Path planning and verification method based on digital twinning
By simulating and adjusting the AGV path in a virtual scene, the problems of multi-vehicle congestion and order time cost were solved, the optimal planning and dynamic adjustment of the AGV path were achieved, and production efficiency and flexibility were improved.
Patent Information
- Application Number
- CN202510867849.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-26
- Publication Date
- 2025-09-26
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing AGV path planning algorithm is difficult to comprehensively consider the congestion problems between multiple vehicles and the order time cost, and lacks simulation and dynamic adjustment capabilities based on digital twins, resulting in low production efficiency and production delays.
Build a virtual scene that corresponds one-to-one with the actual production line, monitor and obtain actual production data, simulate in the virtual environment, generate the optimal AGV path planning, and update the actual production data in real time to adjust the path.
Through digital twin technology, by comprehensively considering trolley congestion and order time costs, optimal planning and dynamic adjustment of AGV trolley paths are achieved, thereby improving production efficiency and flexibility.
Smart Images
Figure CN120704170A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of path planning technology, and in particular to a path planning and verification method based on digital twins. Background Art
[0002] Automated Guided Vehicles (AGVs) play a vital role in modern production lines. Through automated transport systems, they efficiently handle the transportation of raw materials, parts, and finished products. AGVs precisely navigate between workstations according to pre-set paths and task instructions, ensuring the timely supply of materials and the rapid transfer of finished products. This automated transportation method not only improves production efficiency and reduces the errors and fatigue caused by manual intervention, but also optimizes workshop space utilization, making the production process smoother and more organized. Furthermore, AGV operating data can be fed back to the production management system in real time, facilitating monitoring and scheduling, further enhancing the intelligence of the production line.
[0003] However, despite the important role played by AGVs in production lines, their path planning still has some shortcomings that need to be addressed. In current production line environments, several AGVs are often required to meet production needs, but existing path planning algorithms often find it difficult to comprehensively consider the congestion problems between multiple vehicles and the time cost of orders. When multiple vehicles are in operation, the risk of collisions and congestion between vehicles often occur, which not only reduces transportation efficiency but may also cause production delays. In addition, current path planning lacks simulation and adjustment mechanisms based on digital twin technology. Digital twin technology can simulate and optimize production lines in real time through virtual models, but in actual applications, this technology has not been fully utilized, resulting in insufficient flexibility and adaptability in path planning. It is difficult to dynamically adjust the vehicle's operating path according to actual production conditions, making it impossible to achieve optimal production scheduling results.
[0004] In view of this, a path planning and verification method based on digital twins is needed. Summary of the Invention
[0005] In view of the shortcomings of existing technologies in the path planning of AGVs in production lines, such as multi-vehicle congestion and insufficient optimization of order time and cost, as well as the lack of simulation and dynamic adjustment capabilities based on digital twins, the present invention provides a path planning and verification method based on digital twins, which can comprehensively consider the congestion problems of multiple vehicles and the order time and cost issues, and perform simulation and adjustment based on digital twins. The specific technical solutions are as follows:
[0006] A path planning and verification method based on digital twins includes the following steps:
[0007] Build a virtual scene based on the actual production line, which includes at least a raw material storage warehouse, processing stations, and raw material output stations, and the virtual scene corresponds one-to-one with the actual production line;
[0008] In the virtual scene, according to the actual production situation, set the processing time, raw material input point and finished product output point for each workstation;
[0009] Monitor and obtain actual production data;
[0010] Based on actual production data, simulation is performed in a virtual environment to obtain the optimal AGV path planning;
[0011] Apply the optimal AGV path planning to the actual production line, update the actual production data in real time, and obtain the latest AGV path planning based on the updated actual production data.
[0012] Preferably, the actual production data includes: raw material data, order data and workstation failure data during the actual production process.
[0013] Preferably, the raw material data includes the types of raw materials in the actual production line and the corresponding raw material quantities of each type; the order data includes the actual order quantity obtained; and the workstation failure data in the actual production process is used to reflect whether a failure occurs at each workstation.
[0014] Preferably, the station failure data is obtained by the station failure coefficient w i Determine, when the i-th station fails, the corresponding station failure coefficient w i =1, otherwise the corresponding workstation failure coefficient w i =0.
[0015] Preferably, the process of obtaining the optimal AGV path planning is as follows:
[0016] S1: For all loading and unloading points of all workstations, as well as the location of the finished product warehouse, calculate the distance between them to form a distance matrix D;
[0017] S2: Estimate the lower limit of the number of AGVs required based on the order volume and station processing time:
[0018]
[0019] Where, T avg is the average station processing time, T AGV_avg is the average running time of the AGV, V is the maximum speed of the AGV, Q i is the i-th order data, Indicates rounding up;
[0020] S3: For each AGV, use the path planning algorithm to generate several optimal routes from the starting point to the end point; let R k is the set of optimal routes for the kth AGV, where each route is sorted by path length, and the shorter the path, the better;
[0021] S4: Enumerate all AGV route combinations to form a route combination set R, where each combination corresponds to a possible AGV travel plan;
[0022] S5: For each route combination r∈R, calculate the AGV position distribution at each time t according to the time step Δt. The formula is as follows:
[0023]
[0024] Among them, L k (t) is the position of the kth AGV at time t, are the starting point and end point of the car route, D routek is the route length;
[0025] S6: Divide the virtual environment into S parts, each part has a threshold C s , for each time t, count the number of AGV cars N in each space s (t); traverse each time t and each space s, and check whether it satisfies: N s (t)≤C s If it exists, go to step S7;
[0026] S7: For each space s that exceeds the threshold, calculate the number of vehicles that need to adjust the path: ΔAGV s =N s (t)-C s ; Select ΔAGV from the AGV carts in the space s The car replaces its path with the suboptimal path (from R k Recalculate the adjusted AGV position distribution and repeat step S6 until the number of AGVs in all spaces at all times meets the threshold constraint;
[0027] S8: Under the premise of meeting the order completion, adjust C s and AGV m , find the optimal solution; use heuristic algorithm to C s and AGV m For optimization, the objective function is:
[0028] min(AGV m ×T order )
[0029] Among them, T order is the total time to complete the order, AGV m is the number of AGV vehicles.
[0030] S9: Output the optimal solution, including: output the final number of AGVs m , output the optimal path for each AGV car, the total time T for order completion order , AGV car position distribution map at each moment.
[0031] Preferably, the element D of the distance matrix ij is the Euclidean distance from position i to position j.
[0032] Preferably, the number of AGVs is subject to the following constraints:
[0033] AGV m ≥AGV min .
[0034] Preferably, the method further comprises the following steps:
[0035] Obtain the workstation failure coefficient w of each workstation in real time i ,When a work station fails, the corresponding work station in the ,virtual environment stops working, and the optimal route combination of ,each AGV car is re-determined.
[0036] A computer-readable storage medium includes a stored program, wherein when the program is run, the device where the computer-readable storage medium is located is controlled to execute the path planning and verification method based on digital twins as described above.
[0037] A processor is used to run a program, wherein when the program is running, the path planning and verification method based on digital twins as described above is executed.
[0038] Compared with the prior art, the present invention has the following beneficial effects:
[0039] The present invention builds a virtual scene based on the actual production line, and the virtual scene includes at least a raw material storage warehouse, a processing station, and a raw material output station, and the virtual scene corresponds to the actual production line one by one; in the virtual scene, according to the actual production conditions, the processing time, raw material input point, and finished product output point are set for each station; the actual production data is monitored and obtained; based on the actual production data, simulation is performed in a virtual environment to obtain the optimal AGV trolley path planning; the optimal AGV trolley path planning is applied to the actual production line, and the actual production data is updated in real time, and the latest AGV trolley path planning is obtained according to the updated actual production data. Through the above steps, the present invention can comprehensively consider the congestion problem of several trolleys and the order time cost problem, and perform simulation and adjustment based on digital twins. BRIEF DESCRIPTION OF THE DRAWINGS
[0040] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly describes the drawings required for the specific embodiments or the description of the prior art. Similar elements or parts are generally identified by similar reference numerals throughout the drawings. Elements or parts in the drawings are not necessarily drawn to scale.
[0041] Figure 1 Flow chart of the method of the present invention. DETAILED DESCRIPTION
[0042] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.
[0043] It will be understood that when used in this specification and the appended claims, the terms “comprises” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.
[0044] It should also be understood that the terms used in the present specification are only for the purpose of describing particular embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise.
[0045] It should be further understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
[0046] In one embodiment of the present invention, a path planning and verification method based on digital twin is provided, such as Figure 1 As shown, the following steps are included:
[0047] Step 1: Build a virtual scene based on the actual production line. The virtual scene includes at least a raw material storage warehouse, a processing station, and a raw material output station, and the virtual scene corresponds to the actual production line one by one.
[0048] Step 2: In the virtual scene, set the processing time, raw material input point, and finished product output point for each workstation based on the actual production situation.
[0049] It should be noted that the raw materials and finished products mentioned here refer to the input and output of a specific workstation, and do not refer to the raw materials and finished products output of the entire assembly line. In addition, the processing time is the time it takes from the transportation of materials to the workstation until they are output.
[0050] In this step, the purpose of setting specific processing time, raw material input points, and finished product output points according to the actual production conditions is to facilitate the subsequent one-to-one simulation of the actual operation of the production line. When the specific data of actual production is entered into the virtual scene, it can be guaranteed that the simulation results are consistent with the specific conditions of actual production, which facilitates the direct application of the simulation results to actual production.
[0051] Step 3: Monitor and obtain actual production data.
[0052] In this step, the actual production data includes: raw material data, order data and workstation failure data during the actual production process.
[0053] Among them, the raw material data includes the types of raw materials in the actual production line and the corresponding quantities of raw materials under each type; the order data includes the actual order quantity obtained, that is, the types and quantities of the final products required after the entire production line; the workstation failure data in the actual production process reflects whether each workstation has a failure. In this embodiment, the workstation failure data is calculated by the workstation failure coefficient w i Determine, when the i-th station fails, the corresponding station failure coefficient w i =1, otherwise the corresponding workstation failure coefficient w i =0.
[0054] Step 4: Based on actual production data, simulate in a virtual environment to obtain the optimal AGV path planning. This step is as follows:
[0055] S1: For all loading and unloading points of all workstations, as well as the location of the finished product warehouse, calculate the distance between each other to form a distance matrix D, where the element D of the distance matrix is ij is the Euclidean distance from position i to position j;
[0056] S2: Estimate the lower limit of the number of AGVs required based on the order volume and station processing time:
[0057]
[0058] Where, T avg is the average station processing time, T AGV_avg is the average running time of the AGV, V is the maximum speed of the AGV, Q i is the i-th order data (order data is expressed as: Indicates rounding up, ensuring that the calculation result is an integer. Even if the calculated number of carts is a decimal, it will be rounded up to the next integer to ensure that there are enough AGV carts to meet the demand for order transportation.
[0059] Among them, in order to facilitate subsequent calculations, we first initialize the number of AGV cars AGV m , meet AGV m ≥AGV min .
[0060] S3: For each AGV, use a path planning algorithm (such as A* algorithm, Dijkstra algorithm, etc.) to generate several optimal routes from the starting point to the end point; let R k is the set of optimal routes for the kth AGV, where each route is sorted by path length, and the shorter the path, the better.
[0061] Among them, the A* algorithm is a heuristic path search algorithm that is widely used in path planning and graph search problems. It evaluates the priority of each node by combining the actual cost (the cost from the starting point to the current node) and the heuristic estimate (the estimated cost from the current node to the target node) to select the optimal path. The core of the A* algorithm lies in its heuristic function h(n), which estimates the cost from node n to the target node. By reasonably designing the heuristic function, the A* algorithm can significantly reduce the search space and computing time while ensuring that the shortest path is found. It is particularly suitable for path planning in complex environments, such as robot navigation, game map search and other scenarios, and can efficiently find the optimal path from the starting point to the end point.
[0062] The Dijkstra algorithm is a classic shortest path algorithm used to find the shortest paths from a single source node to all other nodes in a weighted graph. The algorithm gradually expands the set of known shortest paths, selecting the currently known shortest path node each time and updating the path lengths of its adjacent nodes. The core of the Dijkstra algorithm is to maintain a priority queue, selecting nodes for expansion in ascending order of path length. This algorithm ensures that the shortest path from the source node to all other nodes can be found even in the absence of negatively weighted edges in the graph. The Dijkstra algorithm is simple and efficient, making it applicable to path planning problems in various graph structures, such as transportation networks and communication networks. It is one of the fundamental algorithms in the field of path search.
[0063] It should be noted that the enumeration of the path algorithm in the present invention is only for example purposes and does not serve as a technical limitation of the present application. Those skilled in the art can flexibly adjust and use the path algorithm to obtain the path planning set of the vehicle according to actual conditions.
[0064] S4: Enumerate all AGV route combinations to form a route combination set R, where each combination corresponds to a possible AGV travel plan;
[0065] S5: For each route combination r∈R, calculate the AGV position distribution at each time t according to the time step Δt (set according to actual needs). The formula is as follows:
[0066]
[0067] Among them, L k (t) is the position of the kth AGV at time t, are the starting point and end point of the car route, D routek is the route length.
[0068] S6: Divide the virtual environment into S parts, each part has a threshold C s , for each time t, count the number of AGV cars N in each space s (t); traverse each time t and each space s, and check whether it satisfies: N s (t)≤C s If it exists, go to step S7;
[0069] S7: For each space s that exceeds the threshold, calculate the number of vehicles that need to adjust the path: ΔAGV s =N s (t)-C s ; Select ΔAGV from the AGV carts in the space s The car replaces its path with the suboptimal path (from Rk Recalculate the adjusted AGV position distribution and repeat step S6 until the number of AGVs in all spaces at all times meets the threshold constraint;
[0070] S8: Under the premise of meeting the order completion, adjust C s and AGV m , find the optimal solution; use heuristic algorithms (such as genetic algorithms, simulated annealing algorithms, etc.) to C s and AGV m For optimization, the objective function is:
[0071] min(AGV m ×T order )
[0072] Among them, T order is the total time to complete the order, AGV m is the number of AGV vehicles.
[0073] Among them, the genetic algorithm is a search and optimization algorithm based on the principles of natural selection and genetics. It simulates the process of biological evolution and gradually improves the quality of candidate solutions through operations such as selection, crossover (recombination), and mutation. The algorithm begins with an initial population, where each individual (chromosome) represents a possible solution, and its fitness is determined by the objective function. By selecting individuals with high fitness for reproduction, combining crossover operations to produce new offspring, and introducing randomness through mutation, the solution space is continuously explored in an iterative process, ultimately converging to a globally optimal or near-optimal solution. Genetic algorithms have strong global search capabilities and are suitable for complex optimization problems. They are widely used in engineering design, machine learning, scheduling optimization and other fields.
[0074] The simulated annealing algorithm is a stochastic optimization algorithm based on the physical annealing process. It seeks the global optimal solution to an optimization problem by simulating the gradual cooling of atoms in a solid, which gradually reach their lowest energy state. The algorithm begins with an initial solution, generates new solutions through random perturbations, and accepts or rejects them based on the Metropolis criterion. As the "temperature" parameter decreases, the algorithm's search range narrows, eventually stabilizing and finding a near-optimal solution. The simulated annealing algorithm avoids falling into local optima during the search process, exhibiting strong global search capabilities and adaptability. It is suitable for complex nonlinear optimization problems such as the Traveling Salesman Problem (TSP), path planning, and parameter optimization.
[0075] It should be noted that the examples listed in the solution algorithm of the present invention are only for illustrative purposes and are not intended to be technical limitations of the present application. Those skilled in the art can flexibly adjust and use the solution algorithm according to actual conditions to obtain the optimal decision.
[0076] S9: Output the optimal solution, including: output the final number of AGVs m , output the optimal path for each AGV car, the total time T for order completion order , AGV car position distribution map at each moment.
[0077] Step 5: Apply the optimal AGV path planning to the actual production line, update the actual production data in real time, and obtain the latest AGV path planning based on the updated actual production data.
[0078] Step 6: Obtain the station failure coefficient w of each station in real time i ,When a work station fails, the corresponding work station in the ,virtual environment stops working, and the optimal route combination of each AGV ,car is re-determined.
[0079] In summary, the present invention builds a virtual scene based on the actual production line, and the virtual scene includes at least a raw material storage warehouse, a processing station, and a raw material output station, and the virtual scene corresponds to the actual production line one by one; in the virtual scene, according to the actual production conditions, the processing time, raw material input point, and finished product output point are set for each station; the actual production data is monitored and obtained; based on the actual production data, simulation is performed in a virtual environment to obtain the optimal AGV trolley path planning; the optimal AGV trolley path planning is applied to the actual production line, and the actual production data is updated in real time, and the latest AGV trolley path planning is obtained according to the updated actual production data. Through the above steps, the present invention can comprehensively consider the congestion problem of several trolleys and the order time cost problem, and perform simulation and adjustment based on digital twins.
[0080] Those skilled in the art will appreciate that the units of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition of each example has been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.
[0081] In the embodiments provided by the present invention, it should be understood that the division of units is merely a logical function division, and there may be other division methods in actual implementation, for example, multiple units can be combined into one unit, one unit can be split into multiple units, or some features can be ignored, etc.
[0082] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.
[0083] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-0nly Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk, etc., various media that can store program code.
[0084] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some or all of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and description of the present invention.
Claims
1. A path planning and verification method based on digital twins, characterized in that: The following steps are involved: Build a virtual scene based on the actual production line. The virtual scene includes at least a raw material storage warehouse, processing stations, and raw material output stations, and the virtual scene corresponds one-to-one with the actual production line. In the virtual scene, according to the actual production situation, set the processing time, raw material input point and finished product output point for each workstation; Monitor and obtain actual production data; Based on actual production data, simulation is performed in a virtual environment to obtain the optimal AGV path planning; Apply the optimal AGV path planning to the actual production line, update the actual production data in real time, and obtain the latest AGV path planning based on the updated actual production data.
2. A path planning and verification method based on digital twins according to claim 1, characterized in that: Actual production data includes: raw material data, order data, and workstation failure data during the actual production process.
3. A path planning and verification method based on digital twins according to claim 2, characterized in that: Raw material data includes the types of raw materials in the actual production line and the corresponding quantity of raw materials under each type; order data includes the actual number of orders obtained; and workstation failure data in the actual production process is used to reflect whether there is a failure at each workstation.
4. A path planning and verification method based on digital twins according to claim 3, characterized in that: The station failure data is obtained through the station failure coefficient w i Determine, when the i-th station fails, the corresponding station failure coefficient w i =1, otherwise the corresponding workstation failure coefficient w i =0.
5. A path planning and verification method based on digital twins according to claim 1, characterized in that: The process of obtaining the optimal AGV path planning is as follows: S1: For all loading and unloading points of all workstations, as well as the location of the finished product warehouse, calculate the distance between them to form a distance matrix D; S2: Estimate the lower limit of the number of AGVs required based on the order volume and station processing time: Where, T avg is the average station processing time, T AGV_avg is the average running time of the AGV, V is the maximum speed of the AGV, Q i is the i-th order data, Indicates rounding up; S3: For each AGV, use the path planning algorithm to generate several optimal routes from the starting point to the end point; let R k is the set of optimal routes for the kth AGV, where each route is sorted by path length, and the shorter the path, the better; S4: Enumerate all AGV route combinations to form a route combination set R, where each combination corresponds to a possible AGV travel plan; S5: For each route combination r∈R, calculate the AGV position distribution at each time t according to the time step Δt. The formula is as follows: Among them, L k (t) is the position of the kth AGV at time t, are the starting point and end point of the kth AGV route, D routek is the route length; S6: Divide the virtual environment into S parts, each part has a threshold C s , for each time t, count the number of AGV cars N in each space s (t); traverse each time t and each space s, and check whether it satisfies: N s (t)≤C s If it exists, go to step S7; S7: For each space s that exceeds the threshold, calculate the number of vehicles that need to adjust the path: ΔAGV s =N s (t)-C s ; Select ΔAGV from the AGV carts in the space s The car replaces its path with the suboptimal path (from R k Recalculate the adjusted AGV position distribution and repeat step S6 until the number of AGVs in all spaces at all times meets the threshold constraint; S8: Under the premise of meeting the order completion, adjust C s and AGV m , find the optimal solution; use heuristic algorithm to C s and AGV m For optimization, the objective function is: my(AGV m ×T order ) Among them, T order is the total time to complete the order, AGV m is the number of AGV vehicles; S9: Output the optimal solution, including: output the final number of AGVs m , output the optimal path for each AGV car, the total time T for order completion order , AGV car position distribution map at each moment.
6. A path planning and verification method based on digital twins according to claim 5, characterized in that: The element D of the distance matrix ij is the Euclidean distance from position i to position j.
7. A path planning and verification method based on digital twins according to claim 5, characterized in that: The number of AGVs is subject to the following constraints: AGV m ≥AGV min 。 8. A path planning and verification method based on digital twins according to claim 4, characterized in that: The following steps are also included: Obtain the workstation failure coefficient w of each workstation in real time i ,When a work station fails, the corresponding work station in the ,virtual environment stops working, and the optimal route combination of each AGV ,car is re-determined.
9. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored program, wherein, when the program is running, the device where the computer-readable storage medium is located is controlled to execute the digital twin-based path planning and verification method according to any one of claims 1 to 8.
10. A processor, characterized in that: The processor is used to run a program, wherein when the program is running, the path planning and verification method based on digital twins described in any one of claims 1 to 8 is executed.