Intelligent warehousing equipment collaborative decision system and method based on digital twinning

Abstract

The application relates to the technical field of warehouse management, and in particular relates to an intelligent warehouse equipment collaborative decision system and method based on digital twinning. The method comprises the following steps: collecting warehouse equipment sensing data, and determining the overall distribution structure of the warehouse equipment; based on the warehouse equipment sensing data, determining the interaction depth between the warehouse equipment; according to the interaction depth between the warehouse equipment, connecting the collaborative relationship lines between the warehouse equipment in the overall distribution structure of the warehouse equipment to construct a digital twinning collaborative network; determining the load change of each warehouse equipment by using the digital twinning collaborative network, and screening the overload relationship lines in the digital twinning collaborative network according to the load change; and according to the operation coupling strength between the overload relationship lines and the adjacent collaborative relationship lines, collaboratively adjusting the load conditions of each warehouse equipment in the overload relationship lines. The application is beneficial to improving the operation efficiency, operation stability and resource utilization rate of the warehouse system, and can adapt to complex and changeable operation scenes.

Description

Technical Field

[0001] This invention relates to the field of warehouse management technology, and in particular to a collaborative decision-making system and method for intelligent warehouse equipment based on digital twins. Background Technology

[0002] Existing intelligent warehousing systems typically consist of a variety of equipment working together, including automated storage and retrieval systems (AS / RS), automated guided vehicles (AGVs), sorting devices, stacking devices, and warehouse management systems. These systems improve warehousing efficiency and turnover capacity by automating operations such as receiving, storing, picking, handling, and shipping goods. In the early stages, the coordination between warehousing equipment relied mainly on fixed-rule scheduling and static operational logic control. Various types of equipment operated independently according to preset paths, sequences, and task instructions. While this approach could achieve basic automation, it had limited adaptability to complex operational scenarios.

[0003] The existing warehouse scheduling and decision-making methods lack a unified collaborative decision-making mechanism among various types of warehouse equipment. The scheduling strategies of various equipment are independent of each other, making it difficult to achieve optimal resource allocation at the global level. Summary of the Invention

[0004] Therefore, the present invention needs to provide a collaborative decision-making system and method for intelligent warehousing equipment based on digital twins to solve at least one of the above-mentioned technical problems.

[0005] To achieve the above objectives, a collaborative decision-making method for intelligent warehousing equipment based on digital twins includes the following steps: Step S1: Collect sensor data of warehousing equipment and determine the overall distribution structure of warehousing equipment based on the location information of each piece of warehousing equipment in the sensor data. Step S2: Determine the interaction depth between warehousing equipment based on the correlation degree of sensor signals between warehousing equipment in the warehousing equipment sensor data; Step S3: Based on the interaction depth between warehousing equipment, connect the collaborative relationship lines between warehousing equipment in the overall distribution structure of warehousing equipment to construct a digital twin collaborative network. Step S4: Use the digital twin collaborative network to determine the load changes of each warehouse equipment, and filter the overload relationship lines in the digital twin collaborative network according to the load changes; Step S5: Based on the operational coupling strength between the overload relationship line and the adjacent collaborative relationship line, coordinately adjust the load status of each storage equipment in the overload relationship line.

[0006] This application constructs a digital twin collaborative network covering the entire warehousing system, dynamically integrating multi-source data such as the real-time operating status of various warehousing equipment, the triggering of work instructions, and load changes. This enables in-depth quantification of interactions between equipment and modeling of collaborative relationships. Based on the digital twin network, real-time analysis of the load and operational coupling relationships of each piece of equipment can identify potential overload relationships and perform collaborative optimization adjustments, thereby achieving optimized allocation of global resources in high-concurrency and high-dynamic operating environments. This application not only enhances the collaborative response capabilities between various types of equipment but also improves the operational efficiency, stability, and resource utilization of the warehousing system. Furthermore, it can adapt to complex and ever-changing operational scenarios, providing accurate, efficient, and scalable decision support for intelligent warehousing systems.

[0007] Optionally, this application also provides a digital twin-based intelligent warehousing equipment collaborative decision-making system for executing the digital twin-based intelligent warehousing equipment collaborative decision-making method described above. The digital twin-based intelligent warehousing equipment collaborative decision-making system includes: The data acquisition module is used to collect sensor data from warehousing equipment and determine the overall distribution structure of warehousing equipment based on the location information of each piece of warehousing equipment in the sensor data. The interaction depth analysis module is used to determine the interaction depth between warehousing equipment based on the correlation degree of sensor signals between warehousing equipment in the sensor data of warehousing equipment. The digital twin building module is used to connect the collaborative relationship lines between warehousing equipment in the overall distribution structure of warehousing equipment according to the interaction depth between warehousing equipment, so as to build a digital twin collaborative network. The overload screening module is used to determine the load changes of each warehouse equipment using a digital twin collaborative network, and to screen the overload relationship lines in the digital twin collaborative network based on the load changes. The overload optimization module is used to coordinately adjust the load of each storage equipment in the overload relationship line based on the operational coupling strength between the overload relationship line and the adjacent collaborative relationship line.

[0008] The present invention relates to a collaborative decision-making system for intelligent warehousing equipment based on digital twins. This system can implement any of the collaborative decision-making methods for intelligent warehousing equipment based on digital twins of the present invention. It is used to combine the operation and signal transmission media between various modules to complete the collaborative decision-making method for intelligent warehousing equipment based on digital twins. The modules within the system cooperate with each other, thereby improving the operational efficiency, operational stability and resource utilization of the warehousing system. Attached Figure Description

[0009] Other features, objects, and advantages of the invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings: Figure 1This is a flowchart illustrating the steps of the collaborative decision-making method for intelligent warehousing equipment based on digital twins according to the present invention. Figure 2 This is a schematic diagram of the structure of the digital twin collaborative network in an embodiment of the present invention; Figure 3 This is a block diagram of the intelligent warehousing equipment collaborative decision-making system based on digital twins in this invention; The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0010] The technical method of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0011] Furthermore, the accompanying drawings are merely illustrative of the invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor methods and / or microcontroller methods.

[0012] It should be understood that although the terms "first," "second," etc., may be used herein to describe various units, these units should not be limited by these terms. These terms are used merely to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, a first unit may be referred to as a second unit, and similarly, a second unit may be referred to as a first unit. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0013] To achieve the above objectives, please refer to Figures 1 to 3 This invention provides a collaborative decision-making method for intelligent warehousing equipment based on digital twins, the method comprising the following steps: Step S1: Collect sensor data of warehousing equipment and determine the overall distribution structure of warehousing equipment based on the location information of each piece of warehousing equipment in the sensor data. In this embodiment, sensing units deployed on each storage equipment synchronously collect spatial coordinate data, operating status signals, and operation execution signals of each storage equipment at a sampling period of 1 second. Then, the coordinate data within 10 consecutive sampling periods are subjected to time-series smoothing to eliminate instantaneous jitter errors. Then, the identifiers of the same operating status signals are used as clustering conditions to spatially merge the coordinate points of similar equipment, determine the spatial distribution range and relative positional relationship of various types of storage equipment, and thus form an overall distribution structure.

[0014] Step S2: Determine the interaction depth between warehousing equipment based on the correlation degree of sensor signals between warehousing equipment in the warehousing equipment sensor data; In a further embodiment, the sequence of operating status changes and the time stamps of job execution triggers for two storage equipment that are determined to operate in the same mode within the same sampling period are extracted over eight consecutive sampling periods. First, the consistency ratio of the direction of status changes in adjacent periods is compared in chronological order, and then the time deviation value between the corresponding job instruction trigger timestamps is calculated. Subsequently, the consistency ratio of status and the time deviation are weighted and integrated at a ratio of 0.6:0.4 to obtain the correlation degree of the sensor signal that characterizes the degree of correlation of the equipment.

[0015] Step S3: Based on the interaction depth between warehousing equipment, connect the collaborative relationship lines between warehousing equipment in the overall distribution structure of warehousing equipment to construct a digital twin collaborative network. In a further embodiment, each device in the overall distribution structure of the warehousing equipment is used as a node. Device pairs that are determined to have deep interaction relationships are connected by solid lines according to their spatial location, while other device pairs that have interaction relationships but do not meet the deep conditions are connected by dashed lines. Subsequently, the solid and dashed line connections in the same warehousing area are uniformly superimposed, so that the device nodes and collaborative connection relationships are presented synchronously in the same structure, thereby forming a digital twin collaborative network.

[0016] Step S4: Use the digital twin collaborative network to determine the load changes of each warehouse equipment, and filter the overload relationship lines in the digital twin collaborative network according to the load changes; In a further embodiment, the sensing units on each warehousing equipment in the digital twin collaborative network are used to synchronously read the operating load value of each node warehousing equipment in each sampling period, and compare it with the load average value of the corresponding equipment in the past 30 sampling periods to calculate the load increment per unit time. When the load increment of any equipment exceeds the historical average value of its collaborative relationship line, the relationship line is first marked as a potential abnormal line. Then, the load increment is weighted and integrated by combining the average state synchronization coefficient of the equipment at both ends of the relationship line under the same operating mode, and sorted according to the weighted result to obtain the overload relationship line.

[0017] Step S5: Based on the operational coupling strength between the overload relationship line and the adjacent collaborative relationship line, coordinately adjust the load status of each storage equipment in the overload relationship line.

[0018] In a further embodiment, the current load values ​​of the storage equipment at both ends of the overload relationship line and their historical load distribution ranges are extracted respectively, and the load response difference of each equipment per unit time is calculated. Then, based on the proportion of the load response difference of each equipment to the total difference of the relationship line, the workload of the corresponding equipment is synchronously reduced or transferred. During the adjustment process, five consecutive sampling periods are used as an iteration window. When the load response difference of each equipment on the overload relationship line shows a continuous shrinking trend and tends to stabilize, the current round of collaborative load adjustment process ends.

[0019] Of particular importance is the construction of a digital twin collaborative network, which includes: The solid lines of collaborative relationships are converted into the first connection matrix, and the dashed lines of collaborative relationships are converted into the second connection matrix. By treating each piece of warehousing equipment as a node, the first connection matrix and the second connection matrix are superimposed according to the same node index to obtain a digital twin collaborative network.

[0020] In this embodiment, the unique equipment number of each warehousing equipment is used as the node identifier, and its spatial coordinates in the overall distribution structure are used as the initial position of the node. Then, the solid lines and dashed lines of the collaborative relationship are converted into two sets of connection relationship matrices, where the solid lines correspond to the first connection matrix and the dashed lines correspond to the second connection matrix. The two sets of connection matrices are then superimposed element by element according to the same node index to form a unified connection structure that simultaneously contains information on strong and weak collaborative relationships. The superimposed result is synchronously refreshed with an update cycle of 2 seconds, thereby obtaining the digital twin collaborative network.

[0021] Optionally, step S1, determining the overall distribution structure of the warehousing equipment, includes: Extract the location information and operating status information of each piece of warehousing equipment from the sensor data of the warehousing equipment; In this embodiment, the planar coordinate values ​​and operating status parameters of each storage equipment are extracted from the sensing data of the storage equipment, and the data within 12 consecutive sampling periods are processed by moving average to eliminate instantaneous jitter error.

[0022] Based on the operational status information of warehousing equipment, the target of equipment operation and operating mode are determined to classify several equipment types; among which, the operating modes include continuous operation mode and discrete operation mode; In a further embodiment, the displacement change amplitude and operation command triggering interval of each device are statistically analyzed over 10 consecutive sampling periods. When the device displacement change shows a continuous small increase and the command triggering interval is consistently less than 3 seconds, it is determined that the device is a conveying device and is marked as a continuous operation mode. When the displacement changes intermittently and the command interval is greater than the duration of a single execution, it is determined that the device is a sorting device and is marked as a discrete operation mode. A device classification rule table is constructed based on the combination relationship between the object category and the operation mode, with the continuous operation mode corresponding to the conveying object and the discrete operation mode corresponding to the sorting or loading / unloading object serving as the basic classification unit. Subsequently, the classification rule table is matched one by one for all warehousing equipment based on the condition of "consistent object and consistent operation mode". When two or more devices meet the same combination condition, they are classified into the same device type number. When devices have the same operation mode but different objects, a new device type number is formed separately, thus obtaining several device type sets.

[0023] It is worth noting that the determination result of the target object can be corroborated by the device number or text information in the operating status parameters.

[0024] Based on the location information of the warehousing equipment, spatial clustering is performed on warehousing equipment of the same type to determine the spatial distribution range of each type of equipment, thereby generating the overall distribution structure of the warehousing equipment.

[0025] In a further embodiment, the spatial coordinate set of the corresponding equipment is extracted using the same equipment type as the merging condition, and the coordinate points of the same type of equipment are spatially merged with the distance between adjacent equipment not exceeding 5m as the aggregation constraint, so as to obtain the distribution boundary and center position (spatial distribution range) of various types of equipment in the warehousing environment; then the distribution boundaries of various types of equipment are superimposed and displayed according to a unified coordinate system, thereby forming the overall distribution structure of warehousing equipment.

[0026] Optionally, determining the operating mode includes: Read the displacement change sequence, operation instruction trigger timestamp, and execution completion time of each piece of warehousing equipment in the current sampling period from the warehousing equipment operation status information; In this embodiment, the cumulative spatial displacement of the device within the current sampling period is continuously read from the operating status parameters with a minimum sampling interval of 0.2s, and the trigger time and execution completion feedback time of the corresponding operation instruction are read from the device control interface simultaneously; then the above data are stored one by one according to the device number.

[0027] The motion continuity of warehousing equipment within adjacent sampling periods is calculated based on displacement change sequences, and the operation response delay is calculated based on the operation instruction trigger timestamp and execution completion time. In a further embodiment, the cumulative displacement within two adjacent sampling periods is differentially calculated. When the displacement direction is consistent for five consecutive periods and the increment fluctuation does not exceed ±8%, a displacement difference sequence is formed; otherwise, the motion continuity is determined to be sporadic motion. The displacement difference sequence is further statistically analyzed using a sliding window with a window length of K = 6 sampling points. If the standard deviation of the displacement increment within the window is less than the fluctuation threshold of 0.15 mm, and the consistency ratio of the displacement change direction is not less than 80%, the time period corresponding to the sliding window is marked as a high consistency interval. Based on this, the proportion of the high consistency interval to the total duration of the current analysis period is used as the motion continuity evaluation value. Simultaneously, the time difference between the trigger time and the completion time of the work instruction is used as the single work response delay, and the average delay of 10 consecutive work instructions is used as the response delay parameter for that period.

[0028] If the continuity of movement of any warehousing equipment is greater than the preset continuous movement threshold and the operation response delay is less than the preset fast response threshold, the warehousing equipment is determined to be in continuous operation mode. If the motion continuity of any warehousing equipment is less than the continuous motion threshold and the time difference between the trigger timestamps of adjacent operation instructions exceeds the execution completion time, then the warehousing equipment is determined to be in discrete operation mode.

[0029] In a further embodiment, when the evaluation value corresponding to motion continuity is greater than the continuous motion threshold of 0.75 and the operation response delay is consistently less than 2 seconds, the device is marked as having continuous operation characteristics; when the displacement change is less than the continuous motion threshold of 0.75 and the interval between operation instructions is generally greater than the time required to complete a single execution, the device is marked as having discrete operation characteristics, thereby completing the differentiation and labeling of the device's operating mode.

[0030] Optionally, the method for obtaining the correlation degree of the sensing signals in step S2 includes: Based on the sensor data of the warehousing equipment, we can select warehousing equipment pairs that operate in the same mode within the same sampling period and that have uploaded corresponding operating status signals and operation execution signals. In this embodiment, all equipment pairs are screened from the sensor data of the warehousing equipment. It is required that the two equipment operate in the same mode for five consecutive sampling periods and upload synchronized operating status signals and operation execution signals. The equipment pairs that meet the conditions are recorded in the warehousing equipment pair list by matching the equipment numbers.

[0031] The consistency of the status changes of the two storage equipment in adjacent sampling periods is calculated based on the operating status signal, and the trigger time difference of the two storage equipment at the corresponding operation instruction trigger timestamp is calculated based on the operation execution signal. In a further embodiment, the continuous displacement sequences of each pair of devices in the operating status signal are timestamped and aligned; then, within a sliding window of N=5 consecutive sampling periods, the state changes (e.g., moving / stationary) of the two devices in each period are compared point by point. When the states are completely consistent, it is recorded as 1, and when they are inconsistent, it is recorded as 0; the arithmetic mean of all comparison results within the sliding window is used to obtain the state change consistency score. The value ranges from 0 to 1; simultaneously, the absolute time difference between the trigger timestamps of the corresponding job instructions is calculated. And take its reciprocal as the trigger synchronization degree in order to quantify the synchronization response characteristics.

[0032] The correlation degree of the sensor signal is obtained by weighting the consistency of state change and the trigger time difference.

[0033] In a further embodiment, the state change consistency score Synchronization with trigger All calculations have been completed, so proceed according to the preset weight ratio. ,Will and Perform linear weighting: Generate the correlation of sensor signals for each pair of warehousing equipment. .

[0034] Optionally, determining the interaction depth between warehousing equipment in step S2 includes: The system detects the changes in sensor correlation of warehousing equipment within a continuous sampling period and calculates the correlation stability coefficient per unit time based on the changes in sensor correlation. In this embodiment, the sliding window length is used. ( Using 6 consecutive sampling periods as the unit, the standard deviation of the sensor correlation variation was calculated. with the mean Calculate the correlation stability coefficient per unit time. The numerical value ranges from 0 to 1, reflecting the device's interaction stability within the current analysis cycle; if the sequence length is insufficient... Then it is calculated based on the available data length.

[0035] The number of interlocks triggered by operational instructions and the number of status synchronization responses between warehouse equipment are synchronously counted using sensor data of warehouse equipment to determine the status synchronization coefficient. In a further embodiment, the synchronization statistics device counts the number of times the operation instructions of the two storage equipment are triggered by interlocking. The interlock ratio R_lock = N_lock / total number of work instructions and the state response ratio R_sync = N_sync / total number of state responses are calculated respectively. The arithmetic mean of R_lock and R_sync is then taken and processed accordingly to obtain the state synchronization coefficient of the device under the current operating mode. The range is 0 to 1. The method for obtaining the number of interlock triggers by work instructions is to count the number of events in a continuous sampling period where the work execution status identifiers of two devices simultaneously change under the same work instruction. The method for obtaining the number of status synchronization responses is to count the status changes of the two devices in a continuous sampling period; complete consistency is recorded as one status synchronization response.

[0036] Storage equipment pairs whose correlation stability coefficient and state synchronization coefficient fluctuate within a preset stable range during continuous sampling periods are identified as having a deep interaction relationship; otherwise, they are identified as having a shallow interaction relationship.

[0037] In a further embodiment, the fluctuation amplitude of both is monitored within a continuous sampling period. , ,when and When the fluctuation amplitude exceeds the above value, the device is determined to have a deep interaction relationship; when any fluctuation amplitude exceeds the above value, it is determined to have a shallow interaction relationship.

[0038] Optionally, determining the state synchronization coefficient of the storage equipment pair includes: If all the storage equipment in a storage equipment pair is in continuous operation mode, the ratio of the number of state synchronization responses to the total number of state responses of each storage equipment is calculated within the continuous sampling period; the arithmetic mean of the state synchronization response ratios is taken as the state synchronization coefficient of the corresponding storage equipment pair. In one embodiment, if both devices in a storage equipment pair are in continuous operation mode within a continuous sampling period, the state response sequence of each device within N=5 consecutive sampling periods is statistically analyzed, and the ratio of the number of state synchronization responses N_sync to the total number of state responses N_total of that device is calculated as R_sync=N_sync / N_total; then, the arithmetic mean of R_sync of the two devices in the equipment pair is taken as the state synchronization coefficient S_sync of the equipment pair, which is limited to a range of 0~1.

[0039] If all the storage equipment in the storage equipment pair is in discrete operation mode, calculate the average time difference of state switching between the storage equipment pair before and after the trigger timestamp of the same operation instruction; at the same time, count the number of interlocks triggered by operation instructions for each storage equipment and the total number of operation instructions triggered, so as to calculate the interlock trigger ratio of the corresponding storage equipment. Take the arithmetic mean of the interlock trigger ratios corresponding to the storage equipment, and multiply the arithmetic mean of the interlock trigger ratios by the reciprocal of the mean of the state switching time difference. The result of this multiplication is the state synchronization coefficient.

[0040] In another embodiment, if two devices in a warehousing equipment pair are both in discrete operation mode within a continuous sampling period, the state switching time difference before and after the trigger timestamp of the same work instruction for each device is considered. Perform statistical analysis and calculate the mean; simultaneously, calculate the interlock trigger count N_lock and the total number of work command triggers N_total for each of the two devices, and calculate the interlock trigger ratio R_lock = N_lock / N_total; then, take the arithmetic mean of R_lock for the two devices in the pair, and compare this mean with... Multiplying the reciprocals of the mean yields the final state synchronization coefficient S_sync.

[0041] It is worth noting that the total number of status responses refers to the total number of status changes (including start-up, stop, and work completion) for each piece of warehousing equipment within the same sampling period. This can be directly calculated by counting the total number of status change events for a single piece of equipment over N consecutive sampling periods (e.g., 5), without considering the status of other equipment. The method for obtaining the time difference between status transitions before and after the work instruction trigger timestamp includes using the work instruction trigger timestamp... And the time of change in the status of the corresponding equipment when it actually starts performing the operation. and completion time Calculate the switching time The job start response time is - The total number of job instruction triggers is counted as the total number of events in which each device receives job instructions within a continuous sampling period, regardless of whether it is coordinated with another device.

[0042] Optionally, the collaboration relationship line includes a solid collaboration relationship line and a dashed collaboration relationship line; wherein the method for obtaining the collaboration relationship line in step S3 includes: The solid lines connect the warehousing equipment whose operating modes are determined to have deep interaction relationships in the overall distribution structure of warehousing equipment, and these solid lines are used as the solid lines of the collaborative relationship between warehousing equipment. The storage equipment that is determined to have a deep interaction relationship with less than two operating modes is connected by a dashed line, and this dashed line is used as the collaborative relationship dashed line between the storage equipment.

[0043] In this embodiment, the results of determining the operating mode of each pair of warehousing equipment in the overall distribution structure of the warehousing equipment within a continuous sampling period are summarized and statistically analyzed. When a pair of equipment is determined to have a deep interaction relationship under all operating modes, the pair of equipment is connected by a solid line in the digital twin collaborative network. The line width of the solid line is set to 2px to represent a relationship with high collaboration strength. At the same time, the node ID and edge weight value Edge_weight=1.0 are recorded in the network data structure. When a pair of equipment is determined to have a deep interaction relationship under fewer than two operating modes, the pair of equipment is connected by a dashed line. The dashed line width is 1px, the line type is set to 5px, and the solid line is spaced 3px apart to represent a relationship with low collaboration strength. The node ID and edge weight value Edge_weight=0.5 are recorded in the network data structure. By uniformly aggregating and superimposing the solid and dashed lines of each pair of equipment in the network topology, a complete collaborative relationship map can be formed. The edge weight can be the average state synchronization coefficient between the warehousing equipment pairs under each operating mode.

[0044] Optionally, the screening of overloaded relationship lines in the digital twin collaborative network in step S4 includes: If the unit time load increment of any warehousing equipment in the digital twin collaborative network exceeds the historical load change average of the corresponding collaborative relationship line, then the collaborative relationship line corresponding to that warehousing equipment is marked as a potential overload relationship line. By combining the average state synchronization coefficient of each storage equipment, the load increment of the storage equipment at both ends of the potential overload relationship line is weighted and calculated to obtain the comprehensive load response index. Based on the ranking results of the comprehensive load response index of each potential overload relationship line, the overload relationship lines are selected.

[0045] In this embodiment, the load increment per unit time is calculated for the warehousing equipment at both ends of each collaborative relationship line in the digital twin collaborative network within a continuous sampling period. When either end device Exceeding the historical average load change of the corresponding collaborative relationship line (e.g., the average of the past 30 sampling periods). When this happens, the collaborative relationship line is marked as a potential overload relationship line; subsequently, the average state synchronization coefficient of the storage equipment at both ends of the potential overload relationship line is obtained. and the load increment at both ends ( 1. According to the average of the status synchronization coefficients of each storage equipment ( , The weighted calculation is performed to obtain the comprehensive load response index. For all potential overload relationship lines The values ​​are sorted, and the top N collaborative relationship lines (N can be set to 20% of the total number of edges in the network) are selected as the final overload relationship lines.

[0046] It is worth noting that in a digital twin collaborative network, each node corresponds to a piece of warehousing equipment and records its historical load data (such as the amount of work or energy consumption per unit time). The load increment per unit time... It can be obtained by calculating the difference in node load values ​​within a continuous sampling period: ;in, This represents the node load value within the current sampling period. This represents the node load value from the previous sampling period. The edges (cooperation relationship lines) in the network will... The value is associated with both ends of the node and is used to determine whether there is an overload trend in the corresponding collaborative relationship line.

[0047] Of particular importance are the methods for obtaining the average state synchronization coefficient of each storage equipment, including: The average initial synchronization coefficient of each warehousing equipment with other warehousing equipment under the same operating mode is calculated. Calculate the difference between the average initial synchronization coefficients of the storage equipment at both ends of the collaborative relationship line, use this difference as an adjustment factor for the storage equipment at both ends of the collaborative relationship line, and weight and merge it with the original average initial synchronization coefficient of each storage equipment to obtain the average state synchronization coefficient of each storage equipment.

[0048] In this embodiment, for each collaborative relationship line, the average initial synchronization coefficients corresponding to the storage equipment at both ends are extracted, and the difference between the two is calculated. ;Should This serves as a synchronization adjustment factor for the storage equipment at both ends of the collaborative relationship. Finally, the synchronization adjustment factor is weighted and merged with the average of the original initial synchronization coefficients of each storage equipment according to a ratio of 0.6:0.4 to obtain the average state synchronization coefficient after merging.

[0049] It is worth noting that the purpose of calculating the adjustment factor is to quantify the difference in the initial state synchronization level between the storage equipment at both ends of the collaborative relationship line. This difference allows for the correction or weighted fusion of the original synchronization coefficients, ensuring that the state synchronization coefficient of each storage equipment not only reflects its average synchronization with other equipment but also takes into account its relative synchronization difference with directly collaborating equipment. This more accurately describes the actual collaborative capability of the equipment in the network, supporting more refined load allocation and job scheduling decisions.

[0050] This is the average state synchronization coefficient of each storage equipment with other storage equipment under the same operating mode.

[0051] Optionally, the coordinated adjustment of the load status of each storage equipment in the overload relationship line in step S5 includes: The load response difference of each storage equipment per unit time is calculated based on the current load and historical load distribution of the storage equipment at both ends of the overload relationship line. Based on the load response differences, the operating tasks of each storage equipment on the overload relationship line are adjusted iteratively according to the proportion of the load response differences of each storage equipment to the total differences of the overload relationship line, until the load response differences of each storage equipment on the overload relationship line converge within the continuous sampling period.

[0052] In this embodiment, for each overload relationship line, the current load of the storage equipment at both ends is read. Historical load distribution within past consecutive sampling periods (For example, the load mean and variance over the most recent 30 sampling periods), calculate the load response difference of each storage equipment per unit time: ; then, The total difference in the overload relationship line accounts for ( and The ratio of the load response difference between the two ends of the warehousing equipment is used as the collaborative adjustment weight. The workload of the two ends of the equipment is iteratively adjusted, that is, the workload is updated. ,in To adjust the step size coefficient (which can be set from 0.1 to 0.3), The original workload is used; it is recalculated after each iteration. And update Repeat the above iterative process to monitor within the continuous sampling period. Change, until Load response convergence is considered complete when both ends of the load are less than 0.05 times the historical load standard deviation.

[0053] Optionally, this application also provides a digital twin-based intelligent warehousing equipment collaborative decision-making system for executing the digital twin-based intelligent warehousing equipment collaborative decision-making method described above. The digital twin-based intelligent warehousing equipment collaborative decision-making system 100 includes: The data acquisition module 101 is used to collect sensor data of the warehousing equipment and determine the overall distribution structure of the warehousing equipment based on the location information of each piece of warehousing equipment in the sensor data. The interaction depth analysis module 102 is used to determine the interaction depth between warehousing equipment based on the correlation degree of the sensing signals between warehousing equipment in the warehousing equipment sensing data. The digital twin construction module 103 is used to connect the collaborative relationship lines between the warehousing equipment in the overall distribution structure of the warehousing equipment according to the interaction depth between the warehousing equipment, so as to construct a digital twin collaborative network. The overload screening module 104 is used to determine the load changes of each storage equipment using a digital twin collaborative network, and to screen the overload relationship lines in the digital twin collaborative network based on the load changes. The overload optimization module 105 is used to coordinately adjust the load of each storage equipment in the overload relationship line according to the operational coupling strength between the overload relationship line and the adjacent collaborative relationship line.

[0054] Figure 2 This is a schematic diagram of the structure of the digital twin collaborative network in an embodiment of the present invention; as shown below. Figure 2 As shown, blue nodes represent AGV measurement devices, which are automated guided vehicle (AGV) transport equipment responsible for moving goods within the warehouse space. Orange nodes represent simulators and conveyor line equipment, which are operation execution equipment responsible for handling and transporting goods. Green nodes represent shelves, sorting equipment, picking equipment, and packaging equipment, which are warehouse operation equipment responsible for storage, sorting, picking, and packaging operations.

[0055] Solid green lines represent collaborative relationships between warehousing equipment that are considered to have a deep interaction, indicating that the load, status, or task of the two ends of the equipment is highly correlated during operation. Dashed blue lines represent collaborative relationships between warehousing equipment that are considered to have a shallow interaction, indicating that the collaborative effect between the two ends of the equipment is weak or indirect during operation.

[0056] Furthermore, the diagram shows the following relationships: Shelf → Sorting Equipment: Solid line, indicating deep collaboration, with goods moving from the shelf to the sorting equipment being the primary operational path. Sorting Equipment → Picking Equipment: Solid line, indicating deep collaboration, showing that picking operations occur directly after sorting. Picking Equipment → Packaging Equipment: Solid line, indicating deep collaboration, with packaging operations starting immediately after picking. AGV Measurement Equipment → Conveyor Line Equipment: Solid line, indicating deep collaboration, with AGVs and conveyors directly coordinating transport. AGV Measurement Equipment → Simulator Equipment, AGV → Sorting Equipment, Conveyor Line → Picking Equipment: Dashed line, indicating shallow collaboration, suggesting low operational correlation or delays / indirect impacts between them.

[0057] The diagram clearly shows the type of each warehousing equipment and its collaborative strength through node colors and edge types. It can intuitively reflect the deep and shallow interaction relationships between devices in the digital twin collaborative network, which is helpful for load analysis and job scheduling optimization.

[0058] Therefore, the embodiments should be considered as exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of the equivalents of the application are intended to be included within the invention.

[0059] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features of the invention herein.

Claims

1. A collaborative decision-making method for intelligent warehousing equipment based on digital twins, characterized in that, Includes the following steps: Step S1: Collect sensor data of warehousing equipment and determine the overall distribution structure of warehousing equipment based on the location information of each piece of warehousing equipment in the sensor data. Step S2: Determine the interaction depth between warehousing equipment based on the correlation degree of sensor signals between warehousing equipment in the warehousing equipment sensor data; Step S3: Based on the interaction depth between warehousing equipment, connect the collaborative relationship lines between warehousing equipment in the overall distribution structure of warehousing equipment to construct a digital twin collaborative network. Step S4: Use the digital twin collaborative network to determine the load changes of each warehouse equipment, and filter the overload relationship lines in the digital twin collaborative network according to the load changes; Step S5: Based on the operational coupling strength between the overload relationship line and the adjacent collaborative relationship line, coordinate and adjust the load status of each storage equipment in the overload relationship line; The method for obtaining the correlation degree of the sensing signals in step S2 includes: Based on the sensor data of the warehousing equipment, we can select warehousing equipment pairs that operate in the same mode within the same sampling period and that have uploaded corresponding operating status signals and operation execution signals. The consistency of the status changes of the two storage equipment in adjacent sampling periods is calculated based on the operating status signal, and the trigger time difference of the two storage equipment at the corresponding operation instruction trigger timestamp is calculated based on the operation execution signal. The correlation degree of the sensor signal is obtained by weighting the consistency of state change and the trigger time difference. Determining the interaction depth between warehousing equipment in step S2 includes: The system detects the changes in sensor correlation of warehousing equipment within a continuous sampling period and calculates the correlation stability coefficient per unit time based on the changes in sensor correlation. The number of interlocks triggered by operational instructions and the number of status synchronization responses between warehouse equipment are synchronously counted using sensor data of warehouse equipment to determine the status synchronization coefficient. Storage equipment pairs whose correlation stability coefficient and state synchronization coefficient fluctuate within a preset stable range during a continuous sampling period are identified as having a deep interaction relationship; otherwise, they are identified as having a shallow interaction relationship. Step S4 involves filtering overloaded relationship lines in the digital twin collaborative network, including: If the unit time load increment of any warehousing equipment in the digital twin collaborative network exceeds the historical load change average of the corresponding collaborative relationship line, then the collaborative relationship line corresponding to that warehousing equipment is marked as a potential overload relationship line. By combining the average state synchronization coefficient of each storage equipment, the load increment of the storage equipment at both ends of the potential overload relationship line is weighted and calculated to obtain the comprehensive load response index. Based on the ranking results of the comprehensive load response index of each potential overload relationship line, the overload relationship lines are selected.

2. The collaborative decision-making method for intelligent warehousing equipment based on digital twins according to claim 1, characterized in that, Step S1, determining the overall distribution structure of the warehousing equipment, includes: Extract the location information and operating status information of each piece of warehousing equipment from the sensor data of the warehousing equipment; Based on the operational status information of warehousing equipment, the target of equipment operation and operating mode are determined to classify several equipment types; among which, the operating modes include continuous operation mode and discrete operation mode; Based on the location information of the warehousing equipment, spatial clustering is performed on warehousing equipment of the same type to determine the spatial distribution range of each type of equipment, thereby generating the overall distribution structure of the warehousing equipment.

3. The collaborative decision-making method for intelligent warehousing equipment based on digital twins according to claim 2, characterized in that, Determining the operating mode includes: Read the displacement change sequence, operation instruction trigger timestamp, and execution completion time of each piece of warehousing equipment in the current sampling period from the warehousing equipment operation status information; The motion continuity of warehousing equipment within adjacent sampling periods is calculated based on displacement change sequences, and the operation response delay is calculated based on the operation instruction trigger timestamp and execution completion time. If the continuity of movement of any warehousing equipment is greater than the preset continuous movement threshold and the operation response delay is less than the preset fast response threshold, the warehousing equipment is determined to be in continuous operation mode. If the motion continuity of any warehousing equipment is less than the continuous motion threshold and the time difference between the trigger timestamps of adjacent operation instructions exceeds the execution completion time, then the warehousing equipment is determined to be in discrete operation mode.

4. The collaborative decision-making method for intelligent warehousing equipment based on digital twins according to claim 1, characterized in that, Determining the state synchronization coefficient of the storage equipment pair includes: If all the storage equipment in a storage equipment pair is in continuous operation mode, the ratio of the number of state synchronization responses to the total number of state responses of each storage equipment is calculated within the continuous sampling period; the arithmetic mean of the state synchronization response ratios is taken as the state synchronization coefficient of the corresponding storage equipment pair. If all the storage equipment in the storage equipment pair is in discrete operation mode, calculate the average time difference of state switching between the storage equipment pair before and after the trigger timestamp of the same operation instruction; at the same time, count the number of interlocks triggered by operation instructions for each storage equipment and the total number of operation instructions triggered, so as to calculate the interlock trigger ratio of the corresponding storage equipment. Take the arithmetic mean of the interlock trigger ratios corresponding to the storage equipment, and multiply the arithmetic mean of the interlock trigger ratios by the reciprocal of the mean of the state switching time difference. The result of this multiplication is the state synchronization coefficient.

5. The collaborative decision-making method for intelligent warehousing equipment based on digital twins according to claim 1, characterized in that, The lines representing collaborative relationships include solid lines and dashed lines representing collaborative relationships; The method for obtaining the collaborative relationship line in step S3 includes: The solid lines connect the warehousing equipment whose operating modes are determined to have deep interaction relationships in the overall distribution structure of warehousing equipment, and these solid lines are used as the solid lines of the collaborative relationship between warehousing equipment. The storage equipment that is determined to have a deep interaction relationship with less than two operating modes is connected by a dashed line, and this dashed line is used as the collaborative relationship dashed line between the storage equipment.

6. The collaborative decision-making method for intelligent warehousing equipment based on digital twins according to claim 1, characterized in that, Step S5 involves coordinating the adjustment of the load status of each storage equipment in the overload relationship line, including: The load response difference of each storage equipment per unit time is calculated based on the current load and historical load distribution of the storage equipment at both ends of the overload relationship line. Based on the load response differences, the operating tasks of each storage equipment on the overload relationship line are adjusted iteratively according to the proportion of the load response differences of each storage equipment to the total differences of the overload relationship line, until the load response differences of each storage equipment on the overload relationship line converge within the continuous sampling period.

7. A collaborative decision-making system for intelligent warehousing equipment based on digital twins, characterized in that, For executing the collaborative decision-making method for intelligent warehousing equipment based on digital twins as described in claim 1, the collaborative decision-making system for intelligent warehousing equipment based on digital twins includes: The data acquisition module is used to collect sensor data from warehousing equipment and determine the overall distribution structure of warehousing equipment based on the location information of each piece of warehousing equipment in the sensor data. The interaction depth analysis module is used to determine the interaction depth between warehousing equipment based on the correlation degree of sensor signals between warehousing equipment in the sensor data of warehousing equipment. The digital twin building module is used to connect the collaborative relationship lines between warehousing equipment in the overall distribution structure of warehousing equipment according to the interaction depth between warehousing equipment, so as to build a digital twin collaborative network. The overload screening module is used to determine the load changes of each warehouse equipment using a digital twin collaborative network, and to screen the overload relationship lines in the digital twin collaborative network based on the load changes. The overload optimization module is used to coordinately adjust the load of each storage equipment in the overload relationship line based on the operational coupling strength between the overload relationship line and the adjacent collaborative relationship line.

Images