Warehousing park operation and maintenance management system and method based on digital twinning

Abstract

The invention relates to the technical field of storage management and control, in particular to a storage park operation and maintenance management method based on digital twinning. A digital twinborn model is constructed through collected shelf position data and cargo data, and visual management of the data is realized; according to the method, warehouse-in and warehouse-out operation is executed through the AGV according to the planned optimal moving route, the weight change data of the target goods shelf after the warehouse-in and warehouse-out operation is verified, whether the warehouse-in and warehouse-out operation is abnormal or not is judged, and the accuracy of the warehouse-in and warehouse-out operation process is guaranteed; optimal temperature and humidity are searched through a dragonfly algorithm, group activities of dragonflies in the nature are simulated, a mathematical model is constructed, and an optimization result is effectively prevented from falling into local optimum; whether each piece of temperature and humidity data in the acquired temperature and humidity data set is in the optimal temperature and humidity interval is judged, the temperature and humidity state of each goods shelf is analyzed, real-time monitoring of the temperature and humidity of the storage park is achieved, and reasonable operation of the park is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of warehousing management, and specifically provides a method for operation and maintenance management of a warehousing park based on digital twin. Background Art

[0002] Digital twin technology maps various types of collected data in a virtual space to construct a digital twin model, and uses the digital twin model to monitor and manage physical facilities in real time.

[0003] The Chinese patent application with the publication number CN112990820A introduces a warehousing management system based on digital twin. It sends the location information of the storage locations and the information of the goods collected by the information collection module to the server and displays them in the digital twin body. When goods are to be stored, it locates the storage location of the goods to be stored in the digital twin body and updates the goods information after the storage is completed to achieve reasonable warehousing management. However, it does not perform route planning during the warehousing process, so it cannot improve the speed and efficiency of inbound and outbound operations. At the same time, it does not monitor the environment in the warehousing park in real time, so it cannot avoid the loss of goods caused by unreasonable warehousing environmental conditions. Summary of the Invention

[0004] (I) Technical Problems to be Solved

[0005] To solve the deficiencies in the background art, the present invention proposes a method for operation and maintenance management of a warehousing park based on digital twin, which realizes real-time monitoring of the warehousing park and ensures the reasonable operation of the park.

[0006] (II) Technical Solutions

[0007] A method for operation and maintenance management of a warehousing park based on digital twin specifically includes the following steps:

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

[0009] S2. When inbound and outbound operations are required, collect the inbound and outbound goods data, lock the target shelf location in the digital twin model according to the inbound and outbound goods data, determine the AGV cart for performing the inbound and outbound operations, and plan the optimal action route in the digital twin model;

[0010] S3. Send an instruction to the AGV cart, and the AGV cart performs the inbound and outbound operations according to the planned optimal action 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 the inbound and outbound operations are abnormal;

[0011] S4. Intelligently manage the environmental parameters of the warehousing park through sensors.

[0012] The present invention constructs a digital twin model through the collected shelf position data and cargo data to achieve visual management of the data; the AGV vehicle performs inbound and outbound operations according to the planned optimal action route, collects the weight change data of the target shelf after the inbound and outbound operations are completed, and numerically compares it with the weight data of the inbound and outbound goods to determine whether there is an abnormality in the inbound and outbound operations, ensuring the accuracy of the inbound and outbound operation process; the dragonfly algorithm is used to find the optimal temperature and humidity, simulating the group activities of dragonflies in nature, constructing a mathematical model, effectively avoiding the optimization result from falling into a local optimum; successively judge whether each temperature and humidity data in the collected temperature and humidity data set is within the optimal temperature and humidity range, and according to the judgment result, analyze the temperature and humidity status of each shelf to realize real-time monitoring of the temperature and humidity in the warehousing park, ensuring the reasonable operation of the park.

[0013] Preferably, collect the position data of each shelf in the warehousing park and the cargo data of the goods stored on each shelf. Based on the position data and the cargo data, the specific steps of constructing a digital twin model through a 3D modeling tool are as follows:

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

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

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

[0017]

[0018] Among them, b ij represents the j-th type of cargo data to be collected of the goods stored on the i-th shelf;

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

[0020] Build a digital twin model through the collected shelf location data and goods data to achieve visual management of the data.

[0021] Preferably, when inbound and outbound operations are required, collect inbound and outbound goods data, lock the target shelf location in the digital twin model according to the inbound and outbound goods data, and determine the AGV cart for performing the inbound and outbound operations. The specific steps for planning the optimal action route in the digital twin model are as follows:

[0022] S21. When performing inbound and outbound operations, collect inbound and outbound goods data, and lock the target shelf location in the digital twin model according to the inbound and outbound goods data;

[0023] S22. Determine the AGV cart for performing the inbound and outbound operations, and plan the optimal action route in the digital twin model according to the location of the target shelf;

[0024] S221. Draw a grid map according to the terrain of the warehousing park;

[0025] S222. Build an ant population, set the population size as N, the third current iteration number as t, the third maximum iteration number as t max , the pheromone evaporation coefficient as ρ, the total pheromone amount as Q, the pheromone weight factor as α, and the heuristic information weight factor as β;

[0026] Set the starting position and the ending position in the grid map, put N ants into the starting position for path search, set a taboo list for each ant, and take all the grid positions where the shelves are located and the starting position as taboo nodes. The ant individuals will not move to the taboo nodes during the path search process;

[0027] S223. Each ant in the ant population starts traversing from the starting position, calculates the probability of entering each accessible grid according to the probability transition formula, and selects the next grid for the ant individual to move through the roulette wheel method. After the ant individual moves to a new grid, add the new grid position to the taboo list of this ant; The probability transition formula is as follows:

[0028]

[0029] Among them, represents the probability that the xth ant moves from grid node i to grid node j, allowed x represents the set of all grid nodes that the xth ant can choose next; s represents any node in the set allowed x ; τ ij (t) represents the pheromone concentration from grid node i to grid node j during the tth iteration process; η ij(t) represents the expected degree from grid node i to grid node j in the t-th iteration process;

[0030] Set where d ij represents the Euclidean distance between grid node i and grid node j;

[0031] S224. Determine whether each ant individual in the ant population has reached the end point. If each ant individual in the ant population has reached the end point, calculate the path length of each ant individual in the ant population, take the path with the shortest path length as the optimal path, and then enter S225; otherwise, return to S223;

[0032] S225. Ant individuals will release pheromones along the way during the path search process. In order to avoid the pheromone concentration on the path being too high and affecting the path search of ant individuals in the next iteration process, update the pheromone; 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 on path (i, j), and its calculation formula is:

[0035]

[0036] where L x represents the total length of the moving path of the x-th ant individual;

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

[0038] Compared with the traditional manual search method, the present invention plans the optimal action route through the ant colony algorithm, reduces the consumption of human resources, and at the same time simulates the behavior of ants searching for food in nature, constructs a mathematical model, speeds up the speed and efficiency of the optimization process, and ensures the accuracy of the optimization result.

[0039] Preferably, a command is issued to the AGV, and the AGV performs the inbound and outbound operation according to the planned optimal action route. After completing the inbound and outbound operation, 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 for determining whether the inbound and outbound operation is abnormal are as follows:

[0040] S31, issuing a command to the AGV, so that the AGV moves to the target shelf according to the planned optimal action route, and performs the in-and-out warehouse operation through the mechanical arm installed on the AGV, and at the same time updates the cargo data in the digital twin model in combination with the in-and-out cargo data;

[0041] S32, after completing the in-and-out operation, collect the weight change data ΔM of the target shelf through the gravity detection sensor installed on the shelf, and extract the weight data M of the in-and-out goods from the collected in-and-out goods data;

[0042] S33, comparing 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, no operation is performed;

[0044] If ΔM≠M, the abnormality of the warehousing operation is fed back to the main control unit, and the main control unit sends an access prompt signal to the corresponding shelf position in the digital twin model.

[0045] By collecting the weight change data of the target shelf after completing the in-and-out operation, and comparing it with the weight data of the in-and-out goods, it is determined whether there is any abnormality in the in-and-out operation, thus ensuring the accuracy of the in-and-out operation process.

[0046] Preferably, the specific steps of intelligently managing the environmental parameters of the storage park through sensors are as follows:

[0047] S41, installing temperature sensors and humidity sensors on each shelf in the storage park, collecting temperature data and humidity data of each shelf in real time, and obtaining a temperature data set and a humidity data set;

[0048] S42, finding the optimal temperature range and the optimal humidity range through an intelligent optimization algorithm;

[0049] S43, sequentially judging whether each temperature data in the temperature data set and each humidity data in the humidity data set are in the optimal temperature range and the optimal humidity range, and analyzing the temperature and humidity status of each shelf according to the judgment result.

[0050] Preferably, a temperature sensor and a humidity sensor are installed on each shelf in the storage park to collect temperature data and humidity data of each shelf in real time. The specific steps of obtaining the temperature data set and the humidity data set are as follows:

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

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

[0053] Preferably, the specific steps to find the optimal temperature range and the optimal humidity range through the intelligent optimization algorithm are as follows:

[0054] S421. Construct the first dragonfly population and the second dragonfly population, and set the scales of the first dragonfly population and the second dragonfly population to m1 and m2 respectively; set the first maximum iteration number to T1 max and the second maximum iteration number to T2 max ; set the optimization search space dimensions of the first dragonfly population and the second dragonfly population to be one-dimensional;

[0055] S422. Find the maximum value c max and the minimum value c min from the real-time temperature data set, and randomly select m1 data between [c min , c max as the initial position set of the first dragonfly population where X i represents the initial position of the i-th dragonfly individual in the first dragonfly population;

[0056] Find the maximum value c' max and the minimum value c' min from the real-time humidity data set, and randomly select m2 data between [c' min , c' max as the initial position set of the second dragonfly population where Y i represents the initial position of the i-th dragonfly individual in the second dragonfly population;

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

[0058]

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

[0060] S424. Start the iterative operation, set the current iteration number of the first dragonfly population as T1 and the current iteration number of the second dragonfly population as T2; in each iteration process of each dragonfly individual in the first dragonfly population and the second dragonfly population, it will be affected by other dragonfly individuals in the population to update its position, and recalculate the fitness function values of each dragonfly individual in the first dragonfly population and the second dragonfly population after the position update. The dragonfly individual with the highest fitness function value in the first dragonfly population and the second dragonfly population is used as the global optimal solution;

[0061] S425. Judge 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 , then the first current iteration number T1 is incremented by 1 and return to S54; otherwise, output the temperature data corresponding to the global optimal solution in the first dragonfly population as the optimal temperature h1;

[0062] Judge whether 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 , then the second current iteration number T2 is incremented by 1 and return to S54; otherwise, output the humidity data corresponding to the global optimal solution in the second dragonfly population 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 interval [h1 - q1, h1 + q1] and the optimal humidity interval [h2 - q2, h2 + q2].

[0064] Compared with analyzing and processing historical data to obtain the optimal temperature and humidity, the present invention uses the dragonfly algorithm to find the optimal temperature and humidity, avoiding the errors in data analysis. At the same time, it simulates the group activities of dragonflies in nature, constructs a mathematical model, and effectively avoids the optimization result from falling into a local optimum.

[0065] Preferably, it is determined in sequence whether each temperature data in the temperature data set and each humidity data in the humidity data set are within the optimal temperature range and the optimal humidity range. According to the judgment results, the specific steps for analyzing the temperature and humidity states of each shelf are as follows:

[0066] S431. Determine in sequence whether each temperature data in the temperature data set C = {c1, c2, …, c i , …, c k} is within the optimal temperature range;

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

[0068] S432. Determine in sequence whether each humidity data in the humidity data set C' = {c'1, c'2, …, c' i , …, c' k} is within the optimal humidity range;

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

[0070] Determine in sequence whether each temperature and humidity data in the collected temperature and humidity data set is within the optimal temperature and humidity range. According to the judgment results, analyze the temperature and humidity states of each shelf, realize the real-time monitoring of the temperature and humidity in the warehousing park, and ensure the reasonable operation of the park.

[0071] The present invention also discloses a system for a warehousing park operation and maintenance management method based on digital twins, including a digital twin model construction module, an optimal action route planning module, an inbound and outbound operation abnormality determination module, a temperature and humidity data collection module, an optimization module, and a shelf temperature and humidity state analysis module;

[0072] The digital twin model construction module constructs a digital twin model through a 3D modeling tool by collecting the location data of each shelf and the goods data on the shelf in the warehousing park;

[0073] The optimal action route planning module locks the target shelf position in the digital twin model according to the inbound and outbound goods data and determines the AGV cart for performing the inbound and outbound operations, and plans the optimal action route in the digital twin model through the ant colony algorithm;

[0074] The inbound and outbound operation anomaly determination module determines whether the inbound and outbound operation is abnormal by collecting the weight change data of the target shelf after the inbound and outbound operation is completed and numerically comparing it with the weight data of the inbound and outbound goods;

[0075] The temperature and humidity data acquisition module installs temperature sensors and humidity sensors on each shelf in the warehousing park to collect the temperature data and humidity data of each shelf in real time;

[0076] The optimization module finds the optimal temperature and optimal humidity through the dragonfly algorithm, sets the optimal temperature deviation value and optimal humidity deviation value, and constructs the optimal temperature range and optimal humidity range;

[0077] The shelf temperature and humidity state analysis module sequentially determines whether each temperature data in the temperature data set and each humidity data in the humidity data set are within the optimal temperature range and optimal humidity range, and analyzes the temperature and humidity states of each shelf according to the judgment results.

[0078] (III) Beneficial effects

[0079] 1. The present invention sets up a digital twin model construction module, an optimal action route planning module, an inbound and outbound operation anomaly determination module, a temperature and humidity data acquisition module, an optimization module, and a shelf temperature and humidity state analysis module; constructs a digital twin model through the collected shelf location data and goods data to realize the visual management of data; the AGV cart performs the inbound and outbound operations according to the planned optimal action route, collects the weight change data of the target shelf after the inbound and outbound operation is completed, and numerically compares it with the weight data of the inbound and outbound goods to determine whether the inbound and outbound operation is abnormal, ensuring the accuracy of the inbound and outbound operation process; sequentially determines whether each temperature and humidity data in the collected temperature and humidity data set is within the optimal temperature and humidity range, and analyzes the temperature and humidity states of each shelf according to the judgment results, realizing the real-time monitoring of the temperature and humidity in the warehousing park and ensuring the reasonable operation of the park;

[0080] 2. Compared with the traditional manual search method, the present invention plans the optimal action route through the ant colony algorithm, reduces the consumption of human resources, and at the same time simulates the behavior of ants searching for food in nature, constructs a mathematical model, speeds up the speed and efficiency of the optimization process, and ensures the accuracy of the optimization result;

[0081] 3. Compared with analyzing and processing historical data to obtain the optimal temperature and humidity, the present 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, constructs a mathematical model, and effectively avoids the optimization result from falling into a local optimum. BRIEF DESCRIPTION OF THE DRAWINGS

[0082] In order to more clearly illustrate the technical solutions of the embodiments of the invention, the drawings required for describing the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0083] Figure 1 It is a flowchart of a method for operation and maintenance management of a warehousing park based on digital twin provided by the present invention;

[0084] Figure 2 It is a schematic diagram of the modules of a system for a method for operation and maintenance management of a warehousing park based on digital twin provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0085] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some of the embodiments of the present invention, rather than all of them. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.

[0086] In the description of the present invention, it should be understood that the terms "opening", "upper", "lower", "top", "middle", "inner", etc. indicating the orientation or position relationship are only for the convenience of describing the invention and simplifying the description, rather than indicating or implying that the components or elements referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation of the invention.

[0087] The first embodiment of the system and method for operation and maintenance management of a warehousing park based on digital twin is as follows:

[0088] Please refer to Figure 1 , a method for operation and maintenance management of a warehousing park based on digital twin, including the following steps:

[0089] S1. Collect the position data of each shelf in the warehousing park and the cargo data of the goods stored on each shelf, and construct a digital twin model through a 3D modeling tool based on the position data and the cargo data;

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

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

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

[0093]

[0094] where b ij represents the j-th type of cargo data to be collected for the goods stored on the i-th shelf;

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

[0096] S2. When inbound and outbound operations are required, collect inbound and outbound cargo data, lock the target shelf location in the digital twin model according to the inbound and outbound cargo data, determine the AGV cart for performing the inbound and outbound operations, and plan the optimal action route in the digital twin model;

[0097] S21. When performing inbound and outbound operations, collect inbound and outbound cargo data, and lock the target shelf location in the digital twin model according to the inbound and outbound cargo data;

[0098] S22. Determine the AGV cart for performing the inbound and outbound operations, and plan the optimal action route in the digital twin model according to the location of the target shelf;

[0099] S221. Draw a grid map according to the terrain of the warehousing park;

[0100] S222. Construct an ant population, set the population size to N, the third current iteration number to t, the third maximum iteration number to t max , the pheromone evaporation coefficient to ρ, the total pheromone amount to Q, the pheromone weight factor to α, and the heuristic information weight factor to β;

[0101] Set the starting position and the ending position in the grid map, put N ants at the starting position for path search, set a taboo list for each ant, and use the grid positions of all the shelves and the starting position as taboo nodes. During the path search process, an ant individual will not move to a taboo node;

[0102] S223. Each ant in the ant population starts traversing from the starting position, calculates the probability of entering each accessible grid according to the probability transition formula, and selects the next grid for the ant individual to move through roulette. After the ant individual moves to a new grid, add the new grid position to the taboo list of this ant. The probability transition formula is as follows:

[0103]

[0104] Among them, represents the probability that the x-th ant moves from grid node i to grid node j, and allowed x represents the set of all grid nodes that the x-th ant can choose next; s represents any node in the set allowed x ; 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 from grid node i to grid node j during the t-th iteration;

[0105] Set Among them, d ij represents the Euclidean distance between grid node i and grid node j;

[0106] S224. Judge whether each ant individual in the ant population has reached the end point. If each ant individual in the ant population has reached the end point, calculate the path length of each ant individual in the ant population, take the path with the shortest path length as the optimal path, and then enter S225; otherwise, return to S223;

[0107] S225. An ant individual will release pheromone along the path during the path search process. To avoid the pheromone concentration on the path being too high and affecting the ant individual's path search in the next iteration, update the pheromone; the update formula is as follows:

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

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

[0110]

[0111] Among them, L x represents the total length of the moving path of the x-th ant individual;

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

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

[0114] S31. Send an instruction to the AGV cart, and the AGV cart moves to the target shelf according to the planned optimal action route and performs the inbound and outbound operations through the robotic arm installed on the AGV cart. At the same time, update the goods data in the digital twin model in combination with the inbound and outbound goods data;

[0115] S32. After the inbound and outbound operations are completed, collect the weight change data ΔM of the target shelf through the gravity detection sensor installed on the shelf, and extract the weight data M of the inbound and outbound goods from the collected inbound and outbound goods data;

[0116] S33. Compare the numerical values of the weight change data ΔM of the target shelf and the weight data M of the inbound and outbound goods;

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

[0118] If ΔM ≠ M, feedback to the main control unit that there is an abnormality in the inbound and outbound operations, and the main control unit issues a storage and retrieval prompt signal at the corresponding shelf position in the digital twin model.

[0119] S4. Intelligently manage the environmental parameters of the warehousing park through sensors;

[0120] S41. Install temperature sensors and humidity sensors on each shelf in the warehousing park to collect the temperature data and humidity data of each shelf in real time, and obtain a temperature data set and a humidity data set;

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

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

[0123] S42. Use an intelligent optimization algorithm to find the optimal temperature range and the optimal humidity range;

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

[0125] S422. Find the maximum value c max and the minimum value c min from the real-time temperature data set, and randomly select m1 data between [c min , c max as the initial position set of the first dragonfly population where X i represents the initial position of the i-th dragonfly individual in the first dragonfly population;

[0126] Find the maximum value c' max and the minimum value c' min from the real-time humidity data set, and randomly select m2 data between [c' min , c' max as the initial position set of the second dragonfly population where Y i represents the initial position of the i-th dragonfly individual in the second dragonfly population;

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

[0128]

[0129] where Fit(x i) represents the fitness function value of the \(i\)-th dragonfly individual in the first dragonfly population, \(x\) i represents the ability of the \(i\)-th dragonfly individual in the first dragonfly population to reduce cargo loss, \(Fit(y\) i ) represents the fitness function value of the \(i\)-th dragonfly individual in the second dragonfly population, \(y\) i represents the ability of the \(i\)-th dragonfly individual in the second dragonfly population to reduce cargo loss, and \(\lambda_1\) and \(\lambda_2\) respectively represent the first correction value and the second correction value;

[0130] S424. Start the iteration operation, set the current iteration number of the first dragonfly population as \(T_1\) and the current iteration number of the second dragonfly population as \(T_2\); in each iteration process of the dragonfly individuals in the first dragonfly population and the second dragonfly population, they will be affected by other dragonfly individuals in the population to update their positions, and recalculate the fitness function values of each dragonfly individual in the first dragonfly population and the second dragonfly population after the position update. The dragonfly individual with the highest fitness function value in the first dragonfly population and the second dragonfly population is used as the global optimal solution;

[0131] S425. Judge whether the first current iteration number \(T_1\) is less than the first maximum iteration number \(T_1\) max , if the first current iteration number \(T_1\) is less than the first maximum iteration number \(T_1\) max , then the first current iteration number \(T_1\) is incremented by 1 and return to S54; otherwise, output the temperature data corresponding to the global optimal solution in the first dragonfly population as the optimal temperature \(h_1\);

[0132] Judge whether the second current iteration number \(T_2\) is less than the second maximum iteration number \(T_2\) max , if the second current iteration number \(T_2\) is less than the second maximum iteration number \(T_2\) max , then the second current iteration number \(T_2\) is incremented by 1 and return to S54; otherwise, output the humidity data corresponding to the global optimal solution in the second dragonfly population as the optimal humidity \(h_2\);

[0133] S4251. Set the optimal temperature deviation value \(q_1\) and the optimal humidity deviation value \(q_2\), and construct the optimal temperature interval \([h_1 - q_1, h_1 + q_1]\) and the optimal humidity interval \([h_2 - q_2, h_2 + q_2]\).

[0134] S43. Sequentially judge whether each temperature data in the temperature data set and each humidity data in the humidity data set are within the optimal temperature interval and the optimal humidity interval, and analyze the temperature and humidity states of each shelf according to the judgment results;

[0135] S431. Sequentially judge whether each temperature data in the temperature data set \(C=\{c_1, c_2, \ldots, c\) i , \ldots, c\) k \} is within the optimal temperature interval;

[0136] S4311. If all temperature data in the temperature dataset are within the optimal temperature range, then all shelves are in the normal temperature state; otherwise, the temperature data that are not within the optimal temperature range in the temperature dataset are recorded as abnormal temperature data, it is determined that the shelves corresponding to the abnormal temperature data are in the abnormal temperature state, the abnormal temperature state is fed back to the main control unit, a temperature abnormality prompt signal is sent at the corresponding shelf position in the digital twin model through the main control unit, and an instruction is sent 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. Judging in turn whether each humidity data in the humidity dataset C' = {c'1, c'2, …, c' i , …, c' k} is 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 the normal humidity state; otherwise, the humidity data that are not within the optimal humidity range in the humidity dataset are recorded as abnormal humidity data, it is determined that the shelves corresponding to the abnormal humidity data are in the abnormal humidity state, the abnormal humidity state is fed back to the main control unit, a humidity abnormality prompt signal is sent at the corresponding shelf position in the digital twin model, and an instruction is sent 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 second embodiment of the warehouse park operation and maintenance management system and method based on digital twin is as follows:

[0140] Please refer to Figure 2 , a system of a warehouse park operation and maintenance management method based on digital twin, including a digital twin model construction module, an optimal action route planning module, an inbound and outbound operation abnormality determination module, a temperature and humidity data acquisition module, an optimization module, and a shelf temperature and humidity state analysis module;

[0141] The digital twin model construction module constructs a digital twin model through a three-dimensional modeling tool by collecting the position data of each shelf and the cargo data on the shelf in the warehouse park;

[0142] The optimal action route planning module locks the target shelf position in the digital twin model according to the inbound and outbound cargo data and determines the AGV cart for performing the inbound and outbound operations, and plans the optimal action route in the digital twin model through the ant colony algorithm;

[0143] The inbound and outbound operation exception determination module determines whether an exception occurs in the inbound and outbound operation by collecting the weight change data of the target shelf after the inbound and outbound operation is completed and comparing the numerical values with the weight data of the inbound and outbound goods;

[0144] The temperature and humidity data collection module collects the temperature data and humidity data of each shelf in real time by installing temperature sensors and humidity sensors on each shelf in the warehousing park;

[0145] The optimization module finds the optimal temperature and the optimal humidity through the dragonfly algorithm, sets the optimal temperature deviation value and the optimal humidity deviation value, and constructs the optimal temperature range and the optimal humidity range;

[0146] The shelf temperature and humidity state analysis module sequentially determines whether each temperature data in the temperature data set and each humidity data in the humidity data set are within the optimal temperature range and the optimal humidity range, and analyzes the temperature and humidity states of each shelf according to the determination results.

[0147] In the description of this specification, the descriptions referring to terms such as "one embodiment", "example", "specific example", etc. mean that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.

[0148] The preferred embodiments of the invention disclosed above are only used to help illustrate the invention. The preferred embodiments do not elaborate on all the details, nor do they limit the invention to the specific embodiments described. Obviously, many modifications and variations can be made according to the content of this specification. These embodiments are selected and specifically described in this specification in order to better explain the principles and practical applications of the invention, so that those skilled in the art can well understand and utilize the invention.

Claims

1. A method for operation and maintenance management of a warehousing park based on digital twin, characterized in that, It includes the following steps: S1. Collect the location data of each shelf in the warehousing park and the cargo data of the goods stored on each shelf. Based on the location data and the cargo data, construct a digital twin model through a 3D modeling tool; S2. When inbound and outbound operations are required, collect the inbound and outbound cargo data. According to the inbound and outbound cargo data, lock the target shelf location in the digital twin model, determine the AGV cart for performing the inbound and outbound operations, and plan the optimal action route in the digital twin model; S3. Send an instruction to the AGV cart. The AGV cart performs the inbound and outbound operations according to the planned optimal action route. After the inbound and outbound operations are completed, collect the weight change data of the target shelf, and compare the numerical value with the weight data of the inbound and outbound cargo to determine whether there is an abnormality in the inbound and outbound operations; S4. Intelligently manage the environmental parameters of the warehousing park through sensors.

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

3. The method for operation and maintenance management of a warehousing park based on digital twin according to claim 2, wherein, The S2 includes the following steps: S21. When inbound and outbound operations are performed, collect the inbound and outbound cargo data, and lock the target shelf location in the digital twin model according to the inbound and outbound cargo data; S22. Determine the AGV cart for performing the inbound and outbound operations, and plan the optimal action route in the digital twin model according to the location of the target shelf.

4. The method for operation and maintenance management of a warehousing park based on digital twin according to claim 3, wherein The planning of the optimal action route in the S22 includes the following steps: S221. Draw a grid map according to the terrain of the warehousing park; S222. Construct an ant population, and set the population size, the third current iteration number, and the third maximum iteration number; Set the starting position and the ending position in the grid map. Put N ants into the starting position for path search. Set a taboo list for each ant, and use the grid positions of all shelves and the starting position as taboo nodes. The ant individuals will not move to the taboo nodes during the path search process; S223. Each ant in the ant population starts traversing from the starting position, calculates the probability of entering each accessible grid according to the probability transfer formula, and selects the next grid for the ant individual to move through the roulette method. After the ant individual moves to a new grid, add the new grid position to the taboo list of the ant; S224. Judge whether each ant individual in the ant population has reached the end. If each ant individual in the ant population has reached the end, calculate the path length of each ant individual in the ant population, use the path with the shortest path length as the optimal path, and then enter S225; otherwise, return to S223; S225. During the path search process, ant individuals release pheromones along the way. To avoid the pheromone concentration on the path being too high and affecting the path search of ant individuals in the next iteration, the pheromone is updated; S226. Determine whether the third current iteration number is less than the third maximum iteration number. If the third current iteration number is less than the third maximum iteration number, then increment the third current iteration number by 1 and return to S223; otherwise, compare the lengths of the optimal paths in each iteration process and output the path with the shortest length as the optimal action route.

5. A method for operation and maintenance management of a warehousing park based on digital twin according to claim 4, characterized in that, The said S3 includes the following steps: S31. Send an instruction to the AGV cart, and the AGV cart moves to the target shelf according to the planned optimal action route, and uses the robotic arm installed on the AGV cart to perform the inbound and outbound operations. At the same time, update the cargo data in the digital twin model in combination with the inbound and outbound cargo data; S32. After completing the inbound and outbound operations, collect the weight change data ΔM of the target shelf through the gravity detection sensor installed on the shelf, and extract the weight data M of the inbound and outbound cargoes from the collected inbound and outbound cargo data; S33. Determine whether an abnormality occurs in the inbound and outbound operations; Compare the numerical sizes of the weight change data ΔM of the target shelf and the weight data M of the inbound and outbound cargoes; If ΔM = M, no operation is performed; If ΔM ≠ M, feedback that an abnormality has occurred in the inbound and outbound operations to the main control unit, and the main control unit issues a storage and retrieval prompt signal at the corresponding shelf position in the digital twin model.

6. The method for operation and maintenance management of a warehousing park based on digital twin according to claim 5, wherein, The said S4 includes the following steps: S41. Install temperature sensors and humidity sensors on each shelf in the warehousing park, and collect the temperature data and humidity data of each shelf in real time to obtain a temperature data set and a humidity data set; S42. Use an intelligent optimization algorithm to find the optimal temperature range and the optimal humidity range; S43. Sequentially determine whether each temperature data in the temperature data set and each humidity data in the humidity data set are within the optimal temperature range and the optimal humidity range, and analyze the temperature and humidity states of each shelf according to the judgment results.

7. A method for operation and maintenance management of a warehousing park based on digital twin according to claim 6, characterized in that, The said S41 includes the following steps: S411. Install temperature sensors on each shelf in the warehousing park, and collect the temperature data of each shelf in real time to obtain a real-time temperature data set; S412. Install humidity sensors on each shelf in the warehousing park, and collect the humidity data of each shelf in real time to obtain a real-time humidity data set.

8. A method for operation and maintenance management of a warehousing park based on digital twin according to claim 7, characterized in that, The said S42 includes the following steps: S421. Construct the first dragonfly population and the second dragonfly population, and set the scales of the first dragonfly population and the second dragonfly population to m1 and m2 respectively; set the first maximum number of iterations to T1 max and the second maximum number of iterations to T2 max ; set the dimension of the optimization search space for both the first dragonfly population and the second dragonfly population to one-dimensional; S422. Find the maximum value c and the minimum value c from the real-time temperature dataset, and randomly select m1 data between [c, c] as the initial position set of the first dragonfly population; max and the minimum value c min , and randomly select m1 data between [c min , c max as the initial position set of the first dragonfly population; Find the maximum value c' from the real-time humidity dataset max and the minimum value c' min , and randomly select m2 data between [c' min , c' max as the initial position set of the second dragonfly population; S423. Calculate the fitness function values of each dragonfly individual in the first dragonfly population and the second dragonfly population; S424. Start the iterative operation, set the current iteration number of the first dragonfly population as T1 and the current iteration number of the second dragonfly population as T2; in each iteration process of each dragonfly individual in the first dragonfly population and the second dragonfly population, it will be affected by other dragonfly individuals in the population to update its position, and recalculate the fitness function values of each dragonfly individual in the first dragonfly population and the second dragonfly population after the position update. The dragonfly individual with the highest fitness function value in the first dragonfly population and the second dragonfly population is used as the global optimal solution; S425. Determine whether T1 is less than T1 max If T1 is less than T1 max then increment T1 by 1 and return to S54; otherwise, output the temperature data corresponding to the global optimal solution in the first dragonfly population as the optimal temperature h1; Determine whether T2 is less than T2 max If T2 is less than T2 max then increment T2 by 1 and return to S54; otherwise, output the humidity data corresponding to the global optimal solution in the second dragonfly population 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].

9. The method for operation and maintenance management of a warehousing park based on digital twin according to claim 8, wherein, The S43 includes the following steps: S431. Sequentially determine whether each temperature data in the temperature dataset is within the optimal temperature range; S4311. If each temperature data in the temperature dataset is within the optimal temperature range, then all shelves are in the normal temperature state; otherwise, record the temperature data that is not within the optimal temperature range in the temperature dataset as abnormal temperature data, determine that the shelf corresponding to the abnormal temperature data is in the abnormal temperature state, feedback the abnormal temperature state to the main control unit, send a temperature anomaly prompt signal at the corresponding shelf position in the digital twin model through the main control unit, and send an instruction to the temperature regulator closest to the shelf. After the temperature regulator receives the instruction, adjust 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 each humidity data in the humidity dataset is within the optimal humidity range, then all shelves are in the normal humidity state; otherwise, record the humidity data that is not within the optimal humidity range in the humidity dataset as abnormal humidity data, determine that the shelf corresponding to the abnormal humidity data is in the abnormal humidity state, feedback the abnormal humidity state to the main control unit, send a humidity anomaly prompt signal at the corresponding shelf position in the digital twin model through the main control unit, and send an instruction to the humidity regulator closest to the shelf. After the humidity regulator receives the instruction, adjust the humidity of the shelf to the optimal humidity.

10. A system for implementing the digital twin-based warehousing park operation and maintenance management method according to any one of claims 1 - 9.

Images