A warehouse park operation and maintenance management system and method based on digital twins

Abstract

This invention relates to the field of warehouse management technology, specifically a warehouse park operation and maintenance management method based on digital twins. It constructs a digital twin model using collected shelf location data and cargo data to achieve visualized data management. AGVs execute inbound and outbound operations according to pre-planned optimal routes, verifying the weight changes of the target shelves after the operations are completed to determine if any anomalies have occurred, thus ensuring the accuracy of the inbound and outbound operation process. The Dragonfly Algorithm is used to find the optimal temperature and humidity, simulating the collective activity of dragonflies in nature to construct a mathematical model, effectively avoiding the optimization results from getting stuck in local optima. The method determines whether each temperature and humidity data point in the collected dataset is within the optimal temperature and humidity range, analyzes the temperature and humidity status of each shelf, and achieves real-time monitoring of the temperature and humidity of the warehouse park, ensuring the rational operation of the park.

Description

Technical Field

[0001] This invention relates to the field of warehouse management technology, specifically a warehouse park operation and maintenance management method based on digital twins. Background Technology

[0002] Digital twin technology involves mapping various types of collected data in a virtual space to build a digital twin model, which is then used to monitor and manage physical facilities in real time.

[0003] Chinese invention patent application CN112990820A describes a warehouse management system based on digital twins. By sending the location status information and cargo information collected by the information acquisition module to the server, the system displays the information in the digital twin. When cargo is received, the system locates the storage location of the cargo in the digital twin and updates the cargo information after the receiving is completed, thus achieving reasonable warehouse management. However, the system does not perform route planning during the warehousing process, which cannot improve the speed and efficiency of inbound and outbound operations. At the same time, it does not monitor the environment in the warehouse park in real time, which cannot avoid cargo damage caused by unreasonable warehousing conditions. Summary of the Invention

[0004] (1) Technical problems solved

[0005] To address the shortcomings of the prior art, this invention proposes a digital twin-based operation and maintenance management method for warehouse parks, enabling real-time monitoring of the warehouse parks and ensuring their proper operation.

[0006] (2) Technical solution

[0007] A warehouse park operation and maintenance management method based on digital twins includes the following steps:

[0008] S1. Collect the location data of each shelf in the warehouse park and the goods data stored on each shelf. Based on the location data and the goods data, construct a digital twin model using a 3D modeling tool.

[0009] S2. When inbound and outbound operations are required, collect inbound and outbound goods data, locate the target shelf in the digital twin model based on the inbound and outbound goods data, determine the AGV vehicle to perform the inbound and outbound operations, and plan the optimal movement route in the digital twin model.

[0010] S3. Send instructions to the AGV vehicle, and the AGV vehicle performs the inbound and outbound operations according to the planned optimal route. After the inbound and outbound operations are completed, collect the weight change data of the target shelf and compare it with the weight data of the inbound and outbound goods to determine whether there is any abnormality in the inbound and outbound operations.

[0011] S4. Intelligent management of environmental parameters in the warehousing park through sensors.

[0012] This invention constructs a digital twin model using collected shelf location and cargo data to achieve visualized data management. AGVs execute inbound and outbound operations according to pre-planned optimal routes, collecting weight changes on the target shelves after each operation and comparing these changes with the weight data of the inbound and outbound goods to determine if any anomalies occurred, ensuring the accuracy of the inbound and outbound operation process. The invention also employs a dragonfly algorithm to find optimal temperature and humidity, simulating the collective activity of dragonflies in nature to construct a mathematical model that effectively avoids getting stuck in local optima. Finally, it sequentially checks whether each temperature and humidity data point in the collected dataset falls within the optimal temperature and humidity range, analyzing the temperature and humidity status of each shelf based on the results, achieving real-time monitoring of the temperature and humidity in the warehouse park and ensuring its efficient operation.

[0013] Preferably, the specific steps for collecting location data of each shelf within the warehouse park and data on the goods stored on each shelf, and then constructing a digital twin model using a 3D modeling tool based on the location data and the goods data, are as follows:

[0014] S11. Collect the location data of each shelf in the warehouse park to obtain the shelf location dataset A = {a1, a2, ..., a i ,…,a k}, where a i This represents the location data of the i-th shelf, and k represents the total number of shelf location data.

[0015] S12. Define the cargo data type set B = {b1, b2, ..., b} i ,…,b l}, where b i Let represent the i-th type of cargo data that needs to be collected, and l represent the total number of cargo data types;

[0016] S13. Scan the RFID tags of goods stored on each shelf using a wireless frequency scanning device to collect the goods data, and obtain the goods data matrix B as follows:

[0017]

[0018] Among them, b ij This represents the data of the j-th type of goods that need to be collected, which are stored on the i-th shelf.

[0019] S14. Based on the shelf location dataset A and the cargo data matrix B, construct a digital twin model using a 3D modeling tool.

[0020] By collecting shelf location data and goods data, a digital twin model is built to achieve visualized data management.

[0021] Preferably, when inbound and outbound operations are required, the following steps are taken to collect inbound and outbound goods data, locate the target shelf in the digital twin model based on the inbound and outbound goods data, determine the AGV (Automated Guided Vehicle) to perform the inbound and outbound operations, and plan the optimal route in the digital twin model:

[0022] S21. When performing inbound and outbound operations, collect inbound and outbound goods data, and locate the target shelf in the digital twin model based on the inbound and outbound goods data.

[0023] S22. Determine the AGV vehicle to perform the inbound and outbound operations, and plan the optimal route in the digital twin model based on the location of the target shelf;

[0024] S221. Draw a grid map based on the terrain of the warehouse park;

[0025] S222. Construct an ant colony, setting the population size to N, the current iteration number to t, and the maximum iteration number to t. max The pheromone evaporation coefficient is ρ, the total amount of pheromones is Q, the pheromone weighting factor is α, and the heuristic information weighting factor is β;

[0026] Set the start and end positions in the grid map, put N ants at the start position to search for paths, set a taboo list for each ant, and take the grid positions of all shelves and the start position as taboo nodes. The individual ants will not move to the taboo nodes during the path search process.

[0027] S223. Each ant in the ant colony traverses from its starting position, calculating the probability of entering each accessible grid cell according to the probability transition formula. A roulette wheel is used to select the next grid cell for each ant to move to. Once an ant moves to a new grid cell, the new grid cell position is added to that ant's taboo list. The probability transition formula is as follows:

[0028]

[0029] in, This represents the probability that the x-th ant travels from grid node i to grid node j, allowed. x s represents the set of all grid nodes that the x-th ant can choose in the next iteration; s represents the set allowed. x Any node in τ; ij (t) represents the pheromone concentration from grid node i to grid node j during the t-th iteration; η ij(t) represents the expected degree of progress from grid node i to grid node j during the t-th iteration;

[0030] set up Where, d ij This represents the Euclidean distance between grid node i and grid node j;

[0031] S224. Determine whether all individual ants in the ant colony have reached the destination. If all individual ants in the ant colony have reached the destination, calculate the path length of each individual ant in the ant colony, take the path with the shortest path length as the optimal path, and then proceed to S225; otherwise, return to S223.

[0032] S225. During pathfinding, individual ants release pheromones along their paths. To prevent excessively high pheromone concentrations from affecting their pathfinding in the next iteration, the pheromone levels are updated. The update formula is as follows:

[0033] τ ij (t+1)=(1-ρ)τ ij (t)+ρΔτ ij (t),

[0034] Where, Δτ ij (t) represents the pheromone increment along path (i,j), and its calculation formula is:

[0035]

[0036] Among them, L x This represents the total length of the path traveled by the xth ant.

[0037] S226. Determine whether the current iteration number t of the third iteration is less than the maximum iteration number t of the third iteration. max If the current iteration number t is less than the maximum iteration number t of the third iteration max If the current iteration number t is incremented by 1, then return S223; otherwise, compare the lengths of the optimal paths in each iteration and output the path with the shortest length as the optimal action route.

[0038] Compared to traditional manual search methods, this invention uses ant colony optimization to plan the optimal action route, reducing the consumption of human resources. At the same time, it simulates the behavior of ants searching for food in nature, constructs a mathematical model, accelerates the speed and efficiency of the optimization process, and ensures the accuracy of the optimization results.

[0039] Preferably, instructions are sent to the AGV (Automated Guided Vehicle), which performs inbound and outbound operations according to the planned optimal route. After the inbound and outbound operations are completed, the weight change data of the target shelf is collected and compared with the weight data of the inbound and outbound goods. The specific steps to determine whether there is an abnormality in the inbound and outbound operations are as follows:

[0040] S31. Send instructions to the AGV vehicle, which moves to the target shelf according to the planned optimal route and performs inbound and outbound operations through the robotic arm installed on the AGV vehicle. At the same time, update the cargo data in the digital twin model by combining the inbound and outbound cargo data.

[0041] S32. After completing the inbound and outbound operations, the weight change data ΔM of the target shelf is collected by the gravity detection sensor installed on the shelf, and the weight data M of the inbound and outbound goods is extracted from the collected inbound and outbound goods data.

[0042] S33. Compare the weight change data ΔM of the target shelf with the weight data M of the goods entering and leaving the warehouse;

[0043] If ΔM = M, then no operation is performed;

[0044] If ΔM≠M, an anomaly in the inbound / outbound operation is reported to the main control unit, and the main control unit sends an access prompt signal to the corresponding shelf location in the digital twin model.

[0045] By collecting data on the weight changes of the target shelves after the completion of inbound and outbound operations, and comparing these data with the weight data of the goods entering and leaving the warehouse, it is possible to determine whether any abnormalities have occurred in the inbound and outbound operations, thus ensuring the accuracy of the inbound and outbound operation process.

[0046] Preferably, the specific steps for intelligent management of environmental parameters in the warehousing park using sensors are as follows:

[0047] S41. Install temperature and humidity sensors on each shelf in the warehouse park to collect temperature and humidity data of each shelf in real time and obtain temperature and humidity datasets.

[0048] S42. Find the optimal temperature range and optimal humidity range through intelligent optimization algorithms;

[0049] S43. Sequentially determine whether each temperature data in the temperature dataset and each humidity data in the humidity dataset are within the optimal temperature range and optimal humidity range, and analyze the temperature and humidity status of each shelf based on the determination results.

[0050] Preferably, temperature and humidity sensors are installed on each shelf in the warehouse area to collect temperature and humidity data from each shelf in real time, and the specific steps to obtain temperature and humidity datasets are as follows:

[0051] S411. Install temperature sensors on each shelf in the warehouse park to collect temperature data of each shelf in real time, and obtain a real-time temperature dataset C = {c1, c2, ..., c i ,…,c k}, where c i This represents the real-time temperature data of the i-th shelf;

[0052] S412. Install humidity sensors on each shelf in the warehouse park to collect humidity data of each shelf in real time, and obtain a real-time humidity dataset C'={c'1,c'2,…,c' i ,…,c' k}, where c' i This represents the real-time humidity data for the i-th shelf.

[0053] Preferably, the specific steps for finding the optimal temperature range and optimal humidity range using intelligent optimization algorithms are as follows:

[0054] S421. Construct a first dragonfly population and a second dragonfly population, setting the sizes of the first and second dragonfly populations to m1 and m2, respectively; set the first maximum number of iterations to T1. max The second maximum number of iterations is T2 max The optimization search space for both the first and second dragonfly populations is set to one dimension.

[0055] S422. Find the maximum value c from the real-time temperature dataset. max and minimum value c min , in [c min c max Randomly select m1 data points from [a set of data points] as the initial location set for the first dragonfly population. Among them, X i This indicates the initial position of the i-th dragonfly individual in the first dragonfly population;

[0056] Find the maximum value c' in the real-time humidity dataset. max and minimum value c' min , in [c' min ,c' max Randomly select m² data points from [a range] as the initial location set for the second dragonfly population. Among them, Y i This indicates the initial position of the i-th dragonfly individual in the second dragonfly population;

[0057] S423. Calculate the fitness function value of each dragonfly individual in the first and second dragonfly populations; the formulas for the fitness function values ​​of the first and second dragonfly populations are as follows:

[0058]

[0059] Among them, Fit(x) i x represents the fitness function value of the i-th dragonfly individual in the first dragonfly population. i Fit(y) represents the ability of the i-th dragonfly individual in the first dragonfly population to reduce cargo loss. i y represents the fitness function value of the i-th dragonfly individual in the second dragonfly population. i λ1 represents the ability of the i-th dragonfly individual in the second dragonfly population to reduce cargo loss, and λ2 represents the first correction value and the second correction value, respectively.

[0060] S424. Start the iteration operation. Set the current iteration number of the first dragonfly population to T1 and the current iteration number of the second dragonfly population to T2. During each iteration, each dragonfly individual in the first and second dragonfly populations will be affected by other dragonfly individuals in the population and will update its position. Recalculate the fitness function value of each dragonfly individual in the first and second dragonfly populations after the position update. The dragonfly individual with the highest fitness function value in the first and second dragonfly populations will be taken as the global optimal solution.

[0061] S425. Determine whether the first current iteration number T1 is less than the first maximum iteration number T1. max If the first current iteration number T1 is less than the first maximum iteration number T1 max If the first iteration number T1 is incremented by 1 and S54 is returned, then the temperature data corresponding to the global optimal solution in the first dragonfly population is output as the optimal temperature h1.

[0062] Determine if the second current iteration number T2 is less than the second maximum iteration number T2. max If the second current iteration number T2 is less than the second maximum iteration number T2 max If the current iteration count T2 is positive, then the second iteration count T2 is incremented by 1 and S54 is returned; otherwise, the humidity data corresponding to the global optimal solution in the second dragonfly population is output as the optimal humidity h2.

[0063] S4251. Set the optimal temperature deviation value q1 and the optimal humidity deviation value q2, and construct the optimal temperature range [h1-q1,h1+q1] and the optimal humidity range [h2-q2,h2+q2].

[0064] Compared to analyzing and processing historical data to obtain the optimal temperature and humidity, this invention uses the dragonfly algorithm to find the optimal temperature and humidity, avoiding errors that may occur in data analysis. At the same time, it simulates the group activities of dragonflies in nature to build a mathematical model, effectively preventing the optimization results from getting stuck in local optima.

[0065] Preferably, the specific steps for determining whether each temperature data point in the temperature dataset and each humidity data point in the humidity dataset are within the optimal temperature and humidity ranges, and then analyzing the temperature and humidity status of each shelf based on the determination results, are as follows:

[0066] S431. Sequentially determine the temperature dataset C = {c1, c2, ..., c...} i ,…,c k Are the temperature data in the table within the optimal temperature range?

[0067] S4311. If all temperature data in the temperature dataset are within the optimal temperature range, then all shelves are in a normal temperature state; otherwise, temperature data in the temperature dataset that are not within the optimal temperature range are recorded as abnormal temperature data, the shelf corresponding to the abnormal temperature data is determined to be in an abnormal temperature state, the abnormal temperature state is fed back to the main control unit, the main control unit issues a temperature abnormality warning signal at the corresponding shelf position in the digital twin model, and issues an instruction to the temperature regulator closest to the shelf. After receiving the instruction, the temperature regulator adjusts the temperature of the shelf to the optimal temperature.

[0068] S432. Sequentially determine the humidity dataset C' = {c'1, c'2, ..., c'} i ,…,c' k Are the humidity data in the table within the optimal humidity range?

[0069] S4321. If all humidity data in the humidity dataset are within the optimal humidity range, then all shelves are in a normal humidity state; otherwise, humidity data that are not within the optimal humidity range in the humidity dataset are recorded as abnormal humidity data, the shelf corresponding to the abnormal humidity data is determined to be in an abnormal humidity state, the abnormal humidity state is fed back to the main control unit, and the main control unit sends a humidity abnormality prompt signal to the corresponding shelf position in the digital twin model, and sends an instruction to the humidity regulator closest to the shelf. After receiving the instruction, the humidity regulator adjusts the humidity of the shelf to the optimal humidity.

[0070] The system sequentially determines whether each temperature and humidity data point in the collected temperature and humidity dataset is within the optimal temperature and humidity range. Based on the determination results, it analyzes the temperature and humidity status of each shelf, thereby achieving real-time monitoring of the temperature and humidity in the storage park and ensuring the park's proper operation.

[0071] This invention also discloses a system for warehouse park operation and maintenance management based on digital twins, including a digital twin model construction module, an optimal action route planning module, an inbound and outbound operation anomaly judgment module, a temperature and humidity data acquisition module, an optimization module, and a shelf temperature and humidity status analysis module.

[0072] The digital twin model building module collects location data of each shelf in the warehouse park and data on the goods on the shelves, and then uses a 3D modeling tool to build a digital twin model.

[0073] The optimal action route planning module locks the target shelf location in the digital twin model based on the inbound and outbound goods data and determines the AGV trolley to perform the inbound and outbound operations. It then plans the optimal action route in the digital twin model using the ant colony algorithm.

[0074] The inbound / outbound operation anomaly determination module collects the weight change data of the target shelf after the inbound / outbound operation is completed, and compares the values ​​with the weight data of the inbound / outbound goods to determine whether there is an anomaly in the inbound / outbound operation.

[0075] The temperature and humidity data acquisition module collects temperature and humidity data of each shelf in real time by installing temperature and humidity sensors on each shelf in the warehouse park.

[0076] The optimization module uses the Dragonfly Algorithm to find the optimal temperature and optimal humidity, and sets the optimal temperature deviation value and optimal humidity deviation value to construct the optimal temperature range and optimal humidity range.

[0077] The shelf temperature and humidity status analysis module sequentially determines whether each temperature data in the temperature dataset and each humidity data in the humidity dataset are within the optimal temperature range and optimal humidity range, and analyzes the temperature and humidity status of each shelf based on the determination results.

[0078] (3) Beneficial effects

[0079] 1. This invention includes a digital twin model construction module, an optimal action route planning module, an inbound / outbound operation anomaly judgment module, a temperature and humidity data acquisition module, an optimization module, and a shelf temperature and humidity status analysis module. It constructs a digital twin model using collected shelf location data and cargo data to achieve visualized data management. AGVs execute inbound / outbound operations according to the planned optimal action route, collecting weight change data of the target shelf after the operation and comparing it with the weight data of the inbound / outbound goods to determine if any anomalies have occurred, ensuring the accuracy of the inbound / outbound operation process. It also sequentially judges whether each temperature and humidity data point in the collected temperature and humidity dataset is within the optimal temperature and humidity range. Based on the judgment results, it analyzes the temperature and humidity status of each shelf, achieving real-time monitoring of the temperature and humidity of the storage park and ensuring the reasonable operation of the park.

[0080] 2. Compared with traditional manual search methods, this invention plans the optimal action route through ant colony algorithm, which reduces the consumption of human resources. At the same time, it simulates the behavior of ants searching for food in nature, builds a mathematical model, accelerates the speed and efficiency of the optimization process, and ensures the accuracy of the optimization results.

[0081] 3. Compared to analyzing and processing historical data to obtain the optimal temperature and humidity, this invention uses the dragonfly algorithm to find the optimal temperature and humidity, avoiding errors in data analysis. At the same time, it simulates the group activities of dragonflies in nature to build a mathematical model, effectively preventing the optimization results from getting stuck in local optima. Attached Figure Description

[0082] To more clearly illustrate the technical solutions of the embodiments of the invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the invention. For those skilled in the art, the drawings can be obtained from these drawings without creative effort.

[0083] Figure 1 A flowchart illustrating a warehouse park operation and maintenance management method based on digital twins provided by this invention;

[0084] Figure 2 This is a schematic diagram of the system modules of a warehouse park operation and maintenance management method based on digital twins provided by the present invention. Detailed Implementation

[0085] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0086] In the description of this invention, it should be understood that the terms "opening", "upper", "lower", "top", "middle", "inner", etc., which indicate orientation or positional relationship, are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the components or elements referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation on the invention.

[0087] The following is an example of a warehouse park operation and maintenance management system and method based on digital twins:

[0088] Please see Figure 1 A warehouse park operation and maintenance management method based on digital twins includes the following steps:

[0089] S1. Collect the location data of each shelf in the warehouse park and the goods data stored on each shelf. Based on the location data and the goods data, construct a digital twin model using a 3D modeling tool.

[0090] S11. Collect the location data of each shelf in the warehouse park to obtain the shelf location dataset A = {a1, a2, ..., a i ,…,a k}, where a i This represents the location data of the i-th shelf, and k represents the total number of shelf location data.

[0091] S12. Define the cargo data type set B = {b1, b2, ..., b} i ,…,b l}, where b i Let represent the i-th type of cargo data that needs to be collected, and l represent the total number of cargo data types;

[0092] S13. Scan the RFID tags of goods stored on each shelf using a wireless frequency scanning device to collect the goods data, and obtain the goods data matrix B as follows:

[0093]

[0094] Among them, b ij This represents the data of the j-th type of goods that need to be collected, which are stored on the i-th shelf.

[0095] S14. Based on the shelf location dataset A and the cargo data matrix B, construct a digital twin model using a 3D modeling tool.

[0096] S2. When inbound and outbound operations are required, collect inbound and outbound goods data, locate the target shelf in the digital twin model based on the inbound and outbound goods data, determine the AGV vehicle to perform the inbound and outbound operations, and plan the optimal movement route in the digital twin model.

[0097] S21. When performing inbound and outbound operations, collect inbound and outbound goods data, and locate the target shelf in the digital twin model based on the inbound and outbound goods data.

[0098] S22. Determine the AGV vehicle to perform the inbound and outbound operations, and plan the optimal route in the digital twin model based on the location of the target shelf;

[0099] S221. Draw a grid map based on the terrain of the warehouse park;

[0100] S222. Construct an ant colony, setting the population size to N, the current iteration number to t, and the maximum iteration number to t. max The pheromone evaporation coefficient is ρ, the total amount of pheromones is Q, the pheromone weighting factor is α, and the heuristic information weighting factor is β;

[0101] Set the start and end positions in the grid map, put N ants at the start position to search for paths, set a taboo list for each ant, and take the grid positions of all shelves and the start position as taboo nodes. The individual ants will not move to the taboo nodes during the path search process.

[0102] S223. Each ant in the ant colony traverses from its starting position, calculating the probability of entering each accessible grid cell according to the probability transition formula. A roulette wheel is used to select the next grid cell for each ant to move to. Once an ant moves to a new grid cell, the new grid cell position is added to that ant's taboo list. The probability transition formula is as follows:

[0103]

[0104] in, This represents the probability that the x-th ant travels from grid node i to grid node j, allowed. x s represents the set of all grid nodes that the x-th ant can choose in the next iteration; s represents the set allowed. x Any node in τ; ij (t) represents the pheromone concentration from grid node i to grid node j during the t-th iteration; η ij (t) represents the expected degree of progress from grid node i to grid node j during the t-th iteration;

[0105] set up Where, d ij This represents the Euclidean distance between grid node i and grid node j;

[0106] S224. Determine whether all individual ants in the ant colony have reached the destination. If all individual ants in the ant colony have reached the destination, calculate the path length of each individual ant in the ant colony, take the path with the shortest path length as the optimal path, and then proceed to S225; otherwise, return to S223.

[0107] S225. During pathfinding, individual ants release pheromones along their paths. To prevent excessively high pheromone concentrations from affecting their pathfinding in the next iteration, the pheromone levels are updated. The update formula is as follows:

[0108] τ ij (t+1)=(1-ρ)τ ij (t)+ρΔτ ij (t),

[0109] Where, Δτ ij (t) represents the pheromone increment along path (i,j), and its calculation formula is:

[0110]

[0111] Among them, L x This represents the total length of the path traveled by the xth ant.

[0112] S226. Determine whether the current iteration number t of the third iteration is less than the maximum iteration number t of the third iteration. max If the current iteration number t is less than the maximum iteration number t of the third iteration max If the current iteration number t is incremented by 1, then S223 is returned; otherwise, the lengths of the optimal paths in each iteration are compared, and the path with the shortest length is output as the optimal action route.

[0113] S3. Send instructions to the AGV vehicle, and the AGV vehicle performs the inbound and outbound operations according to the planned optimal route. After the inbound and outbound operations are completed, collect the weight change data of the target shelf and compare it with the weight data of the inbound and outbound goods to determine whether there is any abnormality in the inbound and outbound operations.

[0114] S31. Send instructions to the AGV vehicle, which moves to the target shelf according to the planned optimal route and performs inbound and outbound operations through the robotic arm installed on the AGV vehicle. At the same time, update the cargo data in the digital twin model by combining the inbound and outbound cargo data.

[0115] S32. After completing the inbound and outbound operations, the weight change data ΔM of the target shelf is collected by the gravity detection sensor installed on the shelf, and the weight data M of the inbound and outbound goods is extracted from the collected inbound and outbound goods data.

[0116] S33. Compare the weight change data ΔM of the target shelf with the weight data M of the goods entering and leaving the warehouse;

[0117] If ΔM = M, then no operation is performed;

[0118] If ΔM≠M, an anomaly in the inbound / outbound operation is reported to the main control unit, and the main control unit sends an access prompt signal to the corresponding shelf location in the digital twin model.

[0119] S4. Intelligent management of environmental parameters in the warehousing park through sensors;

[0120] S41. Install temperature and humidity sensors on each shelf in the warehouse park to collect temperature and humidity data of each shelf in real time and obtain temperature and humidity datasets.

[0121] S411. Install temperature sensors on each shelf in the warehouse park to collect temperature data of each shelf in real time, and obtain a real-time temperature dataset C = {c1, c2, ..., ci ,…,c k}, where c i This represents the real-time temperature data of the i-th shelf;

[0122] S412. Install humidity sensors on each shelf in the warehouse park to collect humidity data of each shelf in real time, and obtain a real-time humidity dataset C'={c'1,c'2,…,c' i ,…,c' k}, where c' i This represents the real-time humidity data for the i-th shelf;

[0123] S42. Find the optimal temperature range and optimal humidity range through intelligent optimization algorithms;

[0124] S421. Construct a first dragonfly population and a second dragonfly population, setting the sizes of the first and second dragonfly populations to m1 and m2, respectively; set the first maximum number of iterations to T1. max The second maximum number of iterations is T2 max The optimization search space for both the first and second dragonfly populations is set to one dimension.

[0125] S422. Find the maximum value c from the real-time temperature dataset. max and minimum value c min , in [c min c max Randomly select m1 data points from [a set of data points] as the initial location set for the first dragonfly population. Among them, X i This indicates the initial position of the i-th dragonfly individual in the first dragonfly population;

[0126] Find the maximum value c' in the real-time humidity dataset. max and minimum value c' min , in [c' min ,c' max Randomly select m² data points from [a range] as the initial location set for the second dragonfly population. Among them, Y i This indicates the initial position of the i-th dragonfly individual in the second dragonfly population;

[0127] S423. Calculate the fitness function value of each dragonfly individual in the first and second dragonfly populations; the formulas for the fitness function values ​​of the first and second dragonfly populations are as follows:

[0128]

[0129] Among them, Fit(x) ix represents the fitness function value of the i-th dragonfly individual in the first dragonfly population. i Fit(y) represents the ability of the i-th dragonfly individual in the first dragonfly population to reduce cargo loss. i y represents the fitness function value of the i-th dragonfly individual in the second dragonfly population. i λ1 represents the ability of the i-th dragonfly individual in the second dragonfly population to reduce cargo loss, and λ2 represents the first correction value and the second correction value, respectively.

[0130] S424. Start the iteration operation. Set the current iteration number of the first dragonfly population to T1 and the current iteration number of the second dragonfly population to T2. During each iteration, each dragonfly individual in the first and second dragonfly populations will be affected by other dragonfly individuals in the population and will update its position. Recalculate the fitness function value of each dragonfly individual in the first and second dragonfly populations after the position update. The dragonfly individual with the highest fitness function value in the first and second dragonfly populations will be taken as the global optimal solution.

[0131] S425. Determine whether the first current iteration number T1 is less than the first maximum iteration number T1. max If the first current iteration number T1 is less than the first maximum iteration number T1 max If the first iteration number T1 is incremented by 1 and S54 is returned, then the temperature data corresponding to the global optimal solution in the first dragonfly population is output as the optimal temperature h1.

[0132] Determine if the second current iteration number T2 is less than the second maximum iteration number T2. max If the second current iteration number T2 is less than the second maximum iteration number T2 max If the current iteration count T2 is positive, then the second iteration count T2 is incremented by 1 and S54 is returned; otherwise, the humidity data corresponding to the global optimal solution in the second dragonfly population is output as the optimal humidity h2.

[0133] S4251. Set the optimal temperature deviation value q1 and the optimal humidity deviation value q2, and construct the optimal temperature range [h1-q1,h1+q1] and the optimal humidity range [h2-q2,h2+q2].

[0134] S43. Sequentially determine whether each temperature data in the temperature dataset and each humidity data in the humidity dataset are within the optimal temperature range and optimal humidity range, and analyze the temperature and humidity status of each shelf based on the determination results.

[0135] S431. Sequentially determine the temperature dataset C = {c1, c2, ..., c...} i ,…,c k Are the temperature data in the table within the optimal temperature range?

[0136] S4311. If all temperature data in the temperature dataset are within the optimal temperature range, then all shelves are in a normal temperature state; otherwise, temperature data in the temperature dataset that are not within the optimal temperature range are recorded as abnormal temperature data, the shelf corresponding to the abnormal temperature data is determined to be in an abnormal temperature state, the abnormal temperature state is fed back to the main control unit, the main control unit issues a temperature abnormality warning signal at the corresponding shelf position in the digital twin model, and issues an instruction to the temperature regulator closest to the shelf. After receiving the instruction, the temperature regulator adjusts the temperature of the shelf to the optimal temperature.

[0137] S432. Sequentially determine the humidity dataset C' = {c'1, c'2, ..., c'} i ,…,c' k Are the humidity data in the table within the optimal humidity range?

[0138] S4321. If all humidity data in the humidity dataset are within the optimal humidity range, then all shelves are in a normal humidity state; otherwise, humidity data that are not within the optimal humidity range in the humidity dataset are recorded as abnormal humidity data, the shelf corresponding to the abnormal humidity data is determined to be in an abnormal humidity state, the abnormal humidity state is fed back to the main control unit, and the main control unit sends a humidity abnormality prompt signal to the corresponding shelf position in the digital twin model, and sends an instruction to the humidity regulator closest to the shelf. After receiving the instruction, the humidity regulator adjusts the humidity of the shelf to the optimal humidity.

[0139] The following is a second embodiment of a warehouse park operation and maintenance management system and method based on digital twins:

[0140] See also Figure 2 A system for warehouse park operation and maintenance management based on digital twins includes a digital twin model construction module, an optimal action route planning module, an inbound and outbound operation anomaly judgment module, a temperature and humidity data acquisition module, an optimization module, and a shelf temperature and humidity status analysis module.

[0141] The digital twin model building module collects location data of each shelf in the warehouse park and data on the goods on the shelves, and then uses a 3D modeling tool to build a digital twin model.

[0142] The optimal action route planning module locks the target shelf location in the digital twin model based on the inbound and outbound goods data and determines the AGV trolley to perform the inbound and outbound operations. It then plans the optimal action route in the digital twin model using the ant colony algorithm.

[0143] The inbound / outbound operation anomaly determination module collects the weight change data of the target shelf after the inbound / outbound operation is completed, and compares the values ​​with the weight data of the inbound / outbound goods to determine whether there is an anomaly in the inbound / outbound operation.

[0144] The temperature and humidity data acquisition module collects temperature and humidity data of each shelf in real time by installing temperature and humidity sensors on each shelf in the warehouse park.

[0145] The optimization module uses the Dragonfly Algorithm to find the optimal temperature and optimal humidity, and sets the optimal temperature deviation value and optimal humidity deviation value to construct the optimal temperature range and optimal humidity range.

[0146] The shelf temperature and humidity status analysis module sequentially determines whether each temperature data in the temperature dataset and each humidity data in the humidity dataset are within the optimal temperature range and optimal humidity range, and analyzes the temperature and humidity status of each shelf based on the determination results.

[0147] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0148] The preferred embodiments of the invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to the specific implementations described. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention.

Claims

1. A method for operation and maintenance management of a warehouse park based on digital twins, characterized in that, Includes the following steps: S1. Collect the location data of each shelf in the warehouse park and the goods data stored on each shelf. Based on the location data and the goods data, construct a digital twin model using a 3D modeling tool. S2. When inbound and outbound operations are required, collect inbound and outbound goods data, locate the target shelf in the digital twin model based on the inbound and outbound goods data, determine the AGV vehicle to perform the inbound and outbound operations, and plan the optimal movement route in the digital twin model. S2 includes the following steps: S21. When performing inbound and outbound operations, collect inbound and outbound goods data, and locate the target shelf in the digital twin model based on the inbound and outbound goods data. S22. Determine the AGV vehicle to perform the inbound and outbound operations, and plan the optimal route in the digital twin model based on the location of the target shelf; Planning the optimal route in S22 includes the following steps: S221. Draw a grid map based on the terrain of the warehouse park; S222. Construct an ant colony, setting the population size, the third current iteration count, and the third maximum iteration count; Set the start and end positions in the grid map, put N ants at the start position to search for paths, set a taboo list for each ant, and take the grid positions of all shelves and the start position as taboo nodes. The individual ants will not move to the taboo nodes during the path search process. S223. Each ant in the ant colony starts from the starting position and traverses the colony. The probability of entering each accessible grid is calculated according to the probability transition formula. The next grid is selected for each ant to move to by roulette. When an ant moves to a new grid, the new grid position is added to the ant's taboo list. S224. Determine whether all individual ants in the ant colony have reached the destination. If all individual ants in the ant colony have reached the destination, calculate the path length of each individual ant in the ant colony, take the path with the shortest path length as the optimal path, and then proceed to S225; otherwise, return to S223. S225. During the path search process, individual ants release pheromones along the way. In order to avoid the pheromone concentration on the path being too high and affecting the path search of individual ants in the next iteration, the pheromone is updated. S226. Determine if the current iteration number is less than the maximum iteration number. If the current iteration number is less than the maximum iteration number, increment the current iteration number by 1 and return to S223. Otherwise, compare the lengths of the optimal paths in each iteration and output the path with the shortest path length as the optimal action route. S3. Send instructions to the AGV vehicle, and the AGV vehicle performs the inbound and outbound operations according to the planned optimal route. After the inbound and outbound operations are completed, collect the weight change data of the target shelf and compare it with the weight data of the inbound and outbound goods to determine whether there is any abnormality in the inbound and outbound operations. S4. Intelligent management of environmental parameters in the warehousing park through sensors; S4 includes the following steps: S41. Install temperature and humidity sensors on each shelf in the warehouse park to collect temperature and humidity data of each shelf in real time and obtain temperature and humidity datasets. S42. Find the optimal temperature range and optimal humidity range through intelligent optimization algorithms; S42 includes the following steps: S421. Construct a first dragonfly population and a second dragonfly population, setting the sizes of the first and second dragonfly populations to m1 and m2, respectively; set the first maximum number of iterations to T1. max The second maximum number of iterations is T2 max The optimization search space for both the first and second dragonfly populations is set to one dimension. S422. Find the maximum value c from the real-time temperature dataset. max and minimum value c min , in [c min c max We randomly select m1 data points from [ ] as the initial location set for the first dragonfly population; Find the maximum value c' in the real-time humidity dataset. max and minimum value c' min , in [c' min ,c' max m2 data points were randomly selected from between [ ] as the initial location set for the second dragonfly population; S423. Calculate the fitness function value of each dragonfly individual in the first and second dragonfly populations; S424. Start the iteration operation. Set the current iteration number of the first dragonfly population to T1 and the current iteration number of the second dragonfly population to T2. During each iteration, each dragonfly individual in the first and second dragonfly populations will be affected by other dragonfly individuals in the population and will update its position. Recalculate the fitness function value of each dragonfly individual in the first and second dragonfly populations after the position update. The dragonfly individual with the highest fitness function value in the first and second dragonfly populations will be taken as the global optimal solution. S425. Determine if T1 is less than T2. max If T1 is less than T1 max If the condition is met, then T1 is incremented by 1 and S424 is returned; otherwise, the temperature data corresponding to the global optimal solution in the first dragonfly population is output as the optimal temperature h1. Determine if T2 is less than T2 max If T2 is less than T2 max If the result is positive, then T2 is incremented by 1 and S424 is returned; otherwise, the humidity data corresponding to the global optimal solution in the second dragonfly population is output as the optimal humidity h2. S4251. Set the optimal temperature deviation value q1 and the optimal humidity deviation value q2, and construct the optimal temperature range [h1-q1,h1+q1] and the optimal humidity range [h2-q2,h2+q2]. S43. Sequentially determine whether each temperature data in the temperature dataset and each humidity data in the humidity dataset are within the optimal temperature range and optimal humidity range, and analyze the temperature and humidity status of each shelf based on the determination results.

2. The method for operation and maintenance management of a warehouse park based on digital twins according to claim 1, characterized in that, S1 includes the following steps: S11. Collect the location data of each shelf in the warehouse park to obtain the shelf location dataset; S12, Set up the cargo data type set; S13. Scan the RFID tags of goods stored on each shelf using a wireless frequency scanning device to collect the goods data and obtain the goods data matrix B; S14. Based on the shelf location dataset A and the cargo data matrix B, construct a digital twin model using a 3D modeling tool.

3. The method for operation and maintenance management of a warehouse park based on digital twins according to claim 2, characterized in that, S3 includes the following steps: S31. Send instructions to the AGV vehicle, which moves to the target shelf according to the planned optimal route and performs inbound and outbound operations through the robotic arm installed on the AGV vehicle. At the same time, update the cargo data in the digital twin model by combining the inbound and outbound cargo data. S32. After completing the inbound and outbound operations, the weight change data ΔM of the target shelf is collected by the gravity detection sensor installed on the shelf, and the weight data M of the inbound and outbound goods is extracted from the collected inbound and outbound goods data. S33. Determine if any abnormalities occur in the inbound and outbound operations; Compare the weight change data ΔM of the target shelf with the weight data M of the goods entering and leaving the warehouse; If ΔM = M, then no operation is performed; If ΔM≠M, an anomaly in the inbound / outbound operation is reported to the main control unit, and the main control unit sends an access prompt signal to the corresponding shelf location in the digital twin model.

4. The method for operation and maintenance management of a warehouse park based on digital twins according to claim 3, characterized in that, S41 includes the following steps: S411. Install temperature sensors on each shelf in the warehouse park to collect temperature data of each shelf in real time and obtain a real-time temperature dataset. S412. Install humidity sensors on each shelf in the warehouse park to collect humidity data of each shelf in real time and obtain a real-time humidity dataset.

5. A warehouse park operation and maintenance management method based on digital twins according to claim 4, characterized in that, S43 includes the following steps: S431. Sequentially determine whether each temperature data in the temperature dataset is within the optimal temperature range; S4311. If all temperature data in the temperature dataset are within the optimal temperature range, then all shelves are in a normal temperature state; otherwise, temperature data in the temperature dataset that are not within the optimal temperature range are recorded as abnormal temperature data, the shelf corresponding to the abnormal temperature data is determined to be in an abnormal temperature state, the abnormal temperature state is fed back to the main control unit, the main control unit issues a temperature abnormality warning signal at the corresponding shelf position in the digital twin model, and issues an instruction to the temperature regulator closest to the shelf. After receiving the instruction, the temperature regulator adjusts the temperature of the shelf to the optimal temperature. S432. Sequentially determine whether each humidity data in the humidity dataset is within the optimal humidity range; S4321. If all humidity data in the humidity dataset are within the optimal humidity range, then all shelves are in a normal humidity state; otherwise, humidity data in the humidity dataset that are not within the optimal humidity range are recorded as abnormal humidity data, the shelf corresponding to the abnormal humidity data is determined to be in an abnormal humidity state, the abnormal humidity state is fed back to the main control unit, and the main control unit sends a humidity abnormality prompt signal to the corresponding shelf position in the digital twin model, and sends an instruction to the humidity regulator closest to the shelf. After receiving the instruction, the humidity regulator adjusts the humidity of the shelf to the optimal humidity.

6. A system for implementing the digital twin-based warehouse park operation and maintenance management method as described in any one of claims 1-5.

Images