A method and system for intelligent storage yard of assembled components

Abstract

The present invention belongs to the field of intelligent yards, and provides a method and system for intelligent yards of prefabricated components. Sensors are installed on prefabricated component production lines, yard areas, and transportation equipment to collect real-time data of components, including the size, weight, position, and status of prefabricated components, and the data is preprocessed; based on historical data and real-time data, a long short-term memory network model is used to predict the time series of component demand and generate a demand prediction sequence; combined with the capacity constraints of the yard and the outbound time of the components, the optimal component storage location and stacking sequence are generated to minimize the handling cost, storage space utilization cost, and delay cost; based on real-time data and yard status, the optimal path planning of AGV is performed, and the scheduling sequence of the handling equipment is dynamically adjusted. The above scheme can improve the efficiency of the prefabricated component yard.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent storage yards, and in particular relates to an intelligent storage yard method and system for assembled components. Background Art

[0002] With the development of prefabricated building technology, the production and use of prefabricated components have gradually become the mainstream trend in the construction industry. Prefabricated components are characterized by standardization and factory production, which can significantly shorten the construction period and improve the quality of buildings. However, with the expansion of the scale of prefabricated buildings and the increase in the number of projects, the storage and management of components have gradually become prominent. The traditional yard management method mainly relies on manual operation, which is not only inefficient, but also prone to problems such as unreasonable component stacking, low space utilization, and delayed delivery. These problems have restricted the development of prefabricated building industrialization to a certain extent.

[0003] In prefabricated construction projects, the yard is a key link in the storage and management of components, and its operating efficiency directly affects the construction progress and cost control. Especially in large-scale projects, the number of components in the yard is huge and varied, and the delivery time and sequence of each component need to be strictly managed according to the construction plan. If the yard is not managed properly, it may lead to the inability to deliver components in time when needed, affecting the construction progress; or unreasonable stacking, occupying too much storage space, increasing logistics and warehousing costs.

[0004] In order to meet these challenges, automated equipment such as automatic guided vehicles (AGVs) have gradually been introduced into yard management, aiming to improve the operating efficiency of the yard through automated handling technology. However, in practical applications, the path planning and scheduling of AGVs has become a new difficulty. Traditional path planning algorithms often cannot adapt to the complex environment and dynamic changes in the yard, resulting in the inability of AGVs to efficiently perform handling tasks, and may even cause path conflicts or handling delays. In addition, traditional scheduling methods are usually based on static rules and cannot flexibly respond to real-time changing task requirements and yard status, further limiting the application effect of AGVs in the yard. Summary of the invention

[0005] In order to solve the problems in the prior art, the present invention provides an intelligent yard method for prefabricated components, which includes the following steps: installing sensors on the prefabricated component production line, the yard area and the transportation equipment to collect real-time data of the components, the real-time data including the size, weight, position and status of the prefabricated components, and preprocessing the data; based on historical data and real-time data, using a long short-term memory network model to perform time series prediction of component demand and generate a demand prediction sequence; combining the capacity constraints of the yard and the outbound time of the components to generate the optimal component storage location and stacking sequence, minimizing the handling cost, storage space utilization cost and delay cost; based on the real-time data and the yard status, performing optimal path planning for the AGV and dynamically adjusting the scheduling sequence of the handling equipment.

[0006] Another aspect of the present invention is to provide an intelligent storage yard system for assembled components, the system comprising the following modules:

[0007] A collection module is used to install sensors on the assembly component production line, the yard area and the transportation equipment to collect the real-time data of the components, including the size, weight, position and status of the assembled components, and pre-process the data;

[0008] The prediction module is used to perform time series prediction of component demand based on historical data and real-time data using the long short-term memory network model to generate a demand prediction sequence;

[0009] The optimization module is used to combine the capacity constraints of the yard and the outbound time of the components to generate the optimal component storage location and stacking sequence, minimizing the handling cost, storage space utilization cost and delay cost;

[0010] The scheduling module is used to plan the optimal path for AGV based on real-time data and yard status, and dynamically adjust the scheduling order of handling equipment.

[0011] The present invention significantly improves the efficiency and intelligence level of prefabricated component yard management by introducing an AGV optimal path planning and dynamic scheduling method based on real-time data and yard status. Compared with traditional yard management methods, the present invention has the following beneficial effects:

[0012] Through intelligent planning and real-time adjustment of component storage locations, the present invention can maximize the utilization of the yard space and avoid space waste. Reasonable stacking of components not only reduces unnecessary handling operations, but also enables the yard to accommodate more components, thereby improving the storage capacity of the yard.

[0013] The present invention uses a path planning algorithm to calculate the optimal transport path for the AGV, ensuring that the AGV completes the transport task in the yard with the shortest path, thereby greatly reducing the transport time and energy consumption and improving the overall work efficiency of the AGV.

[0014] The present invention considers dynamic environmental factors in the yard in real time when planning the AGV path, such as the operating status of other AGVs, obstacles on the path, etc., and can effectively avoid path conflicts. By dynamically adjusting the AGV's transportation path, the system ensures coordinated operation between AGVs and reduces transportation delays and resource waste caused by path conflicts.

[0015] The dynamic scheduling function of the present invention makes the task allocation of AGV more flexible, and can dynamically adjust the scheduling order of AGV according to the changes in real-time data and task priorities. This flexibility ensures that high-priority tasks can be executed in a timely manner, thereby ensuring the progress and quality of the construction project.

[0016] By optimizing the path planning and task scheduling of AGV, the present invention reduces the driving distance and running time of AGV, reduces the energy consumption and equipment wear during the handling process. In addition, due to the improvement of the utilization rate of the yard space, the storage cost is also effectively controlled, thereby reducing the overall operating cost.

[0017] The present invention enhances the resilience and reliability of the yard management system through real-time monitoring and dynamic adjustment. The system can quickly respond to emergencies in the yard, such as AGV failure or path blockage, and adjust scheduling and path planning in a timely manner to ensure the continuity and safety of the handling task.

[0018] The method of the present invention has good scalability and adaptability, and can meet the management requirements of yards of different scales and complexities. Whether it is the daily operation of a small yard or the management of complex components in a large project, the present invention can provide an efficient and reliable solution, laying a solid foundation for the widespread application of prefabricated buildings. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0020] Figure 1 is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0021] Below, the invention is preferably described in conjunction with the accompanying drawings and specific implementation methods.

[0022] This embodiment solves the above problem through the following steps:

[0023] In one embodiment, reference Figure 1 The present invention provides an intelligent stacking method for prefabricated components.

[0024] Prefabricated components refer to parts or modules that are pre-produced and processed in the factory during the industrial production process, such as prefabricated wall panels, floor slabs, beams and columns, etc. These components are manufactured in the factory according to standardized designs and assembled on site, thus shortening the construction time and improving construction efficiency.

[0025] Smart yard refers to a system that uses artificial intelligence, the Internet of Things, automated equipment and other technologies to achieve automated storage, management and scheduling of prefabricated components during storage and management. Smart yards ensure efficient storage and in-and-out management of components through real-time data collection, optimization algorithms and dynamic scheduling.

[0026] The present invention aims to improve the operation efficiency of the storage yard by intelligently managing the storage, scheduling, and transportation of prefabricated building components. The present invention involves multiple key technical links, including data collection, demand forecasting, optimized storage and scheduling, dynamic path planning, and scheduling adjustment.

[0027] Sensors are installed on prefabricated component production lines, storage yards, and transportation equipment to collect real-time data on components, including the size, weight, location, and status of prefabricated components, and the data is preprocessed.

[0028] Prefabricated component production line refers to the assembly line system used to produce prefabricated building components in the factory. The production line usually includes multiple processes such as concrete pouring, steel frame installation, mold forming, etc., and can efficiently produce standardized building components such as wall panels, floor slabs, beams and columns.

[0029] The yard area refers to a specific site or space used to store and manage prefabricated components. The yard is usually located near a factory or construction site and is used to temporarily store prefabricated components so that they can be depotted and transported according to the construction progress.

[0030] Transport equipment refers to mechanical equipment used to transport prefabricated components within the storage yard or between the storage yard and the construction site. Common transport equipment includes automatic guided vehicles (AGVs), forklifts, cranes, etc. These devices can perform transport tasks automatically or semi-automatically.

[0031] Sensors are installed on assembly production lines, yard areas, and transportation equipment to collect real-time data on components. These sensors can monitor and record the physical characteristics, spatial position, and operating status of each component in real time, thus providing accurate basic data for the intelligent yard management system.

[0032] Specifically, the sensors on the assembly line are mainly responsible for monitoring the size and weight data of the components during the production process. These data help ensure that the components meet the design standards and can be effectively managed during storage and transportation. The sensors in the yard area are mainly responsible for tracking the specific storage location of the components and their current status, such as whether they are in a stacked state and whether there is structural damage. This information plays a key role in subsequent storage optimization and outbound scheduling. The sensors on the transportation equipment can collect the position data of the components in real time during the transportation process, ensuring that every step of the transportation process is under the monitoring of the system to prevent misoperation or deviation of the transportation path.

[0033] The real-time data includes key parameters such as the size, weight, position and status of the assembled components. By collecting this data, the system can fully grasp the real-time situation of each component. However, the raw data collected by the sensor often contains noise or outliers, so the data needs to be preprocessed. The preprocessing process includes cleaning the data to eliminate invalid or erroneous data; standardizing and normalizing to ensure that data from different sources can be used uniformly for subsequent analysis; and ensuring the accuracy and reliability of the data through outlier detection and correction.

[0034] These pre-processed data are input into the intelligent yard system as the basis for further optimizing storage solutions, path planning, and real-time scheduling decisions. Through this series of data processing and application, the present invention can achieve efficient and intelligent management of prefabricated components, greatly improving the operational efficiency and safety of the yard.

[0035] Based on historical data and real-time data, the long short-term memory network model is used to perform time series forecasting of component demand and generate a demand forecast sequence.

[0036] In intelligent yard management, it is crucial to understand the demand for components in the future. To achieve this goal, the present invention first collects and integrates a large amount of historical data, including production records, delivery time, construction plan, and market demand of components. At the same time, the system also continuously collects real-time data in the yard, such as current inventory levels, real-time in and out records of components, changes in construction progress, etc. The combination of these data provides rich basic information for demand forecasting.

[0037] On this basis, the present invention uses a long short-term memory network (LSTM) model to perform time series forecasting of component demand. LSTM is a deep learning model that is particularly suitable for processing time series data and can capture long-term dependencies and short-term change trends in the data. By training the LSTM model, the present invention can accurately predict component demand in the future, thereby generating a demand forecast sequence.

[0038] Take an actual prefabricated construction project as an example, which involves the production and installation of a variety of prefabricated components, such as prefabricated wall panels, floor slabs, beams and columns, etc. In order to ensure the smooth progress of the construction, the yard management system needs to estimate the demand for each component in the next few weeks in advance and adjust the production and storage plans accordingly.

[0039] Assume that in the past few months, the system has collected a large amount of historical data, including the number of various components produced each week, the number of components shipped out of the warehouse, the demand for components at the construction site, changes in construction progress, and fluctuations in market demand, etc. These data reflect the changing pattern of component demand in different time periods, for example, some components are in greater demand at the beginning of construction, while other components are used in large quantities only in the later stages.

[0040] In addition, the system also collects real-time information on current inventory, ongoing construction tasks, and changes in current market demand. These real-time data complement historical data, allowing the system to capture current and future demand trends.

[0041] Based on this data, the LSTM model is used to train and predict the demand for various components in the coming weeks. By learning from time series data, the LSTM model can predict that the demand for a certain component (such as prefabricated wall panels) will increase significantly in the next week, possibly because the construction progress will enter the wall installation stage. On the other hand, the model may also predict that the demand for a certain component (such as floor slabs) will gradually decrease after two weeks because the main floor slab installation work is nearly completed.

[0042] Based on these forecast results, the system generates a demand forecast sequence, which clearly indicates the number and type of components that need to be shipped from the yard in the next week. Managers can adjust production plans based on this sequence to ensure that the required components can be produced and stored in time. At the same time, the yard system can also optimize the storage location and transportation path of components in advance based on demand forecasts to ensure that components can be shipped quickly when needed, reducing construction delays and transportation costs.

[0043] In this way, the present invention not only improves the management efficiency of the storage yard, but also greatly reduces the problem of overproduction or shortage caused by inaccurate demand forecasting, ensuring the smooth progress of the prefabricated building project.

[0044] Combining the capacity constraints of the yard and the outbound time of the components, the optimal component storage location and stacking sequence are generated to minimize the handling cost, storage space utilization cost and delay cost.

[0045] In the intelligent storage yard method for prefabricated components, the storage location and stacking order of each component are determined, which specifically includes the following steps:

[0046] Definition of the objective function:

[0047] Transportation costs: including the cost of transporting components from the production line to the yard and from the yard to the outbound location. The goal is to reduce the travel and time of the transportation equipment, thereby reducing energy consumption and equipment wear.

[0048] Storage space utilization cost: The available space in the yard is limited, and the optimization goal is to maximize space utilization and reduce space waste caused by unreasonable storage.

[0049] Delay cost: If the components cannot be shipped on time, it will affect the construction progress and cause delay costs. Therefore, the model needs to ensure that the components can be shipped before the required time point to minimize the delay cost.

[0050] The objective function of the model can be expressed as:

[0051]

[0052] in:

[0053] Z represents the target cost; Minimize represents minimization;

[0054] C ij represents the transportation cost of component i stored at location j;

[0055] X ij is a binary decision variable. If component i is stored in position j, then X ij =1, otherwise X ij =0;

[0056] S k represents the storage space utilization cost of the yard location k;

[0057] y k is a binary variable. If the yard position 𝑘 is occupied, then y k =1, otherwise y k =0;

[0058] T m represents the delay cost of component m, z m Indicates whether the component is shipped on time. If the component is not shipped on time, then z m =1;

[0059] Setting of constraints:

[0060] Capacity constraint: The capacity of each storage location is limited, and it must be ensured that the volume of component i does not exceed the capacity of storage location j:

[0061]

[0062] in, V i is the volume of component i, V j is the capacity of storage location j;

[0063] Uniqueness constraint: Each component can only be stored in one location to prevent duplicate storage:

[0064]

[0065] Time constraint: To avoid delay costs, it is necessary to ensure that component m is completed at the required time. T m Before delivery:

[0066]

[0067] in t m is the actual delivery time of component m.

[0068] For example:

[0069] Suppose in a prefabricated building project, there are the following scenarios:

[0070] Project requirements: 20 prefabricated wall panels, 15 floor panels and 10 beams are required in a certain construction phase. These components will be produced and stored in the yard one after another, and will be shipped out in sequence when needed at the construction site.

[0071] Yard conditions: The yard is divided into three areas, each with different available storage capacity and handling equipment paths. Area A is closest to the production line but has limited space, Area B has larger space but is far from the warehouse exit, and Area C is on the other side of the yard with a more complex handling path.

[0072] Data collection and processing

[0073] Historical data: including historical demand for various components, historical usage of the yard area, transportation routes and times of different components, etc.

[0074] Real-time data: including current yard capacity, production progress of each component, real-time demand at the construction site, etc.

[0075] Model building and optimization

[0076] Transportation cost: Taking into account the transportation paths and distances of various areas of the yard, area A has the lowest transportation cost, while areas B and C have higher transportation costs.

[0077] Storage space utilization cost: Since the space in area A is limited, components that are frequently shipped out of the warehouse are stored in this area first to save transportation costs; area B can store larger floor slabs; area C is used to store beams and columns that do not need to be shipped out urgently.

[0078] Delay cost: The construction plan requires that wall panels be shipped out first, and the order in which floor slabs and beams and columns are shipped out is arranged according to the construction progress. It is necessary to ensure that all components are in place on time.

[0079] Solution and result application

[0080] Solution process: Through the planning solver (such as Gurobi, Cplex), the model calculates the optimal component storage location and stacking order. For example, wall panels will be stored in area A first, floor panels will be placed in area B, and beams and columns will be stored in area C.

[0081] Result analysis and implementation: Based on the optimization results, managers can arrange the handling and storage of components in an orderly manner to ensure that each component can be efficiently shipped from the yard to the construction site when needed, reducing transportation time and costs and avoiding delays.

[0082] Furthermore, in the optimization model of the present invention, different cost elements (such as transportation cost, time cost, and space utilization cost) may need to be normalized in the objective function to ensure that the contribution of each element in the model is balanced.

[0083] Transportation costs and time costs can be normalized using Min-Max since these costs usually have clear upper and lower bounds.

[0084] Space utilization costs can often be normalized using Max Abs, especially when the available space varies greatly in different yard areas.

[0085] For example, the original values ​​of the transportation cost, time cost, safety cost and space utilization cost are:

[0086] Transportation cost: ranges from 100 to 1000 yuan

[0087] Time cost: ranges from 30 to 120 minutes

[0088] Space utilization cost: range 0.2-0.8 (dimensionless score)

[0089] Through normalization, each factor is adjusted to the same scale range so that they have a balanced contribution to the objective function, avoiding a factor dominating the optimization process due to excessively large or small values.

[0090] Based on real-time data and yard status, the optimal path planning of AGV is carried out and the scheduling order of handling equipment is dynamically adjusted.

[0091] Before the AGV performs path planning, the system first needs to comprehensively monitor the real-time status of the yard. This status information includes:

[0092] Component location: The specific storage location of each component in the current yard and its type, size, weight and other information.

[0093] Inventory status: available storage space in each area of ​​the yard, quantity and type of stored components.

[0094] AGV status: the real-time location, speed, current task status (such as the type of component being transported and the destination) of each AGV.

[0095] Environmental status: dynamic environmental factors within the yard, such as whether the path is unobstructed, whether there are obstacles, the activities of other handling equipment, etc.

[0096] These real-time data are collected through sensor networks, IoT platforms, and the AGV’s own sensor systems, and transmitted to the central control system for analysis and processing.

[0097] Specifically, the optimal path planning includes the following steps:

[0098] Path initialization: The system first determines the starting point (such as the current storage location) and the destination (such as the exit or designated stacking area) of the AGV. These locations are usually represented as nodes in the map of the yard.

[0099] Node expansion and path selection: Starting from the starting point, expand the adjacent nodes (i.e. possible next step locations) in sequence, and calculate the actual cost from the starting point to these adjacent nodes g(n) and the estimated cost from these nodes to the destination h(n) , and calculate the evaluation function f(n) = g(n) + h(n)

[0100] Actual cost g(n)The calculation is based on the actual driving distance of the AGV in the yard, possible path obstacles and current traffic conditions. For example, if there are obstacles or other AGVs on the path, the system will increase the corresponding cost.

[0101] Estimated costs h(n) Estimate the shortest path length from the current node to the target node using a heuristic function such as Manhattan distance or Euclidean distance.

[0102] System selection evaluation function f(n) The smallest node is expanded to the next step, and the process is repeated until the optimal path connecting the starting point and the target point is found.

[0103] When the AGV is performing the handling task, if the real-time status in the yard changes (for example, a new obstacle appears on the path or other AGVs enter the same path), the system will dynamically adjust the path planning and recalculate the optimal path.

[0104] After the path planning is completed, the system will also dynamically adjust the scheduling order of AGVs to improve the overall yard operation efficiency. Task scheduling is based on real-time data and task priority to ensure that high-priority tasks are processed in a timely manner.

[0105] a) Dynamic adjustment of task priorities

[0106] The priority of a task is determined by a variety of factors, including the time requirements for component delivery, the urgency of construction, the current status of the AGV (such as power, load, etc.), etc. Based on real-time monitoring of the task queue, the system dynamically adjusts the priority of the task. For example, if a task becomes more urgent due to an emergency, the system will immediately increase the priority of the task and adjust the scheduling order of the AGV accordingly.

[0107] b) Task redistribution and path adjustment

[0108] When the AGV is performing a low-priority task and a high-priority task needs to be processed immediately, the system can dynamically adjust in the following ways:

[0109] Task redistribution: Assign high-priority tasks to the most suitable AGV. If an AGV is performing a low-priority task, the system can assign another AGV to take over the high-priority task, or directly switch the task of the current AGV.

[0110] Path adjustment: If a new high-priority task appears on the current path, the system will adjust the path according to the real-time status to give priority to the urgent task. For example, if the AGV needs to switch targets midway, the system will re-plan the path to ensure that the task is completed smoothly according to the priority.

[0111] Assume that in a large construction project, the yard management system needs to coordinate multiple AGVs to transport components. The following scenarios currently exist in the yard:

[0112] Task requirements:

[0113] Task A: Move 20 prefabricated wall panels from area B to the delivery port. The delivery time is the first week and the priority is high.

[0114] Task B: Move 15 beams from area C to the construction site. The task is urgent and has a medium priority.

[0115] Task C: Move 10 floor slabs from area A to the warehouse. The task is not urgent and has a low priority.

[0116] Real-time data:

[0117] AGV1 is currently executing task C, but an obstacle appears on the path.

[0118] AGV2 has just completed the return path of task B, but has not yet been assigned a new task.

[0119] Path planning and scheduling example:

[0120] Path planning:

[0121] The system calculates paths for AGV1 and AGV2. AGV1 needs to re-plan its path because there is an obstacle on its path. The system finds an alternative path that avoids the obstacle so that AGV1 can continue to complete Task C.

[0122] AGV2 is assigned to perform the highest priority task A, and the system plans the optimal path for it from area B to the exit. Due to the urgency of task A, AGV2's path planning prioritizes the shortest time and least interference.

[0123] Dynamic dispatch:

[0124] If AGV1 encounters further obstacles in completing task C, the system may dispatch other AGVs to take over task C, or reassign AGV1 to a new high-priority task.

[0125] The system continuously monitors the status of AGV1 and AGV2, and dynamically adjusts their task sequence and paths according to actual conditions to ensure that the handling tasks within the yard can be completed efficiently and safely.

[0126] On the other hand, the present invention also provides an intelligent storage yard system for assembled components, comprising:

[0127] A collection module is used to install sensors on the assembly component production line, the yard area and the transportation equipment to collect the real-time data of the components, including the size, weight, position and status of the assembled components, and pre-process the data;

[0128] The prediction module is used to perform time series prediction of component demand based on historical data and real-time data using the long short-term memory network model to generate a demand prediction sequence;

[0129] The optimization module is used to combine the capacity constraints of the yard and the outbound time of the components to generate the optimal component storage location and stacking sequence, minimizing the handling cost, storage space utilization cost and delay cost;

[0130] The scheduling module is used to plan the optimal path for AGV based on real-time data and yard status, and dynamically adjust the scheduling order of handling equipment.

[0131] Furthermore, the specific implementation methods of the above-mentioned intelligent yard system for prefabricated components are the same as those of an intelligent yard method for prefabricated components, and all further technical solutions in an intelligent yard method for prefabricated components are fully introduced into an intelligent yard system for prefabricated components.

[0132] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

[0133] The present invention does not particularly specify the structure of some modules, which shall be subject to the contents recorded in the prior art. The prior art mentioned in the above background technology section and the specific embodiment section of the present invention can be used as part of the present invention to understand the meaning of some technical features or parameters. The scope of protection of the present invention shall be subject to the contents actually recorded in the claims.

Claims

1. A method for intelligent storage of assembled components, characterized in that: The method comprises the following steps: Install sensors on the assembly component production line, yard area and transportation equipment to collect real-time data of the components, including the size, weight, location and status of the assembled components, and pre-process the data; Based on historical data and real-time data, the long short-term memory network model is used to predict the time series of component demand and generate a demand forecast sequence; Combine the capacity constraints of the yard and the time for the components to leave the warehouse to generate the optimal component storage location and stacking sequence to minimize the handling cost, storage space utilization cost and delay cost; Based on real-time data and yard status, the optimal path planning of AGV is carried out, and the scheduling sequence of handling equipment is dynamically adjusted; Combined with the capacity constraints of the yard and the outbound time of the components, the optimal component storage location and stacking sequence are generated to minimize the handling cost, storage space utilization cost and delay cost, including: An optimization model is constructed, and the objective function of the model is expressed as: in: Z represents the target cost; Minimize represents minimization; C ij represents the transportation cost of component i stored at location j; x i,j is a binary decision variable. If component i is stored in position j, then x i,j =1, otherwise x i,j =0; S k represents the storage space utilization cost of the yard location k; y k is a binary variable. If the yard position k is occupied, then y k =1, otherwise y k =0; T m represents the delay cost of component m, Z m Indicates whether the component is shipped on time. If the component is not shipped on time, then z m =1; Setting of constraints: Capacity constraint: The capacity of each storage location is limited, and it must be ensured that the volume of component i does not exceed the capacity of storage location j: Among them, V i is the volume of component i, V j is the capacity of storage location j; Uniqueness constraint: Each component can only be stored in one location to prevent duplicate storage: Time constraint: To avoid delay costs, it is necessary to ensure that component m is completed at the required time point T. m Before delivery: where t m is the actual delivery time of component m.

2. The method for intelligent storage of prefabricated components according to claim 1, characterized in that: The model is solved by a planning solver to calculate the optimal component storage location and stacking sequence.

3. The method for intelligent storage of prefabricated components according to claim 1, characterized in that: In the model, the transportation cost, time cost, and space utilization cost are normalized; wherein the transportation cost and the time cost are normalized using Min-Max; and the space utilization cost is normalized using Max Abs.

4. The method for intelligent storage of prefabricated components according to claim 1, characterized in that: Based on real-time data and yard status, the optimal path planning of AGV is carried out, and the scheduling sequence of handling equipment is dynamically adjusted, including: Determine the starting and destination points of the AGV; Starting from the starting point, expand the adjacent nodes one by one, calculate the actual cost g(n) from the starting point to these adjacent nodes and the estimated cost h(n) from these nodes to the target point, and calculate the evaluation function f(n) = g(n) + h(n); The actual cost g(n) is calculated based on the actual driving distance of the AGV in the yard, possible path obstacles, and current traffic conditions; The estimated cost h(n) uses a heuristic function to estimate the shortest path length from the current node to the target node; Select the node with the smallest evaluation function f(n) for the next step of expansion, and repeat this process until the optimal path connecting the starting point and the target point is found; When the AGV is performing the handling task, if the real-time status in the yard changes, the path planning will be dynamically adjusted and the optimal path will be recalculated.

5. An intelligent storage yard system for assembled components, characterized in that: The system includes the following modules: A collection module is used to install sensors on the assembly component production line, the yard area and the transportation equipment to collect the real-time data of the components, including the size, weight, position and status of the assembled components, and pre-process the data; The prediction module is used to perform time series prediction of component demand based on historical data and real-time data using the long short-term memory network model to generate a demand prediction sequence; The optimization module is used to combine the capacity constraints of the yard and the outbound time of the components to generate the optimal component storage location and stacking sequence, minimizing the handling cost, storage space utilization cost and delay cost; The scheduling module is used to plan the optimal path for AGVs based on real-time data and yard status, and dynamically adjust the scheduling order of handling equipment; Combined with the capacity constraints of the yard and the outbound time of the components, the optimal component storage location and stacking sequence are generated to minimize the handling cost, storage space utilization cost and delay cost, including: An optimization model is constructed, and the objective function of the model is expressed as: in: Z represents the target cost; Minimize represents minimization; C ij represents the transportation cost of component i stored at location j; x i,j is a binary decision variable. If component i is stored in position j, then x i,j =1, otherwise x i,j =0; S k represents the storage space utilization cost of the yard location k; y k is a binary variable. If the yard position k is occupied, then y k =1, otherwise y k =0; T m represents the delay cost of component m, Z m Indicates whether the component is shipped on time. If the component is not shipped on time, then z m =1; Setting of constraints: Capacity constraint: The capacity of each storage location is limited, and it must be ensured that the volume of component i does not exceed the capacity of storage location j: Among them, V i is the volume of component i, V j is the capacity of storage location j; Uniqueness constraint: Each component can only be stored in one location to prevent duplicate storage: Time constraint: To avoid delay costs, it is necessary to ensure that component m is completed at the required time point T. m Before delivery: where t m is the actual delivery time of component m.

6. The intelligent storage yard system for prefabricated components according to claim 5 is characterized in that: The model is solved by a planning solver to calculate the optimal component storage location and stacking sequence.

7. The intelligent storage yard system for prefabricated components according to claim 6 is characterized in that: In the model, the transportation cost, time cost, and space utilization cost are normalized; wherein the transportation cost and the time cost are normalized using Min-Max; and the space utilization cost is normalized using Max Abs.

8. The intelligent storage yard system for prefabricated components according to claim 5 is characterized in that: Based on real-time data and yard status, the optimal path planning of AGV is carried out, and the scheduling sequence of handling equipment is dynamically adjusted, including: Determine the starting and destination points of the AGV; Starting from the starting point, expand the adjacent nodes one by one, calculate the actual cost g(n) from the starting point to these adjacent nodes and the estimated cost h(n) from these nodes to the target point, and calculate the evaluation function f(n) = g(n) + h(n); The actual cost g(n) is calculated based on the actual driving distance of the AGV in the yard, possible path obstacles, and current traffic conditions; The estimated cost h(n) uses a heuristic function to estimate the shortest path length from the current node to the target node; Select the node with the smallest evaluation function f(n) for the next step of expansion, and repeat this process until the optimal path connecting the starting point and the target point is found; When the AGV is performing the handling task, if the real-time status in the yard changes, the path planning will be dynamically adjusted and the optimal path will be recalculated.

Images