high degree of alignment between material supply and production tasks, avoiding inventory backlogs and material shortages that can occur with traditional methods due to a disconnect between production planning and material management. This effectively improves the coordination and responsiveness of material management.

[0044] In some embodiments of the present application, the multimodal prediction model includes a long short-term memory network, a graph neural network, and an attention mechanism. In step S200, the multimodal prediction model is used to extract time-series production features from real-time production data and equipment topology features from the equipment topology map. The time-series production features, equipment topology features, and production scheduling features are then integrated using the attention mechanism to output a predicted material consumption rate. The process includes, but is not limited to, the following steps.

[0045] In step S210, a long short-term memory network is used to extract time series production features from real-time production data.

[0046] In step S210, the dynamic patterns of material consumption are captured from the time series information of real-time production data. Real-time production data (such as the change in material weight over time in line warehouses and the time-series fluctuations in equipment vibration values) is time-dependent. Long Short-Term Memory (LSTM), a neural network that excels at processing time-series data, can identify long-term trends (such as a gradual increase in material consumption), short-term fluctuations (such as a surge in consumption caused by a temporary equipment acceleration), or cyclical patterns (such as peak consumption at fixed times of the day). By extracting time-series production features from LSTM, the system can accurately grasp the actual dynamics of recent material consumption, providing a key basis for the time dimension in subsequent forecasts and avoiding the forecast bias caused by traditional methods that ignore time dependencies.

[0047] In step S220 , a graph neural network is used to extract device topology features from the device topology graph.

[0048] In step S220, a graph neural network (GNN) is used to analyze the equipment topology to extract characteristics of the potential impact of equipment anomalies (such as failures and maintenance delays) on the material demand of associated equipment. For example, a failure in equipment A might cause a material backlog at downstream equipment B (because equipment A cannot supply semi-finished products), reducing the material demand of equipment B. Or a failure in equipment C might cause upstream equipment D to accelerate production, increasing the material demand of equipment D. These topological characteristics provide key information about the equipment-related dimensions for predicting material consumption rates, enabling the system to proactively predict the impact of equipment anomalies on material demand.

[0049] In step S230, the time series production features, equipment topology features, and production scheduling features are integrated through the attention mechanism to output the predicted material consumption rate.

[0050] In step S230, multi-dimensional features are dynamically integrated to generate prediction results tailored to actual production scenarios. Time-series production features reflect the temporal trend of material consumption (e.g., recent acceleration of consumption), equipment topology features reflect the potential impact of equipment anomalies (e.g., a failure in equipment A may reduce the material demand for equipment B), and scheduling features reflect the priority of production tasks (e.g., urgent work orders require priority in securing materials). The attention mechanism automatically adjusts the importance of these features based on the current production scenario (e.g., whether there are urgent work orders or equipment failures). For example, when there are urgent work orders, the weight of scheduling features increases to ensure that the prediction results prioritize the needs of urgent tasks; when a piece of equipment fails, the weight of equipment topology features increases to correct for changes in demand caused by the equipment anomaly. Through this dynamic integration, the system's final output, a predicted material consumption rate, more accurately reflects actual production demand, providing a reliable basis for subsequent inventory adjustments and replenishment decisions.

[0051] In some embodiments of the present application, in step S300, the implementation process of calculating the real-time inventory level and dynamic replenishment threshold by combining the predicted material consumption rate, current material inventory, material incoming rate, basic inventory buffer and equipment operating parameters includes but is not limited to the following steps.

[0052] Step S310: Calculate a dynamic risk compensation coefficient based on the mean time to repair and mean time between failures in the equipment operating parameters.

[0053] In step S310, the reliability risk of the equipment's current operating status is quantified, providing key risk quantification indicators for subsequent inventory adjustments. The mean time to repair (MTTR) within the equipment's operating parameters reflects the average time required to recover after a failure, while the mean time between failures (MTBF) reflects the average interval between failures. By analyzing the ratio of these two parameters, the potential risk of production anomalies caused by equipment failure can be assessed: the longer the MTTR or the shorter the MTBF, the lower the equipment reliability and the higher the risk of failure-induced production fluctuations. The calculation of a dynamic risk compensation coefficient converts this risk into a quantifiable numerical indicator, providing a decision-making basis for dynamically adjusting inventory buffers and replenishment thresholds based on the equipment's status.

[0054] Step S320: Calculate the dynamic inventory buffer and the dynamic replenishment threshold based on the dynamic risk compensation coefficient and the basic inventory buffer.

[0055] In step S320, the basic inventory buffer is a safety stock benchmark set based on historical regular demand fluctuations and replenishment uncertainties, while the dynamic risk compensation coefficient reflects the quantitative results of the current equipment abnormality risk. Through the combined calculation of the two, the dynamic inventory buffer is adjusted according to the equipment risk level on the basis of the basic buffer. The dynamic replenishment threshold, as the critical value for triggering replenishment, is also adjusted based on the dynamic inventory buffer to ensure that it is highly matched with the current equipment status and production needs, thereby improving the targeted nature of the replenishment strategy. The higher the equipment risk, the larger the dynamic inventory buffer and the higher the dynamic replenishment threshold, so as to reserve more inventory to cope with potential production fluctuations; when the equipment is operating stably, the dynamic inventory buffer is reduced accordingly, and the dynamic replenishment threshold is also reduced accordingly to avoid inventory redundancy.

[0056] Step S330 , calculating the real-time inventory level based on the dynamic inventory buffer, the predicted material consumption rate, the current material inventory and the material incoming rate.

[0057] In step S330, the actual available inventory level of the line warehouse is calculated by integrating multi-dimensional information, providing a direct basis for replenishment decisions. The calculation of the real-time inventory level needs to take into account: the predicted material consumption rate (reflecting the material demand within the future preset time window), the current material inventory (the existing material reserves of the line warehouse), the material entry rate (materials in transit that have been issued but not delivered), and the dynamic inventory buffer (additional inventory to deal with equipment abnormality risks). Through the comprehensive calculation of the above parameters, the real-time inventory level can accurately reflect the actual supply capacity of the line warehouse after considering future demand, existing reserves and risk buffers. If the real-time inventory level is lower than the dynamic replenishment threshold, it means that the existing inventory cannot meet future demand and replenishment needs to be triggered immediately; otherwise, it means that the inventory is sufficient to avoid waste of resources caused by excessive replenishment. This step converts the prediction results and real-time data into actionable inventory indicators to ensure that inventory management is accurately matched with actual production needs.

[0058] In some embodiments of the present application, the real-time inventory water level satisfies the following formula (1): (1); In formula (1), Indicates real-time inventory water level; Indicates the current material inventory; Indicates the material incoming rate, Indicates the material warehousing time window; represents the predicted material consumption rate, Indicates the material consumption time window; Indicates the dynamic inventory buffer, It is the product of the dynamic risk compensation coefficient and the basic inventory buffer. The dynamic risk compensation coefficient is calculated based on the mean repair time and mean time between failures in the equipment operating parameters.

[0059] As can be seen from formula (1), the calculation formula for real-time inventory level achieves accurate quantification of the actual available inventory of the line warehouse by integrating multi-dimensional data, providing a key basis for dynamic replenishment decision-making. Specifically, the calculation of real-time inventory level comprehensively considers the following core elements: the current material inventory (the existing material reserves of the line warehouse) reflects the current inventory that can be directly used; the material inbound rate (materials in transit that have been issued but not yet delivered) reflects the inventory to be replenished; the product of the predicted material consumption rate and the preset time window (the expected material consumption in the future period) clarifies future demand; the dynamic inventory buffer (the product of the risk compensation coefficient calculated based on equipment operating parameters and the basic inventory buffer) reserves a safety margin to cope with demand fluctuations caused by equipment abnormalities (such as failures and maintenance delays). Through the comprehensive calculation of the above elements, the real-time inventory level can accurately reflect the actual supply capacity of the line warehouse after considering the existing reserves, in-transit materials, future demand and risk buffer, ensuring that the inventory level not only meets the needs of production continuity but also avoids resource waste caused by excessive replenishment, effectively improving the dynamic adaptability and accuracy of material management.

[0060] In some embodiments of the present application, the dynamic replenishment threshold satisfies the following formula (2): (2); In formula (2), represents the dynamic replenishment threshold, represents the replenishment lead time, represents the mean of the historical material consumption rate, Indicates the mean time to repair in the equipment operating parameters, Indicates the mean time between failures in the equipment operating parameters; Indicates the preset mean time between failures threshold, Indicates the preset mean time to repair threshold.

[0061] As can be seen from formula (2), the calculation method of the dynamic replenishment threshold realizes the dynamic adjustment of the replenishment trigger condition by combining the equipment reliability status and historical demand characteristics, ensuring that inventory management is highly adapted to actual production needs. Specifically, the setting of the dynamic replenishment threshold is based on the comparison of the mean repair time (reflecting the time it takes to recover after a device failure) and the mean time between failures (reflecting the frequency of device failures) in the equipment operating parameters with the preset thresholds. There are two scenarios: when the equipment's mean repair time does not exceed the preset mean repair time threshold and the equipment's mean time between failures is higher than the preset mean time between failures threshold, the equipment reliability is high and the equipment operating status is relatively stable. The dynamic replenishment threshold is calculated based on the product of the replenishment lead time and the mean of the historical material consumption rate and the dynamic inventory buffer. When the equipment's mean repair time exceeds the preset mean repair time threshold and the equipment's mean time between failures is not higher than the preset mean time between failures threshold, the equipment reliability is low. In this case, the dynamic replenishment threshold is further increased based on the above basic value to reserve more inventory to deal with potential material shortage risks.

[0062] Therefore, dynamically increasing the buffer by adjusting the ratio of equipment reliability parameters not only ensures production continuity but also avoids inventory backlogs caused by overly conservative management. This dynamic adjustment mechanism allows replenishment thresholds to flexibly adapt to changes in equipment status, effectively improving the accuracy and risk mitigation of material management.

[0063] In some embodiments of the present application, the dynamic risk compensation coefficient satisfies the following formula (3): (3); In formula (3), represents the dynamic risk compensation coefficient, Indicates the remaining time of the current work order. Represents the process cycle constant.

[0064] As can be seen from formula (3), the dynamic risk compensation coefficient achieves accurate quantification of inventory risk by integrating equipment reliability status and work order remaining time, providing a key basis for dynamically adjusting inventory buffers. Specifically, the coefficient is calculated by combining the equipment's mean repair time, mean time between failures, the current work order remaining time (reflecting the urgency of the production task), and the process cycle constant (the standard time it takes for the equipment to complete a single process): the longer the equipment's mean repair time or the shorter the mean time between failures (the less reliable the equipment), the shorter the current work order remaining time (the more urgent the production task), and the larger the dynamic risk compensation coefficient, indicating that more inventory buffers are needed to cope with material demand fluctuations that may be caused by equipment failures (such as production suspension during maintenance and subsequent demand surges when it resumes). Conversely, the higher the equipment reliability or the more sufficient the work order remaining time, the smaller the dynamic risk compensation coefficient, avoiding inventory backlogs caused by excessive buffering. Through this quantitative mechanism, the system can dynamically adjust inventory strategies based on the actual equipment status and production tasks, effectively improving the accuracy and risk resistance of material management.

[0065] In some embodiments of the present application, the basic inventory buffer satisfies the following formula (4): (4); In formula (4), represents the basic inventory buffer, Indicates the material breakage tolerance coefficient. Represents the replenishment lead time variance. Represents the standard deviation of the historical material consumption rate.

[0066] As can be seen from formula (4), the calculation method of the basic inventory buffer provides a basic guarantee for inventory management to cope with conventional risks by comprehensively considering demand fluctuations and the uncertainty of replenishment time. It is a key design to ensure production continuity and on-time delivery. Specifically, the determination of the basic inventory buffer combines the following core elements: the material shortage tolerance coefficient is determined by the company's tolerance for material shortage risk. For example, a material shortage tolerance coefficient of 97% means that with a 97% probability, inventory will not fall below demand, which means that only 3 out of every 100 replenishments may lead to material shortages due to insufficient inventory; replenishment lead time (the average time from the issuance of a replenishment request to the delivery of materials), the standard deviation of the historical material consumption rate (reflecting the degree of fluctuation in material demand; the larger the standard deviation, the more unstable the demand), and the replenishment lead time variance (reflecting the degree of fluctuation in replenishment time; the larger the variance, the more uncertain the replenishment time).

[0067] By integrating these factors, the basic inventory buffer can quantify the combined impact of demand fluctuations and replenishment time uncertainty on inventory, setting a reasonable safety stock baseline for line warehouses: when demand fluctuates significantly or replenishment time is unstable, the basic buffer is increased accordingly to ensure sufficient inventory to cope with unexpected demand; when demand is stable or replenishment time is reliable, the basic buffer is appropriately reduced to avoid inventory backlogs. This calculation method provides a scientific basis for dynamically adjusting inventory strategies, effectively balancing production continuity and inventory costs, and effectively improving the level of refined material management.

[0068] In some embodiments of the present application, the minimum delay path objective function satisfies the following formula (5): (5); In formula (5), Represents the minimum delay path objective function value. Indicates the number of replenishment tasks in the smart workshop. Indicates that the automated guided vehicle has completed the The time for a replenishment task, Indicates the The deadline for a replenishment task, Indicates the The delayed completion time of a replenishment task. Represents the distance weight coefficient, which is used to adjust the importance of the total travel distance of the automated guided vehicle in the minimum delay path objective function value. Indicates the Automated guided vehicles complete the The driving distance of a replenishment task, Indicates the number of automated guided vehicles. , Indicates the The replenishment task is assigned to Automated guided vehicles perform, Indicates the The replenishment task is not assigned to the Automated guided vehicles.

[0069] As can be seen from formula (5), the minimum delay path objective function provides a scientific optimization basis for automated guided vehicle (AGV) path planning by comprehensively considering task punctuality and logistics costs, effectively improving the execution efficiency and resource utilization of replenishment tasks. Specifically, the core logic of this objective function is to minimize the weighted sum of two parts: the first part is the sum of the delay times of all replenishment tasks (only the part where the actual completion time exceeds the deadline is calculated), ensuring that the tasks are completed as on time as possible and avoiding production line interruptions caused by delays; the second part is the weighted sum of the total travel distance of all AGVs performing tasks (the weight is adjusted by the distance weight coefficient β), which controls the ineffective travel of AGVs and reduces logistics energy consumption and equipment loss. Through the constraint of a 0-1 variable (indicating whether a task is performed by a certain AGV), the system can dynamically assign tasks to different AGVs and balance the load of each AGV. The design of this objective function enables AGV path planning to take into account both task punctuality and logistics costs, and adjusts the distance weight coefficient value according to actual needs (for example, lowering the distance weight coefficient in emergency scenarios to prioritize punctuality), ultimately achieving efficient and economical execution of replenishment tasks, effectively improving the reliability of workshop material supply and resource utilization efficiency.

[0070] In some embodiments of the present application, the minimum delay path objective function needs to satisfy three constraints, including a first constraint, a second constraint, and a third constraint.

[0071] The three constraints of the minimum delay path objective function guarantee the feasibility and efficiency of automated guided vehicle (AGV) scheduling by clarifying the task allocation rules and execution restrictions, ensuring that the optimization results of the objective function meet the needs of actual production scenarios. Specifically: the first constraint limits the number of tasks or loads performed by each AGV, avoiding equipment failure or efficiency loss due to AGV overload or too many tasks, thereby ensuring the safety and stability of AGV operation; the second constraint stipulates that each replenishment task can only be performed by one AGV, avoiding duplicate assignment or omission of tasks, and ensuring the uniqueness and accuracy of material supply; the third constraint avoids conflicts between multiple AGVs in the same time or space by stipulating the time sequence and spatial restrictions of task execution (for example, the current task can only be started after the previous task is completed, and the travel time must meet the relationship between distance and speed), thus ensuring the continuity of task execution and the rationality of path planning.

[0072] These three constraints restrict the objective function from the three dimensions of equipment load, task allocation, and spatiotemporal coordination, so that the optimized AGV path can not only minimize delays and driving distances, but also comply with the actual operating rules of the workshop, effectively improving the reliability and efficiency of replenishment task execution.

[0073] In some embodiments of the present application, the first constraint condition satisfies the following formula (6): (6); In formula (6), Indicates the The mission capacity of an automated guided vehicle.

[0074] As can be seen from Equation (6), the first constraint ensures the safety and efficiency of AGV operation by limiting the task load of each AGV. It is a key rule for ensuring the reliable execution of replenishment tasks. Specifically, this constraint stipulates that the number of tasks assigned to each AGV (a 0-1 variable indicates whether a task is executed) must not exceed its preset task capacity (such as a maximum of 5 tasks at a time or a maximum cargo capacity limit). This restriction avoids problems such as AGV overload, excessive travel time, or increased equipment wear caused by excessive task assignment, ensuring that the AGV can execute tasks in the optimal state for its design.

[0075] At the same time, the first constraint balances the task load across multiple AGVs, preventing resource waste such as individual AGVs being delayed due to excessive tasks while other AGVs remain idle, thereby improving overall scheduling efficiency. Ultimately, this constraint, by regulating the upper limit of AGV task allocation, ensures the stability and reliability of replenishment tasks, providing a fundamental guarantee for the continuity of material supply on the shop floor.

[0076] In some embodiments of the present application, the second constraint condition satisfies the following formula (7): (7); As can be seen from formula (7), the second constraint condition indicates that any replenishment task in the smart workshop is assigned to only one automated guided vehicle for execution, which ensures the uniqueness and accuracy of task assignment and is a key rule for ensuring the orderly supply of materials. Specifically, this constraint requires that any replenishment task must and can only be executed by one AGV (limited by a 0-1 variable), avoiding duplicate transportation caused by multiple AGVs performing the same task at the same time (such as a batch of materials being delivered multiple times, resulting in redundant inventory in the line warehouse) or task omissions (such as a shortage of materials due to the lack of an AGV performing a task).

[0077] At the same time, unique assignment clarifies the correspondence between tasks and AGVs, facilitating real-time tracking of task execution status (e.g., which AGV is responsible for which task and its current progress). When a task is delayed or anomaly occurs, the responsible AGV can be quickly located and emergency measures can be taken (e.g., adjusting the path or dispatching other AGVs for assistance), effectively improving the efficiency of replenishment tasks and the ability to respond to exceptions. By standardizing the uniqueness of task assignments, this constraint ensures the accuracy of material supply and the efficient use of logistics resources, providing a key guarantee for the continuity of workshop production.

[0078] The third constraint satisfies the following formula (8): (8); In formula (8), Indicates the The first automated guided vehicle began to The time for a replenishment task. Indicates the The automated guided vehicle completed the The time for a replenishment task. Indicates the The location and The distance between the locations of the replenishment tasks. Indicates the The moving speed of an automated guided vehicle. Indicates the The number of tasks that an automated guided vehicle needs to perform.

[0079] From formula (8), we can see that the third constraint condition guarantees the continuity of task execution and the feasibility of path planning by regulating the time and space relationship of AGV task execution, and is the key rule to avoid AGV time and space conflicts. Specifically, this constraint stipulates that AGV starts to execute the The time required for each replenishment task must be at least equal to the time required to complete the previous task ( task), plus the time from Mission location to The system limits the travel time between each task location (calculated by the distance between the two locations and the AGV's speed). This rule ensures that the AGV can only start subsequent tasks after completing the previous task, avoiding task confusion caused by time overlap. Furthermore, the travel time limit ensures that the AGV has sufficient time to move from one task location to the next, avoiding path conflicts caused by insufficient spatial distance (such as appearing at two task locations at the same time). This constraint allows the system to generate AGV paths that conform to actual operating rules, improving the reliability and efficiency of task execution and ensuring the continuity and accuracy of material supply.

[0080] Secondly, an embodiment of the present application provides an intelligent workshop material dynamic pulling control system, including a data acquisition module 410, a material consumption prediction module 420 and a replenishment control module 430.

[0081] Data acquisition module 410 is used to obtain the basic inventory buffer of the smart workshop, equipment topology, production scheduling characteristics, real-time production data, and material inflow rate. Real-time production data includes current material inventory, equipment operating parameters, and material transportation parameters. Production scheduling characteristics represent information about production tasks and their corresponding product material usage.

[0082] The material consumption prediction module 420 is used to use a multimodal prediction model to extract time-series production features from real-time production data, and to extract equipment topology features from the equipment topology map, and to fuse time-series production features, equipment topology features and production scheduling features through an attention mechanism to output a predicted material consumption rate.

[0083] Replenishment control module 430 calculates the real-time inventory level and dynamic replenishment threshold based on the predicted material consumption rate, current material inventory, material inbound rate, basic inventory buffer, and equipment operating parameters. If the real-time inventory level falls below the dynamic replenishment threshold, a replenishment instruction is generated. Based on the material transportation parameters, a minimum delay path objective function is constructed to generate an optimal path and control the automated guided vehicles to execute the replenishment.

[0084] Furthermore, an embodiment of the present application provides a smart workshop material dynamic pulling control device, including: an Internet of Things sensing device 510, an edge computing device 520, a central decision-making device 530 and an automatic guided transport vehicle 540.

[0085] The IoT sensing device 510 is used to collect real-time production data of the smart workshop, including current material inventory, equipment operating parameters, and material transportation parameters.

[0086] The edge computing device 520 is deployed with an INT8 quantized multimodal prediction model, which is called through a gRPC interface.

[0087] Deploying INT8-quantized multimodal prediction models on edge computing devices and invoking them via the gRPC interface is a key technical support for achieving real-time and efficient dynamic control of materials in intelligent workshops. Specifically, the INT8-quantized model compresses the weights and activation values ​​of the original 32-bit floating-point model into 8-bit integers, effectively reducing the model size (typically by more than 75%), reducing the storage and computing resource usage of edge computing devices, and simultaneously increasing inference speed (typically by more than 2 times). This enables it to quickly process real-time production data (such as lineside warehouse inventory, equipment vibration, etc.) with limited hardware resources, meeting the stringent real-time requirements of workshop material management.

[0088] The gRPC interface, a high-performance remote procedure call framework, uses the HTTP / 2 protocol to achieve low-latency, high-throughput communication, ensuring efficient and reliable data transmission and model invocation between edge computing devices and other devices, avoiding the problem of delayed prediction results caused by latency or bandwidth limitations in traditional interfaces. The two work together to enable the multimodal prediction model to extract time-series production characteristics, equipment topology characteristics, and production scheduling characteristics in real time, outputting accurate material consumption rates, and providing timely and reliable decision-making basis for dynamic inventory level calculation and replenishment strategy generation, ultimately ensuring the continuity of material supply in the workshop and the achievement of lean management goals.

[0089] The edge computing device 520 is used to obtain the basic inventory buffer, equipment topology map, production scheduling characteristics and material inflow rate of the smart workshop, and use the multimodal prediction model to extract time series production features from real-time production data and equipment topology features from the equipment topology map. It also fuses time series production features, equipment topology features and production scheduling features through the attention mechanism to output the predicted material consumption rate.

[0090] The central decision-making unit 530 is used to calculate the real-time inventory level and dynamic replenishment threshold based on the predicted material consumption rate, current material inventory, material inflow rate, basic inventory buffer, and equipment operating parameters. If the real-time inventory level falls below the dynamic replenishment threshold, a replenishment instruction is generated. Based on the material transportation parameters, a minimum delay path objective function is constructed to generate an optimal path, and the automated guided vehicle 540 is controlled to carry out the replenishment.

[0091] In some embodiments of the present application, the Internet of Things sensing device 510 includes a line-side warehouse sensing unit 511, an equipment status sensing unit 512 and a logistics sensing unit 513. The line-side warehouse sensing unit 511 is used to obtain the current material inventory. The line-side warehouse sensing unit 511 includes a smart material box, which includes a weighing sensor and an RFID reader.

[0092] The lineside warehouse sensing unit 511 accurately and in real time obtains the current material inventory in the lineside warehouse, providing basic data support for inventory level calculation and replenishment decisions. This unit is implemented through a smart material bin, which integrates a weighing sensor and an RFID reader. The weighing sensor detects the material weight in real time (e.g., a range of 0-500kg) and calculates the current material quantity in the lineside warehouse based on material density or unit weight conversion. The RFID reader reads the material tag to obtain information such as the material work order number and material ID, ensuring the binding of inventory data to production work orders. The two work together to ensure real-time inventory quantity and traceability of material sources and destinations (e.g., matching work order requirements with tag information), avoiding inventory management deviations caused by material mismatches or data errors.

[0093] The device status sensing unit 512 is used to collect device operating parameters. The device status sensing unit is deployed on the production equipment in the smart workshop and includes a vibration sensor and a PLC interface.

[0094] The equipment status sensing unit 512 collects operating parameters of production equipment, providing critical data for equipment reliability analysis and dynamic risk compensation. Deployed on production equipment (such as injection molding machines and assembly machines), this unit integrates a vibration sensor and a PLC interface. The vibration sensor samples equipment vibration at high frequencies (e.g., 1kHz) and combines it with fast Fourier transform analysis (e.g., within the 50-500Hz frequency range) to identify equipment operating anomalies (such as bearing wear and loose components). The PLC interface communicates with the equipment control system (e.g., using the Modbus TCP protocol) to directly obtain reliability metrics such as mean time between failures (MTBF) and mean time to repair (MTTR). Using this data, the system quantifies equipment failure risk (e.g., longer MTTR and shorter MTBF indicate less reliable equipment). The system then dynamically adjusts inventory buffer levels and replenishment thresholds to prevent material shortages or excess inventory caused by equipment anomalies.

[0095] The logistics perception unit 513 is used to collect the position, speed, and vehicle capacity of the AGV 540 as material transportation parameters. The logistics perception unit is deployed on the AGV 540 and includes a laser radar, a visual SLAM processor, and a UWB chip.

[0096] The Logistics Perception Unit 513 collects real-time status data from automated guided vehicles (AGVs), providing a logistics-focused decision-making basis for route optimization and replenishment execution. Deployed on the AGV, this unit integrates a lidar (LiDAR), a visual SLAM (Simulation and Mapping) processor, and a UWB (Universal Wide Band) chip. The LiDAR emits laser pulses to scan the environment (with an accuracy of ±2cm), detecting obstacles (such as temporarily stored materials) in real time. The visual SLAM processor analyzes camera images (such as workshop scene characteristics) to construct an environmental map and locate the AGV. The UWB chip communicates with the workshop base station to achieve centimeter-level high-precision positioning.

[0097] Working together, the three can obtain the AGV's position, speed (e.g., 0.5-2 m / s), and carrier capacity (e.g., 1.2 m³ / 800 kg in standard mode and 2.5 m³ / 1500 kg in extended mode) in real time, providing logistics status input for the minimum delay path objective function. This ensures the real-time and accuracy of AGV path planning, and avoids replenishment delays or path conflicts caused by delayed logistics information.

[0098] In some embodiments of this application, the technical capabilities of the intelligent workshop material dynamic pull control method, system, and device are not limited to the material management of a single workshop, but can be extended to the coordinated transportation and inventory control of materials at the entire supply chain level. Through hierarchical functional positioning, parameterized dynamic calculation, and a full-link collaborative replenishment process, precise control of the entire chain from supplier to production line is achieved, effectively improving the efficiency and reliability of the supply chain. Taking the supply chain of battery cells and protection boards as an example, a detailed explanation is provided from three aspects: the supply chain hierarchy structure, the definition of core parameters, and the collaborative replenishment process.

[0099] First of all, the supply chain used in the embodiment of the present application includes four core levels, each level has clear functions and inventory types, forming a material flow chain of supplier warehouses, central warehouse storage warehouses, central warehouse available warehouses, workshop lineside warehouses and production lines, ensuring the accurate flow of materials from the production source to the end of the production line.

[0100] Specifically, the supplier warehouse, as the starting point of the supply chain, utilizes a just-in-time (JIT) production model and delivers materials directly to the central warehouse. Its core function is to produce to order and deliver materials on time. This warehouse's inventory consists of unused battery cells and protective boards, which must be strictly aligned with the production schedule to avoid inventory backlogs caused by overproduction. Key parameters include lead time and delivery reliability. Lead time is the time it takes to complete an order, e.g., a supplier needs three days to complete production. Delivery reliability is the probability of on-time delivery, e.g., a 95% on-time delivery rate. This is used to assess supplier stability and adjust replenishment lead times.

[0101] The central warehouse storage warehouse serves as a transit point between suppliers and available warehouses. For example, the central warehouse storage warehouse receives battery cells directly from suppliers and uses refrigerated storage. Its core function is to complete the static processing and quality inspection of materials. The inventory type at this node is refrigerated battery cells, which must undergo a 24-hour static process (for example, the battery cells must be stabilized in a low-temperature environment) to ensure that the materials transferred to the available warehouse meet production requirements. Its core parameters include the static buffer and the supplier replenishment cycle. The static buffer is the inventory buffer that must be reserved during the static process. For example, if materials cannot be released during the static period and need to be stockpiled in advance; the supplier replenishment cycle is the time period from the order being placed with the supplier to the delivery of materials to the storage warehouse. For example, if the supplier requires three days to complete production and transportation, this cycle is used to dynamically adjust the storage warehouse's replenishment strategy.

[0102] The available warehouse in the central warehouse serves as the upstream supply node of the workshop line-side warehouse. It mainly stores battery cells that have been put to rest for 24 hours and are available at room temperature. Its core function is to provide the workshop line-side warehouse with available materials that can respond quickly. The inventory type of this node is battery cells that can be put to rest at room temperature. It is necessary to ensure that the materials have passed the static inspection (for example, the battery cells need stable performance) to avoid production anomalies caused by failure to rest. Its core parameters include the available inventory threshold and AGV response time: the available inventory threshold is the minimum inventory that triggers replenishment to the storage warehouse. When the inventory drops to this value, a replenishment request must be initiated to the central warehouse storage warehouse; the AGV response time is the time constraint from receiving the workshop request to completing the material delivery. For example, the AGV delivers once every 2 hours to ensure that the inventory of the workshop line-side warehouse is replenished in time.

[0103] The workshop lineside warehouse directly serves the production line (for example, 20 parallel production lines). Its core function is to replenish materials to the production line in real time on demand to ensure production continuity. Its inventory types include battery cells and protection boards, which are stored at room temperature. Because they are directly exposed to the production site, they must respond quickly to the immediate needs of the production line. Its core parameters include: the replenishment point, which is the minimum inventory threshold that triggers replenishment. When the inventory drops to this value, a replenishment request is automatically sent to the available warehouse in the central warehouse; safety stock, which is used to buffer demand fluctuations and avoid material shortages due to short-term demand surges; demand fluctuations, which are parameters that reflect production uncertainty (such as equipment failures and fluctuations in production rhythm) and are used to dynamically adjust safety stock.

[0104] Secondly, each level achieves precise control of inventory through quantitative parameters. Taking the workshop line warehouse as an example, the definition and calculation of its core parameters directly determine the scientific nature of the replenishment strategy.

[0105] For example, the mean demand is 40,000 units per hour, calculated from 20 production lines with a demand of 2,000 units per hour per line. This reflects the average level of regular production demand. This value is based on historical production data statistics (such as the average consumption rate over the past 30 days) and is the basis for calculating safety stock and replenishment points. The standard deviation of demand is 4,800 units per hour, calculated by combining production fluctuations and equipment failure rates. Production fluctuations, such as a temporary increase in orders or equipment failures, such as a production line shutdown causing other lines to speed up, can cause demand to deviate from the mean. The larger the standard deviation, the higher the safety stock required. The replenishment lead time is 2 hours, which refers to the time it takes for the AGV to transport the available warehouse in the central warehouse to the lineside warehouse on the workshop floor. This determines the time window from when replenishment is triggered to when the material arrives. The longer the lead time, the higher the safety stock required, as more material may have been consumed before it arrives. The material shortage tolerance coefficient is determined by the company's tolerance for material shortage risks. For example, a material shortage tolerance coefficient of 97% indicates that there is a 97% probability that inventory will not fall below demand, meaning that material shortages may occur only 3 out of every 100 replenishments due to insufficient inventory.

[0106] Then, through the linkage of dynamic inventory levels and replenishment thresholds, coordinated replenishment at all levels is achieved. The specific process is as follows: the workshop line warehouse triggers replenishment. When the line warehouse inventory drops to the replenishment point, that is, less than or equal to 160,000 units, the system automatically sends a replenishment request to the available warehouse in the central warehouse. The threshold is set based on the average demand of 40,000 units / hour and the replenishment lead time of 2 hours. The consumption of 2 hours under normal demand is 40,000 × 2 = 80,000 superimposed safety stocks, such as 80,000, ensure that when replenishment is triggered, there is still enough inventory to maintain until the materials are delivered; the available warehouse of the central warehouse responds and links the storage warehouse. After receiving the request, the available warehouse of the central warehouse releases the resting battery cells, that is, they are available at room temperature to complete the delivery. At the same time, the system checks whether the available warehouse inventory has dropped to the available inventory threshold, that is, less than or equal to 880,000. If it is met, a replenishment request to the central warehouse storage warehouse is triggered. The setting of this threshold is based on the average demand of the workshop line warehouse of 40,000 / hour and the AGV delivery frequency of once every 2 hours. Ensure that the available warehouse can cover multiple delivery needs, such as 880,000 can support 22 deliveries to avoid frequent requests to the storage warehouse; the central warehouse storage warehouse places an order with the supplier. After the storage warehouse receives the replenishment request from the available warehouse Check whether its own inventory has dropped to the storage warehouse replenishment threshold, that is, less than or equal to 2448000. If it meets the system, it will place an order with the supplier. The setting of this threshold is based on the 24-hour static cycle and the 3-day supplier replenishment cycle to ensure that the storage warehouse still has sufficient inventory to support the demand of the available warehouse during the 24-hour static period. For example, 2448000 can support 61.2 hours of static demand; the supplier's production and delivery complete the full-link closed loop. After receiving the order, the supplier completes the production and transports the materials to the central warehouse storage warehouse according to the production cycle of 3 days, and then starts the 24-hour static process. After the static process is completed, the materials are transferred to the central warehouse available warehouse to wait for the replenishment request of the workshop line warehouse, forming a full-link closed loop of the supplier warehouse, central warehouse storage warehouse, central warehouse available warehouse, workshop line warehouse and production line.

[0107] Through the dynamic pull control technology provided by the embodiments of the present application, inventory status and replenishment demand at each level of the supply chain are synchronized in real time, effectively improving the overall efficiency and reliability of the supply chain. It reduces inventory backlogs. Through dynamic calculation of demand mean, standard deviation, and stock-out tolerance coefficient, each level initiates replenishment only when a threshold is triggered, avoiding inventory redundancy caused by advance stocking in the traditional model. For example, the central warehouse's available warehouse only requests replenishment from the storage warehouse when inventory falls below a threshold, rather than regular batch replenishment. It also reduces the risk of stock outages. The high-frequency delivery of AGVs every 2 hours and the multi-level replenishment trigger mechanism (from line warehouses to available warehouses to storage warehouses and then to suppliers) ensure the continuity of material supply to the production line. For example, when the inventory of the workshop line warehouse falls below a threshold, an immediate response is provided to avoid stock outages caused by transportation delays. It optimizes supply chain efficiency. The linkage between the JIT model and the supplier's production cycle reduces material in-transit time and idle waiting time. For example, suppliers only produce when the storage warehouse triggers replenishment, avoiding overproduction. At the same time, the precise scheduling of AGV deliveries every 2 hours improves the utilization of logistics resources.

[0108] In summary, the embodiments of the present application achieve precise control of materials in the entire supply chain from suppliers to production lines through hierarchical functional positioning, parameterized dynamic calculation and a full-link collaborative replenishment process, providing key technical support for supply chain collaboration and lean management in the manufacturing industry, and effectively solving the core contradiction of the coexistence of inventory backlogs and material shortage risks in traditional supply chains.

[0109] In summary, the method, system and device for dynamic material pulling control in an intelligent workshop provided by the embodiments of the present application have the following technical effects.

[0110] The intelligent workshop material dynamic pull control method, system, and device provided in the embodiments of the present application effectively improve the accuracy and dynamic adaptability of material management through multimodal data fusion and AI intelligent prediction technology. On the one hand, the multimodal prediction model that integrates LSTM, GNN, and attention mechanism accurately captures the short-term trend of material consumption, the impact of equipment failure, and the priority of production tasks, and controls the prediction error within 8.5%, providing a reliable basis for dynamic decision-making; in combination with equipment operating parameters (MTBF / MTTR), the inventory buffer and replenishment threshold are dynamically adjusted. When equipment reliability is low, the buffer is increased to avoid material shortages, and when it is stable, the buffer is decreased to reduce backlogs, thereby reducing the proportion of inventory and material stagnation in line warehouses and shortening the downtime caused by material shortages, effectively balancing inventory costs and production continuity.

[0111] On the other hand, based on the material transportation parameters, the minimum delay path objective function and multiple constraints (AGV capacity, task uniqueness, and time-space conflicts) are constructed. The system dynamically allocates replenishment tasks and generates the optimal path, taking into account both punctuality and logistics costs, reducing AGV task response delays, improving inventory turnover, and effectively improving logistics efficiency. At the same time, the IoT sensing device realizes full-scene data collection, the edge computing device ensures real-time performance through the INT8 quantization model and the gRPC interface, the central decision-making device dynamically responds to abnormal scenarios, and the overall system availability is provided, which comprehensively enhances the risk resistance and production guarantee level of workshop material management.

[0112] In some optional embodiments, the functions / operations mentioned in the block diagram may not occur in the order mentioned in the operation schematic diagram. For example, depending on the functions / operations involved, the two boxes shown in succession may actually be executed substantially simultaneously or the boxes can sometimes be executed in reverse order. In addition, the embodiments presented and described in the flow chart of the present application are provided in an exemplary manner for the purpose of providing a more comprehensive understanding of the technology. The disclosed method is not limited to the operations and logical flows presented herein. Optional embodiments are contemplated in which the order of the various operations is changed and the sub-operations described as a part of a larger operation are performed independently.

[0113] In addition, although the present application is described in the context of functional modules, it should be understood that, unless otherwise stated, one or more of the functions and / or features may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in separate physical devices or software modules. It is also understood that a detailed discussion of the actual implementation of each module is not necessary for understanding the present application. More specifically, given the properties, functions, and internal relationships of the various functional modules in the devices disclosed herein, the actual implementation of the module will be understood within the routine skills of an engineer. Therefore, a person skilled in the art will be able to implement the present application as set forth in the claims using ordinary techniques. It is also understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present application, which is determined by the full scope of the appended claims and their equivalents.

[0114] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or the portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several programs that enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the various embodiments of the method of the present invention. The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0115] The logic and / or steps represented in a flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable programs for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, a program execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can retrieve and execute a program from a program execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, a program execution system, apparatus, or device.

[0116] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting, or processing it in a suitable manner as necessary, and then storing it in a computer memory.

[0117] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable program execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having logic gate circuits for implementing logic functions on data signals, an application-specific integrated circuit having suitable combinational logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0118] In the above description of this specification, reference to the terms "one embodiment / implementation," "another embodiment / implementation," or "certain embodiments / implementations" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in the embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0119] Although the embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the claims and their equivalents.

[0120] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the embodiments. Those skilled in the art can make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of the present invention.

Claims

1. A method for dynamic material pulling control in an intelligent workshop, characterized in that: The steps include: Obtain the basic inventory buffer, equipment topology, production scheduling characteristics, real-time production data, and material inflow rate of the smart workshop; the real-time production data includes the current material inventory, equipment operating parameters, and material transportation parameters; the production scheduling characteristics are used to characterize the information of the production tasks and their corresponding product material usage; Utilizing a multimodal prediction model, extracting time-series production features from the real-time production data and extracting equipment topology features from the equipment topology map, and fusing the time-series production features, the equipment topology features, and the production scheduling features through an attention mechanism to output a predicted material consumption rate; Calculate the real-time inventory level and dynamic replenishment threshold based on the predicted material consumption rate, the current material inventory, the material incoming rate, the basic inventory buffer, and the equipment operating parameters; If the real-time inventory level is lower than the dynamic replenishment threshold, a replenishment instruction is generated, and based on the material transportation parameters, a minimum delay path objective function is constructed to generate an optimal path and control the automatic guided vehicle to perform replenishment.

2. The intelligent workshop material dynamic pulling control method according to claim 1 is characterized in that: The equipment topology map is used to characterize the process connections and fault propagation weights between devices; the equipment topology map is constructed based on the production process flow chart, equipment physical layout and historical fault data of the smart workshop; The device topology diagram is in the form of a graph In the form of Represents a device node, Indicates the process connection relationship between equipment, represents the fault propagation weight between devices, The value of is the probability of cascading impact of equipment failure.

3. The intelligent workshop material dynamic pulling control method according to claim 1 is characterized in that: The multimodal prediction model includes a long short-term memory network, a graph neural network, and an attention mechanism; The method utilizes a multimodal prediction model to extract time series production features from the real-time production data, extracts equipment topology features from the equipment topology map, and fuses the time series production features, the equipment topology features, and the production scheduling features through an attention mechanism to output a predicted material consumption rate, including the following steps: Extracting the time series production features from the real-time production data using the long short-term memory network; Extracting the device topology features from the device topology graph using the graph neural network; The time series production features, the equipment topology features and the production scheduling features are fused through the attention mechanism to output the predicted material consumption rate.

4. The intelligent workshop material dynamic pulling control method according to claim 1 is characterized in that: The step of calculating the real-time inventory level and the dynamic replenishment threshold by combining the predicted material consumption rate, the current material inventory, the material incoming rate, the basic inventory buffer, and the equipment operating parameters comprises the following steps: A dynamic risk compensation coefficient is calculated based on the mean time to repair and mean time between failures in the equipment operating parameters; Calculating a dynamic inventory buffer and a dynamic replenishment threshold according to the dynamic risk compensation coefficient and the basic inventory buffer; Calculate the real-time inventory level based on the dynamic inventory buffer, the predicted material consumption rate, the current material inventory, and the material incoming rate; The real-time inventory water level satisfies the following formula: ; in, Indicates the real-time inventory water level; Indicates the current material inventory; Indicates the material entry rate, Indicates the material warehousing time window; represents the predicted material consumption rate, Indicates the material consumption time window; Indicates the dynamic inventory buffer, The product of the dynamic risk compensation coefficient and the basic inventory buffer, wherein the dynamic risk compensation coefficient is calculated based on the mean time to repair and mean time between failures in the equipment operating parameters; The dynamic replenishment threshold satisfies the following formula: ； in, represents the dynamic replenishment threshold, Replenishment lead time, represents the mean of the historical material consumption rate, represents the mean time to repair in the equipment operating parameters, Indicates the mean time between failures in the operating parameters of the equipment; Indicates the preset mean time between failures threshold, Indicates the preset mean time to repair threshold.

5. The intelligent workshop material dynamic pulling control method according to claim 4 is characterized in that: The dynamic risk compensation coefficient satisfies the following formula: ； in, represents the dynamic risk compensation coefficient, Indicates the remaining time of the current work order. Represents the process cycle constant; The basic inventory buffer volume satisfies the following formula: ； in, represents the basic inventory buffer amount, Indicates the material breakage tolerance coefficient; represents the replenishment lead time variance; Represents the standard deviation of the historical material consumption rate.

6. The intelligent workshop material dynamic pulling control method according to claim 1 is characterized in that: The minimum delay path objective function satisfies the following formula: ； in, represents the minimum delay path objective function value; Indicates the number of replenishment tasks of the smart workshop; Indicates that the automated guided transport vehicle completes the The time for a replenishment task, Indicates the The deadline for a replenishment task, Indicates the The delay in completing a replenishment task; represents a distance weight coefficient, which is used to adjust the importance of the total travel distance of the automated guided transport vehicle in the minimum delay path objective function value; Indicates the The automated guided transport vehicle completes the The driving distance of a replenishment task, Indicates the number of the automated guided vehicles; , Indicates the The replenishment task is assigned to The automated guided vehicle performs, Indicates the The replenishment task is not assigned to the The automated guided vehicle is executed.

7. The intelligent workshop material dynamic pulling control method according to claim 6 is characterized in that: The minimum delay path objective function must satisfy three constraints, including a first constraint, a second constraint, and a third constraint; The first constraint condition satisfies the following formula: ； in, Indicates the the mission capacity of each of the automated guided vehicles; The second constraint condition satisfies the following formula: ； The second constraint condition indicates that any replenishment task of the smart workshop is only assigned to one of the automated guided vehicles for execution; The third constraint condition satisfies the following formula: ； in, Indicates the The automated guided vehicle begins to execute the The time for a replenishment task; Indicates the The automated guided transport vehicle completes the The time for a replenishment task; Indicates the The location and The distance between the locations of the replenishment tasks; Indicates the The moving speed of each of the automated guided vehicles; Indicates the The number of tasks to be performed by the automated guided vehicle.

8. An intelligent workshop material dynamic pulling control system, characterized in that: It includes data acquisition module, material consumption forecast module and replenishment control module; The data acquisition module is used to obtain the basic inventory buffer, equipment topology, production scheduling characteristics, real-time production data and material inflow rate of the smart workshop; wherein the real-time production data includes the current material inventory, equipment operating parameters and material transportation parameters; the production scheduling characteristics are used to characterize the information of the production task and its corresponding product material usage; The material consumption prediction module is used to use a multimodal prediction model to extract time-series production features from the real-time production data and extract equipment topology features from the equipment topology map, and fuse the time-series production features, the equipment topology features and the production scheduling features through an attention mechanism to output a predicted material consumption rate; The replenishment control module is used to calculate the real-time inventory level and the dynamic replenishment threshold based on the predicted material consumption rate, the current material inventory, the material incoming rate, the basic inventory buffer and the equipment operating parameters; if the real-time inventory level is lower than the dynamic replenishment threshold, a replenishment instruction is generated, and based on the material transportation parameters, a minimum delay path objective function is constructed to generate an optimal path, and the automated guided vehicle is controlled to perform the replenishment.

9. An intelligent workshop material dynamic pulling control device, characterized in that: include: IoT sensing devices, edge computing devices, central decision-making devices, and automated guided vehicles; The IoT sensing device is used to collect real-time production data of the smart workshop; wherein the real-time production data includes current material inventory, equipment operating parameters and material transportation parameters; The edge computing device is deployed with an INT8 quantized multimodal prediction model, and the multimodal prediction model is called through a gRPC interface; The edge computing device is used to obtain the basic inventory buffer, equipment topology map, production scheduling characteristics and material inflow rate of the smart workshop, and use the multimodal prediction model to extract time-series production features from the real-time production data and equipment topology features from the equipment topology map. The time-series production features, equipment topology features and production scheduling features are fused through an attention mechanism to output a predicted material consumption rate; the production scheduling features are used to characterize information about production tasks and their corresponding product material usage; The central decision-making device is used to calculate the real-time inventory level and the dynamic replenishment threshold based on the predicted material consumption rate, the current material inventory, the material incoming rate, the basic inventory buffer and the equipment operating parameters; if the real-time inventory level is lower than the dynamic replenishment threshold, a replenishment instruction is generated, and based on the material transportation parameters, a minimum delay path objective function is constructed to generate an optimal path and control the automatic guided vehicle to perform the replenishment.

10. The intelligent workshop material dynamic pulling control device according to claim 9, characterized in that: The IoT sensing device includes a line-side warehouse sensing unit, an equipment status sensing unit, and a logistics sensing unit; The line-side warehouse sensing unit is used to obtain the current material inventory; the line-side warehouse sensing unit includes an intelligent material box, and the intelligent material box includes a weighing sensor and an RFID reader; The device status sensing unit is used to collect the device operating parameters; the device status sensing unit is deployed on the production equipment of the smart workshop, and the device status sensing unit includes a vibration sensor and a PLC interface; The logistics perception unit is used to collect the position, speed and carrier capacity of the automatic guided transport vehicle as the material transportation parameters; the logistics perception unit is deployed on the automatic guided transport vehicle, and the logistics perception unit includes a laser radar, a visual SLAM processor and a UWB chip.

Images