Automatic stockpiling management and optimization system based on digital twinning technology

Abstract

The invention relates to the technical field of storage stockpiling, and discloses an automatic stockpiling management and optimization system based on a digital twinborn technology, which comprises a real-time data acquisition module, a digital twinborn model construction module, an equipment operation monitoring and maintenance module, a production guidance and optimization module, an automatic control module and a visual interaction module. According to the automatic stockpiling management and optimization system based on the digital twinning technology, the use efficiency of a storage space is effectively expanded, the production interruption risk and the maintenance cost caused by equipment faults are reduced, the efficiency of the whole stockpiling operation process is improved, and the stockpiling management level is remarkably improved.

Description

Technical Field

[0001] The present invention relates to the field of warehouse stockpiling technology, and in particular to an automated stockpiling management and optimization system based on digital twin technology. Background Art

[0002] Traditional stockpile management relies heavily on manual experience and simple monitoring equipment, making it difficult to accurately monitor the status of the material pile in real time and efficiently optimize stockpile operations. Manual stockpiling often results in uneven stacking, leading to low storage capacity utilization, excessive accumulation in some areas, and underutilization in other areas, resulting in wasted resources.

[0003] At the same time, there's a lack of effective real-time monitoring for the equipment involved in stockpiling operations, making it impossible to promptly detect faults and anomalies during equipment operation. Repairs are often delayed until serious equipment failures occur, resulting in prolonged equipment downtime and impacting the continuity and efficiency of stockpiling operations. Furthermore, during stockpiling operations, it's difficult to adjust stockpiling strategies based on actual changes in the material pile, which can easily lead to problems like burying equipment or wasting storage capacity, preventing optimal stockpiling operations.

[0004] With the continuous development of the warehousing industry and the increasing requirements for stockpile management, traditional stockpile management methods are no longer able to meet the needs. There is an urgent need for an automated stockpile management and optimization system that can achieve real-time data collection, accurate modeling, equipment monitoring and maintenance, production guidance and optimization, and visual interaction. This can improve storage capacity utilization, reduce equipment failure rates, optimize stockpile operation efficiency, and enhance stockpile management. Summary of the Invention

[0005] In response to the shortcomings of the existing technology, the present invention provides an automated stockpile management and optimization system based on digital twin technology to solve the above problems.

[0006] To achieve the above objectives, the present invention provides the following technical solutions: an automated stockpile management and optimization system based on digital twin technology, comprising: The real-time data acquisition module consists of a LiDAR sensor, a weight sensor, and a temperature sensor. The LiDAR sensor uses multi-line LiDAR technology to quickly acquire three-dimensional information about large-area material piles and perform precise measurements. These sensors are evenly distributed at key locations in the storage space and are used to collect real-time data on various physical parameters of the material pile and transmit it to the data processing center. The digital twin model construction module uses collected real-time data and physical model-based 3D modeling technology to digitally model the physical characteristics and motion patterns of elements such as storage space, material piles, and equipment. This includes building a material pile model based on its fluidity and stacking density, and a motion model for the stacker based on its mechanical structure and kinematic characteristics. This allows the digital twin model to accurately reflect the dynamic changes in the actual storage environment. The equipment operation monitoring and maintenance module monitors the operating status of equipment involved in the stacking operation, such as the stacker and the warehouse unloader, in real time. Acceleration sensors, speed sensors, and current sensors are installed on the equipment to collect operating parameters and transmit them to the equipment operation monitoring system. The production guidance and optimization module, based on the digital twin model and real-time data collection, uses optimization algorithms such as genetic algorithms and simulated annealing algorithms to automatically calculate the optimal feeding position, feeding amount, and feeding sequence, ensuring that materials are evenly stacked in the storage space to improve storage capacity utilization. At the same time, by real-time monitoring and analysis of changes in material pile shape and available stacking capacity, the stacking strategy is adjusted in advance to avoid wasting equipment or storage capacity due to material accumulation; The automation control module connects to equipment such as stackers and bin-out machines to achieve automated control. It uses a model-based predictive control strategy to compare and analyze the stacking plan in the digital twin model with the actual stacking situation in real time to predict potential problems during the stacking process and take control measures in advance. The visualization interaction module presents the digital twin model to the operator in a visual form through virtual reality (VR) or augmented reality (AR) technology. The operator wears a VR helmet or uses AR equipment to perform stacking operations and monitor in a virtual or augmented warehouse environment.

[0007] Preferably, lidar sensors are installed on the top and around the storage space, and the installation height and angle are reasonably adjusted according to the size and shape of the storage space to obtain the best measurement effect. Weight sensors are installed at key positions of the material pile, and wireless transmission technology is used to transmit data to the data processing center. Temperature sensors and other sensors are integrated in the data acquisition node to transmit data through the network.

[0008] Preferably, the equipment operation monitoring system adopts a distributed architecture, stores data in a local database, and performs data analysis and processing through a cloud computing platform.

[0009] Preferably, the maintenance plan includes the time and content of regular maintenance, and the spare parts replacement suggestion includes the type and quantity of spare parts that need to be replaced.

[0010] Preferably, optimization algorithms such as genetic algorithms and simulated annealing algorithms are used to simulate and evaluate various stockpiling schemes to find the optimal stockpiling scheme to maximize storage capacity utilization.

[0011] Preferably, the communication connection between the automation control module and the stacking machine, the warehouse discharge machine and other equipment adopts field bus technology or industrial Ethernet technology to realize data transmission and control instruction sending.

[0012] Preferably, the equipment operation monitoring and maintenance module uses machine learning algorithms such as support vector machines, neural networks, etc. to analyze operation data to determine whether the equipment has faults or abnormal conditions, and generates maintenance plans and spare parts replacement recommendations based on the equipment operation history data and preset maintenance rules.

[0013] Preferably, the advance control measures within the automation control module include adjusting the movement speed and action of the stacker to ensure the accuracy and stability of the stacking operation, real-time monitoring of the discharge status of the warehouse discharger and automatic adjustment of the discharge speed and gate opening position to avoid the formation of vertical gable material piles.

[0014] Preferably, the visual interaction module also includes a user interface, through which operators can input production plans, adjust stockpiling parameters, etc., and has data analysis and report generation functions, performs statistical analysis on equipment operation data, stockpiling data, etc., and generates reports to provide data support for stockpiling management and optimization.

[0015] Compared with the existing technology, the present invention provides an automated stockpile management and optimization system based on digital twin technology, which has the following beneficial effects: In terms of storage capacity utilization, since the system can achieve uniform stacking of materials, it avoids the space waste caused by uneven stacking in the past, and greatly improves the storage capacity utilization rate. For example, in actual application, it can be increased by more than 15%, effectively expanding the utilization efficiency of storage space, saving enterprises a lot of storage costs and increasing economic benefits.

[0016] For equipment operation, the equipment operation monitoring and maintenance module can monitor the equipment status in real time, accurately diagnose faults with the help of machine learning algorithms, issue alarms in advance and locate the causes, and generate maintenance plans and spare parts replacement recommendations based on historical operation data and preset rules, thereby effectively reducing the equipment failure rate by more than 20%, reducing equipment maintenance time by 30%, ensuring the stable operation of the equipment, and reducing the risk of production interruption and maintenance costs caused by equipment failure.

[0017] In terms of stacking operation efficiency, the production guidance and optimization module automatically calculates the optimal feeding parameters and adjusts the strategy in advance. The automation control module adjusts the equipment operating parameters in real time, making the stacking operation more accurate, stable and efficient. The operating efficiency has been improved by more than 30%, improving the efficiency of the entire stacking operation process.

[0018] At the stockpile management level, the intuitive operating interface and data analysis functions provided by the visual interactive module enable managers to grasp key information such as stockpile operation conditions and equipment status in real time, facilitating timely decision-making and optimizing management strategies, significantly improving the stockpile management level, providing strong support for the company's refined management, and helping the company achieve better results and competitiveness in the field of stockpile management. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 This is a schematic diagram of the connection relationship structure of each system of the present invention. DETAILED DESCRIPTION

[0020] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Obviously, the embodiments described are only some embodiments of the invention, not all embodiments. In the absence of conflict, the embodiments and features in the embodiments of this application can be combined with each other. Based on the embodiments of the invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the invention.

[0021] See also Figure 1 , automated stockpile management and optimization system based on digital twin technology:

[0022] Installation and debugging of real-time data acquisition module According to design requirements, LiDAR sensors are installed on the roof and around the storage space. By adjusting the installation height and angle appropriately, they can quickly acquire 3D information and perform precise measurements of large areas of material piles. For example, for a large storage space, a multi-line LiDAR sensor can be installed on the roof, with corresponding LiDAR sensors installed at key locations around the perimeter to achieve comprehensive data collection of the material pile.

[0023] Weight sensors are installed at key locations of the material pile, such as different height layers, corners, etc. Wireless transmission technology is used to transmit the collected material weight data to the data processing center to ensure the real-time and stability of data transmission.

[0024] Temperature sensors and other sensors are integrated into data acquisition nodes, which transmit data through the network to monitor the temperature changes of the material pile in real time, providing more comprehensive physical parameter information for pile management.

[0025] Establishment of digital twin model building modules Leveraging the collected real-time data and using 3D modeling technology based on physical models, we began to build a digital twin model. First, we digitally modeled the warehouse space, including information such as its size, shape, and obstacle distribution, to ensure the model's consistency with the actual warehouse space.

[0026] For material piles, a material accumulation model is established based on its fluidity, bulk density, and other characteristics. For example, for materials with good fluidity, the model can simulate the material's flow trend and accumulation form. For materials with different bulk densities, corresponding accumulation models are established to more accurately reflect the actual situation of the material pile.

[0027] For the stacker, a motion model was established based on its mechanical structure and kinematic characteristics. The motion relationships, speeds, accelerations, and other parameters of each component of the stacker were described in detail, enabling the stacker in the digital twin model to accurately simulate the motion behavior of the actual stacker.

[0028] Implementation of equipment operation monitoring and maintenance module Acceleration sensors, speed sensors, and current sensors are installed on equipment involved in the stacking operation, such as stackers and bin-out machines, to collect real-time operating parameters. These sensors transmit the collected data to the equipment operation monitoring system via wired or wireless means.

[0029] The equipment operation monitoring system adopts a distributed architecture, storing data in a local database to ensure data security and reliability. Simultaneously, data analysis and processing are performed through a cloud computing platform, using advanced algorithms to monitor and analyze equipment operation data in real time, enabling timely detection of abnormalities in equipment operation.

[0030] Development of production guidance and optimization modules Based on the digital twin model and real-time data collection, optimization algorithms such as genetic algorithms and simulated annealing are introduced. These algorithms can simulate and evaluate various stacking schemes. Through continuous iteration and optimization, they find the optimal feeding location, feeding amount, and feeding sequence to ensure that materials are evenly stacked in the storage space and improve storage capacity utilization.

[0031] During the production process, changes in the material pile shape and available stacking capacity are monitored and analyzed in real time. Stacking strategies are adjusted in advance based on actual conditions to avoid burying equipment or wasting storage capacity. For example, if an abnormal shape is detected or the available stacking capacity decreases, the system automatically adjusts the stacker's motion trajectory and feeding parameters to ensure smooth stacking operations.

[0032] Connection and configuration of automation control modules The automation control module connects to equipment such as the stacker and bin-dispenser via fieldbus or industrial Ethernet technology, enabling data transmission and the sending of control instructions. This ensures the timeliness and accuracy of control instructions, allowing the stacker and bin-dispenser to operate according to the predetermined stacking plan.

[0033] Using a model-based predictive control strategy, the digital twin model's stacking plan and actual stacking conditions are compared and analyzed in real time. By predicting potential issues during the stacking process, such as uneven material accumulation and equipment failure, control measures can be implemented in advance, such as adjusting the stacker's speed and adjusting the discharge status of the bin ejector, ensuring the accuracy and stability of the stacking operation.

[0034] Implementation of visual interaction module The digital twin model is presented to operators in a visual form through virtual reality (VR) or augmented reality (AR) technology. Operators wearing VR helmets or using AR devices can operate and monitor stacking operations in a virtual or augmented warehouse environment.

[0035] The visual interaction module also includes a user interface, allowing operators to input production plans and adjust stockpiling parameters. Furthermore, this module features data analysis and report generation, performing statistical analysis on equipment operating data and stockpiling data, and generating reports to support stockpiling management and optimization. For example, the system can generate real-time reports on stockpiling operations, equipment operating status, and storage capacity utilization, helping managers to promptly understand stockpiling conditions and equipment operating conditions, enabling them to make informed decisions.

[0036] Real-time data collection and transmission The real-time data acquisition module operates continuously. The LiDAR sensor continuously acquires three-dimensional information about the pile, the weight sensor monitors weight changes in real time, and the temperature sensor monitors the temperature of the pile. This data is transmitted wirelessly or wired to the data processing center to ensure real-time and accurate data.

[0037] The data processing center preprocesses the collected data to remove noise and anomalies to ensure data quality. The processed data is then transmitted to other modules, such as the digital twin model construction module, the equipment operation monitoring and maintenance module, and the production guidance and optimization module, providing data support for each module.

[0038] Dynamic update of digital twin models As stockpiling operations progress, the shape, position, weight, and other parameters of the material pile constantly change. The digital twin model construction module dynamically updates the digital twin model based on real-time data, ensuring that the model accurately reflects the dynamic changes in the actual warehouse environment.

[0039] For example, when a stacker is stacking materials, the material pile model in the digital twin model updates the material's stacking position and shape in real time. When the weight of the material pile changes, the weight parameters in the model are also updated accordingly. This ensures that the digital twin model remains consistent with the actual warehouse environment, providing accurate foundational data for other modules.

[0040] Equipment operation monitoring and fault diagnosis The equipment operation monitoring and maintenance module monitors the operating status of equipment such as stackers and warehouse ejectors in real time, and determines whether there are any faults or abnormal conditions in the equipment through operating parameters collected by acceleration sensors, speed sensors, current sensors, etc.

[0041] Machine learning algorithms such as support vector machines and neural networks are used to analyze operational data and establish equipment fault diagnosis models. When equipment operating parameters become abnormal, the system promptly issues an alarm and uses the fault diagnosis model to locate the cause, providing an accurate basis for equipment maintenance.

[0042] Based on historical equipment operation data and pre-set maintenance rules, maintenance plans and spare parts replacement recommendations are generated. Maintenance plans include the timing and content of scheduled maintenance, while spare parts replacement recommendations include the type and quantity of replacement parts. Based on these recommendations, managers can schedule equipment maintenance and spare parts replacement in advance to prevent equipment failures from impacting stockpiling operations.

[0043] Production guidance and optimization The production guidance and optimization module automatically calculates the optimal feed location, quantity, and sequence based on the digital twin model and real-time data. Through continuous iteration and optimization of the optimization algorithm, materials are evenly stacked in the storage space, improving storage capacity utilization.

[0044] Real-time monitoring and analysis of changes in the material pile shape and available stacking capacity allows for proactive adjustments to the stacking strategy. For example, if the system detects a tilted material pile or excessively high stacking in certain areas, it automatically adjusts the stacker's trajectory to ensure even stacking. If the available stacking capacity decreases, the system promptly notifies the operator to adjust the feeding plan to avoid wasted storage capacity.

[0045] The automation control module, based on instructions from the production guidance and optimization module, adjusts the operating parameters of the stacker and unloader in real time to ensure the accuracy and stability of the stacking operation. For example, it adjusts the speed and movement of the stacker to ensure more even material accumulation. It also monitors the unloader's discharge status in real time and automatically adjusts the discharge speed and gate opening position to avoid the formation of vertical gable piles, which would affect the efficiency and safety of the stacking operation.

[0046] Visual interaction and operation Operators, wearing VR headsets or using AR devices, can operate and monitor stacking operations in a virtual or augmented warehouse environment. The visual interaction module provides an intuitive interface, allowing operators to control the movement of stackers and unloaders through simple gestures or commands, achieving automated control of stacking operations.

[0047] During the stacking operation, operators can use the interactive visualization module to view real-time information such as the shape, position, and weight of the material pile, as well as the operating status and parameters of the equipment. Based on this information, operators can promptly adjust the stacking strategy and equipment operating parameters to ensure smooth stacking operations.

[0048] The visual interaction module also has data analysis and report generation functions. Operators can view various reports and statistical analysis results through the interface, understand indicators such as the efficiency of stacking operations and storage capacity utilization, and provide data support for stacking management and optimization.

[0049] Improve storage capacity utilization Through the automated stacking management and optimization system based on digital twin technology, materials can be evenly stacked in the storage space, avoiding uneven stacking and waste of materials, and significantly improving storage capacity utilization.

[0050] Reduce equipment failure rate The equipment operation monitoring and maintenance module monitors the equipment's operating status in real time, promptly identifies equipment failures and abnormalities, and uses fault diagnosis models to locate the cause of the failure, providing an accurate basis for equipment maintenance. This significantly reduces equipment failure rates and reduces equipment maintenance time and costs.

[0051] Optimize stacking efficiency The production guidance and optimization module automatically calculates the optimal feed position, feed amount, and feed sequence, and adjusts the stacking strategy in advance to ensure the accuracy and stability of the stacking operation. The automation control module adjusts the operating parameters of the stacker and warehouse unloader in real time, improving the automation level and efficiency of the stacking operation.

[0052] Improve stockpile management The visual interaction module provides an intuitive operation interface and data analysis functions. Managers can use the interface to view the stockpiling operation status and equipment operating status in real time, and understand indicators such as stockpiling efficiency and storage capacity utilization. This helps managers make timely decisions, optimize stockpiling management strategies, and improve stockpiling management level.

[0053] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. The automated stockpile management and optimization system based on digital twin technology is characterized by: include: The real-time data acquisition module consists of a LiDAR sensor, a weight sensor, and a temperature sensor. The LiDAR sensor uses multi-line LiDAR technology to quickly acquire three-dimensional information about large-area material piles and perform precise measurements. These sensors are evenly distributed at key locations in the storage space and are used to collect real-time data on various physical parameters of the material pile and transmit it to the data processing center. The digital twin model construction module uses collected real-time data and physical model-based 3D modeling technology to digitally model the physical characteristics and motion patterns of elements such as storage space, material piles, and equipment. This includes building a material pile model based on its fluidity and stacking density, and a motion model for the stacker based on its mechanical structure and kinematic characteristics. This allows the digital twin model to accurately reflect the dynamic changes in the actual storage environment. The equipment operation monitoring and maintenance module monitors the operating status of equipment involved in the stacking operation, such as the stacker and the warehouse unloader, in real time. Acceleration sensors, speed sensors, and current sensors are installed on the equipment to collect operating parameters and transmit them to the equipment operation monitoring system. The production guidance and optimization module, based on the digital twin model and real-time data collection, uses optimization algorithms such as genetic algorithms and simulated annealing algorithms to automatically calculate the optimal feeding position, feeding amount, and feeding sequence, ensuring that materials are evenly stacked in the storage space to improve storage capacity utilization. At the same time, by real-time monitoring and analysis of changes in material pile shape and available stacking capacity, the stacking strategy is adjusted in advance to avoid wasting equipment or storage capacity due to material accumulation; The automation control module connects to equipment such as stackers and bin-out machines to achieve automated control. It uses a model-based predictive control strategy to compare and analyze the stacking plan in the digital twin model with the actual stacking situation in real time to predict potential problems during the stacking process and take control measures in advance. The visualization interaction module presents the digital twin model to the operator in a visual form through virtual reality (VR) or augmented reality (AR) technology. The operator wears a VR helmet or uses AR equipment to perform stacking operations and monitor in a virtual or augmented warehouse environment.

2. The automated stockpile management and optimization system based on digital twin technology according to claim 1, characterized in that: The lidar sensors are installed on the top and around the storage space. The installation height and angle are reasonably adjusted according to the size and shape of the storage space to obtain the best measurement effect. The weight sensor is installed at the key position of the material pile, and wireless transmission technology is used to transmit data to the data processing center. The temperature sensor and other sensors are integrated in the data acquisition node to transmit data through the network.

3. The automated stockpile management and optimization system based on digital twin technology according to claim 1, characterized in that: The equipment operation monitoring system adopts a distributed architecture, stores data in a local database, and performs data analysis and processing through a cloud computing platform.

4. The automated stockpile management and optimization system based on digital twin technology according to claim 1, characterized in that: The maintenance plan includes the time and content of regular maintenance, and the spare parts replacement recommendation includes the type and quantity of spare parts that need to be replaced.

5. The automated stockpile management and optimization system based on digital twin technology according to claim 1, characterized in that: The optimization algorithms such as the genetic algorithm and the simulated annealing algorithm are used to simulate and evaluate various stockpiling schemes to find the optimal stockpiling scheme to maximize the storage capacity utilization rate.

6. The automated stockpile management and optimization system based on digital twin technology according to claim 1, characterized in that: The communication connection between the automatic control module and the stacking machine, the warehouse discharge machine and other equipment adopts field bus technology or industrial Ethernet technology to realize data transmission and control instruction sending.

7. The automated stockpile management and optimization system based on digital twin technology according to claim 1, characterized in that: The equipment operation monitoring and maintenance module uses machine learning algorithms such as support vector machines and neural networks to analyze operation data to determine whether there are any faults or abnormalities in the equipment, and generates maintenance plans and spare parts replacement suggestions based on the equipment operation history data and preset maintenance rules.

8. The automated stockpile management and optimization system based on digital twin technology according to claim 1, characterized in that: The advance control measures within the automation control module include adjusting the movement speed and action of the stacker to ensure the accuracy and stability of the stacking operation, real-time monitoring of the discharge status of the warehouse discharger and automatic adjustment of the discharge speed and gate opening position to avoid the formation of vertical gable material piles.

9. The automated stockpile management and optimization system based on digital twin technology according to claim 1, characterized in that: The visual interaction module also includes a user interface, through which operators can input production plans, adjust stockpiling parameters, etc., and has data analysis and report generation functions, which can perform statistical analysis on equipment operation data, stockpiling data, etc. and generate reports to provide data support for stockpiling management and optimization.

Images