Method for optimizing physical layout of production workshop equipment based on digital twinning

Abstract

The invention discloses a digital twinning-based production workshop equipment physical layout optimization method, which is suitable for layout planning and optimization design in industrial production. The method comprises the steps of simulation modeling, workspace construction, layout optimization, collision detection, layout evaluation and the like. The method focuses on equipment layout optimization in the planning design stage, and does not need to depend on parameter setting, data acquisition and complex model training in the production operation process, so that the method is more suitable for rapid design adjustment in the initial stage of layout, the optimization process is simplified, and the design efficiency and operability are improved. Through the simulation and optimization algorithm based on digital twinning, the position of the equipment can be adjusted more intelligently, efficiently and dynamically, so that the layout is more reasonable and compact, and the space utilization rate of a production workshop is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of typical parts processing, and in particular to a method for optimizing the physical layout of production workshop equipment based on digital twins. Background Art

[0002] With the development of intelligent manufacturing, the layout planning of production workshops plays an increasingly important role in improving production efficiency, optimizing resource allocation and reducing cost waste. At present, traditional workshop layout methods usually rely on manual experience and static models, which are difficult to cope with complex and changing production needs and cannot fully utilize workshop space. This static layout method often ignores the actual physical size of the equipment and the dynamic relationship between them, resulting in low space utilization, poor material flow and reduced production efficiency.

[0003] With the rapid development of digital twin technology, it has gradually become a reality to import the 3D model of the equipment into the virtual environment for simulation verification. Through this technology, the actual production environment in the factory workshop can be accurately reproduced in the virtual space, and the physical characteristics and layout effects of the equipment can be simulated. This allows not only to intuitively see the placement of the equipment when planning and adjusting the workshop layout, but also to verify the feasibility of different layout plans through simulation.

[0004] Therefore, it is necessary to provide an effective method for optimizing the physical layout of equipment by combining digital twin technology with intelligent optimization algorithms to solve the problems of insufficient flexibility in layout adjustment and low space utilization in existing technologies. Summary of the invention

[0005] The purpose of the present invention is to provide a method for optimizing the physical layout of equipment in a production workshop based on digital twins, in response to the problems of unreasonable equipment layout and complex adjustment in current industrial production, starting from the key factors that affect the efficiency of the physical layout of equipment and space utilization. This method uses simulation technology and intelligent optimization algorithms to achieve dynamic adjustment and optimization of the equipment layout in the production workshop, aiming to improve space utilization and production efficiency, and is suitable for layout planning and optimization design in industrial production. By modeling, testing and verification, and layout optimization in a virtual simulation environment, dynamic adjustment of equipment layout and improvement of space utilization can be achieved, thereby improving overall production efficiency. A method for optimizing the physical layout of equipment in a production workshop based on digital twins.

[0006] The technical solution of the present invention is as follows:

[0007] A method for optimizing the physical layout of production workshop equipment based on digital twins, comprising the following steps:

[0008] S1 Simulation Modeling

[0009] Based on the processing technology of the equipment, the entire production process is modeled using simulation software;

[0010] By inputting the equipment processing time and material transportation method, the simulation results of the set production process are calculated and output to provide data support for subsequent layout optimization;

[0011] S2 workspace construction

[0012] S2.1 Carry out physical modeling of the three-dimensional workspace and define the spatial dimensions of the equipment and workshop;

[0013] S2.2 Each device has a unique number and a collision body. By initializing the device model in the virtual environment, an optimized three-dimensional model corresponding to the real device is established;

[0014] S2.3 collects the position information of the object to be optimized each time, and passes this data as input to the particle swarm intelligent optimization algorithm, which is used in the subsequent iterative optimization process;

[0015] S3 layout optimization

[0016] Set the iteration termination condition T, use the particle swarm optimization algorithm PSO to optimize the equipment layout, and feed back the optimized equipment location information to the digital twin space;

[0017] S4 Collision Detection

[0018] When a device collides with other devices or boundaries during movement, the layout is optimized and adjusted according to a layout reorganization algorithm; the layout reorganization algorithm includes:

[0019] Each time a collision occurs, the current count of collisions between the two colliding objects (recorded as current count) and the total count of collisions (recorded as total count) are recorded;

[0020] When the value of (current count ÷ total count) is less than the set recombination probability value, if there is a suitable vacancy at the displacement point pointed by the velocity vector, the moving object will move directly to that position; if there is no suitable vacancy at the target vacancy pointed by the velocity vector, the moving object will search for a suitable vacancy along the edge of the collided object along the shortest path until it reaches the target vacancy; if no suitable vacancy is found until it reaches the target vacancy, the move will be abandoned;

[0021] When the value of (current count ÷ total count) is greater than or equal to the set reorganization probability value, the forced layout reorganization operation is performed. When entering the forced layout reorganization stage, if the target space is a suitable space, the object can be placed directly in the target space. If the target space is not a suitable space, the object is placed directly in the target space, and then the layout adjustment operation is performed;

[0022] Furthermore, the layout adjustment is performed by determining the positions and overlaps of the collision objects and making corresponding adjustments in each direction to eliminate overlaps and optimize the overall layout;

[0023] The final stage of layout reorganization is center positioning, which includes: calculating the geometric center of the entire equipment layout to make it coincide with the geometric center point of the workshop layout; if this iteration meets the preset iteration termination condition T, the layout iteration optimization is stopped and step S5 is entered for layout evaluation; otherwise, return to step S2.3.

[0024] S5 Layout Evaluation

[0025] Calculate the total occupied space of the equipment and evaluate the space utilization of the workshop layout to determine whether the layout optimization result meets the preset iteration termination condition T. If not, return to step S2.3.

[0026] Furthermore, the update formula of the j-th dimension coordinate of the ith particle of the t+1th generation in the particle swarm intelligent optimization algorithm is:

[0027] x ij (t+1)=x ij (t)+v ij (t+1)

[0028] v ij (t+1)=wv ij (t)+c1r1(t)[p ij (t)-x ij (t)]+c2r2(t)[p gj (t)-x ij (t)]

[0029] Where: v ij (t) represents the j-th dimension velocity of the ith particle in the current generation (the tth generation); v ij (t+1) represents the j-dimensional velocity of the ith particle in the next generation (t+1th generation); w represents the inertia weight, which controls the influence of the current velocity of the particle in the next generation and is used to balance the global and local search capabilities of the algorithm; c1 represents the self-cognition coefficient, which is used to adjust the particle's own optimal position p ij (t) the effect on its speed; p ij (t) represents the individual historical best position of the i-th particle in the j-th dimension of the t-th generation; c2 represents the self-cognition coefficient, which is used to adjust the particle's own best position p ij (t) the effect on its speed; p gj(t) represents the global optimal position of the jth dimension, which means the best position historically reached by all particles in the particle swarm; r1(t) and r2(t) represent random numbers between 0 and 1, ensuring the diversity of particles in the search space.

[0030] Furthermore, the material transportation mode is used to calculate the material transportation time between devices; the material transportation mode includes two types: straight-line transportation and two-segment broken-line transportation; the material transportation time between devices is calculated based on a two-dimensional world coordinate system; when the line between the devices is parallel to the coordinate system, the material transportation mode between the devices is only straight-line transportation; when the line between the devices intersects the coordinate system, the material transportation mode can be straight-line transportation or two-segment broken-line transportation; the material transportation time between devices is determined by the total length of the transportation line segment;

[0031] The two-segment broken-line transport mode means that when the connecting line between the equipment intersects the coordinate system, the transport path of the material is connected by two straight line segments which are parallel to the coordinate axis in sequence, so as to avoid obstacles or adapt to the actual layout.

[0032] Furthermore, the global best position in the global search process refers to the best position among all the preceding and succeeding devices of the current device.

[0033] Furthermore, the objects corresponding to all equipment cannot exceed the boundary range of the workshop layout. If an object exceeds the boundary, you can choose to re-optimize or select the reasonable data in the most recent iteration as the final optimization result; if there is no reasonable iteration data after multiple retries, you can choose different process rules to re-simulate the model or expand the workshop layout size.

[0034] Furthermore, the space utilization value U is calculated, and the curve graph of the simulation result S, the curve graph of the space utilization U, and the curve graph of the comprehensive index I are displayed through the Ui panel in the digital twin space, which is convenient for analyzing and selecting appropriate layout optimization results; the calculation formula of the comprehensive index I is as follows:

[0035]

[0036] Among them, S min represents the minimum value of the simulation results among all device layout optimization solutions, S represents the current simulation result, and U max represents the maximum value of space utilization among all equipment layout optimization schemes, U represents the space utilization of the current equipment layout optimization scheme, and γ represents the weight coefficient;

[0037] By observing the layout space utilization, simulation time curve and comprehensive index curve, the convergence of layout optimization iteration can be evaluated, and the optimization iteration process can be terminated early.

[0038] Furthermore, the suitable empty space refers to a position where the object does not overlap with other surrounding objects after being placed;

[0039] The target empty position refers to the displacement position pointed to by the particle velocity vector calculated by the particle swarm intelligent optimization algorithm or the movement position across the boundary of the collided object along the velocity vector direction;

[0040] The shortest path means that when a moving object is searching for a suitable empty space around a collided object, starting from the center point of the moving object, a ray with a velocity vector as the direction will divide the collided object into two parts, and the moving object will preferentially move along the boundary of the area with a smaller area to shorten the path for searching for a suitable empty space as much as possible.

[0041] Furthermore, the layout adjustment includes the following steps:

[0042] Calculate the size of the overlapping area between the current object and the surrounding collision objects in the space directly above, directly below, directly to the left, and directly to the right;

[0043] According to the positions of the objects in the overlapping area, all the objects located at the corresponding positions above, below, to the left and to the right of the current object are determined;

[0044] The moving distance of the objects in the corresponding position is calculated according to the projection of the overlapping area on the position to eliminate the overlap and restore the rationality of the layout.

[0045] Furthermore, establishing a three-dimensional model corresponding to the real device includes setting the height of the device model to a uniform standard value during the construction of the workspace; the size of the collision body increases the range of the device working space accordingly;

[0046] The simulation software used to model the entire production process is Plant Simulation;

[0047] The physical modeling of the three-dimensional workspace utilizes Unity3d.

[0048] A computer-readable storage medium having a computer program stored thereon, the program being executed by a processor to implement the steps of a method for optimizing the physical layout of production workshop equipment based on digital twins described in the present invention.

[0049] Compared with the prior art, the present invention has the following beneficial effects:

[0050] (1) Through simulation and intelligent optimization algorithms based on digital twins, the equipment position can be adjusted dynamically and efficiently, making the equipment layout more reasonable and compact, thereby improving the utilization of workshop space;

[0051] (2) Unlike the production line layout algorithm based on neural network, the present invention focuses on the equipment layout optimization in the planning and design stage, without relying on parameter setting, data collection and complex model training during the production operation. This makes the present invention more suitable for rapid design adjustment in the early stage of layout, simplifies the optimization process, and improves design efficiency and operability. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 This is an overall flow chart of the method for optimizing the physical layout of production workshop equipment based on digital twins of the present invention.

[0053] Figure 2 Schematic diagram of the collision body movement rules.

[0054] Figure 3 Adjust the schematic for layout. DETAILED DESCRIPTION

[0055] See also Figure 1 , a method for optimizing the physical layout of production workshop equipment based on digital twins, comprising the following steps:

[0056] 1. Simulation modeling, including the following steps:

[0057] 1.1 Set the processing time for each device, and define the material processing path according to the process processing rules. The devices are connected by conveyor belts. Set the number of processed materials to 1000, and enable the non-animation simulation mode;

[0058] 1.2 Add a unique ID attribute to each device, and set the material transportation mode between devices to be a straight-line transportation mode or a two-segment zigzag transportation mode; use the equipment table equipment in the database to store equipment information, and use the transport table to store the equipment information that chooses to use the two-segment zigzag transportation mode;

[0059] 1.3 Establish a socket channel with the digital twin space built on the Unity3d platform, wait for the signal to start simulation, dynamically set the conveyor speed v of the conveyor belt according to the transport table in the database, and output the simulation result rt to the digital twin workspace.

[0060] 2. Workspace construction, including the following steps:

[0061] 2.1 The workspace will read the required data from the database and assign an ID number for this optimization process to the object corresponding to each device; for the equipment that needs layout optimization, set the length el and width ew size information, as well as its working space size, and uniformly set the height of the equipment to 1;

[0062] 2.2 Set the length sl and width sw of the workshop size; if the equipment is not allowed to be close to the wall or workshop boundary, and the distance g needs to be maintained, the corresponding value needs to be added to the workshop size:

[0063] sl=sl+g,sw=sw+g;

[0064] 2.3 Check whether the workshop size can accommodate the equipment to be optimized, that is, whether:

[0065] and

[0066] Where i is a device to be optimized;

[0067] 2.4 Add a collision body of corresponding size to each device object and add a collision detection script; for easy observation, set a random map for each object;

[0068] 2.5 Randomly initialize the position of each device corresponding to the object, and check the random initialization results at the same time; that is, the object cannot exceed the range of the workshop space, and there cannot be overlapping areas between two objects; when the initialization is completed, the collision will not be triggered, and the random initialization is considered successful;

[0069] 2.6 The position information of objects in the digital twin space is passed to the particle swarm intelligent optimization algorithm, and the layout optimization iteration will be performed;

[0070] 2.7 Draw the positions of objects after layout optimization, and display the curve graph of simulation time S, the curve graph of space utilization U and the curve graph of comprehensive index I of this layout in real time on the Ui panel of the digital twin space.

[0071] 3. Layout optimization, including the following steps:

[0072] 3.1 Set the initialization parameters of the particle swarm intelligent optimization algorithm, parameter w: [0.5, 0.8], parameters c1, c2: [0.1, 2] and iteration termination condition T: Where k represents the number of times the layout has been iterated, T k represents the total number of optimization iterations, S represents the current simulation result, and S min represents the minimum value of the simulation results among all layout schemes, U represents the space utilization of the current layout scheme, and U max represents the maximum space utilization rate among all layout schemes, I represents the comprehensive index of the current layout scheme, and I best represents the current best comprehensive indicator, and ε:[0.1,10] is the threshold indicating convergence.

[0073] 3.2 Obtain the list of preceding and succeeding devices of the current device from the database, and the particle swarm intelligent optimization algorithm calculates the j-th dimension global optimal position coordinate p of the ith particle of the tth generation based on it gj (t);

[0074] 3.3 Pass the object layout position information to the particle swarm intelligent optimization algorithm to calculate the j-th dimension coordinate of the ith particle of the t+1th generation:

[0075] x ij (t+1)=x ij (t)+v ij (t+1)

[0076] Among them, v ij (t+1)=wv ij (t)+c1r1(t)[p ij (t)-x ij (t)]+c2r2(t)[p gj (t)-x ij (t)];

[0077] 3.4 Read the transport table from the database, calculate the transport distance s between the associated devices according to the transport type, write the result into the database, and send a simulation start signal through the socket to perform simulation calculation of the fitness value;

[0078] Furthermore, the calculation formula of the transport distance s between the associated devices is:

[0079] s=|Ax-Bx|+|Ay-By|

[0080] Where A and B are two associated devices, Ax and Bx represent the horizontal coordinates of device A and device B on the two-dimensional xoy plane, and Ay and By represent the vertical coordinates of device A and device B on the two-dimensional xoy plane.

[0081] 3.5 The particle swarm intelligent optimization algorithm feeds back the optimized device location information to the digital twin space.

[0082] 4. Collision detection, including:

[0083] The detection of non-compliant objects with overlapping spaces is achieved by mounting collision detection scripts on objects in the digital twin space. After receiving the device location information of the particle swarm intelligent optimization algorithm, the layout of the corresponding objects of the device in the digital twin space is regenerated. If a collision occurs between objects, the collision information is collected, and an object is randomly selected from all the colliding objects to start the layout reorganization algorithm, and the particle swarm intelligent optimization algorithm is adaptively adjusted.

[0084] The layout reorganization algorithm includes:

[0085] Set the probability value of layout reorganization lr = 0.3. When the value of (current count ÷ total count) is less than lr, if the target space is a suitable space, the object is directly placed in the target space;

[0086] like Figure 2 As shown, if the target space is not a suitable space, a two-dimensional plane coordinate system xoy is established with the center point of the current object as the origin o. Starting from the origin, there are two rays passing through the center point of the collided object and along the direction of the velocity vector, namely α and β; from ray α to ray β, the path-finding direction of the object can be determined to be clockwise or counterclockwise, so that the current object moves along this direction close to the edge of the collided object to find a suitable space for placement; if the current object still does not find a suitable space before reaching the target space, then the movement is abandoned;

[0087] The forced layout reorganization operation will only be performed when the value of (current count ÷ total count) is greater than or equal to lr; during the forced layout reorganization stage, if the target space is a suitable space, the object can be directly placed in the target space; if the target space is not a suitable space, the object is directly placed in the target space, and then the layout adjustment operation is performed;

[0088] like Figure 3 As shown, take the two-dimensional plane coordinate system xoy established with the center point of the current object as the origin o as a reference, and find all objects whose center points are located in the positive direction of the x-axis, the negative direction of the x-axis, the positive direction of the y-axis, and the negative direction of the y-axis respectively;

[0089] Calculate the difference mv between the minimum value of the lower boundary and the maximum value of the upper boundary of the projection of the overlapping area on the corresponding direction coordinate axis when the objects in the above respective directions collide with the current object;

[0090] Move the objects in the above directions by a distance mv along the corresponding coordinate axis;

[0091] When all objects have completed the layout reorganization, calculate the geometric center points of all current objects to make them coincide with the geometric center points of the workshop layout; if an object collides with the boundary of the workshop layout, move it horizontally into the workshop layout and apply a layout adjustment operation to it; record whether there are objects beyond the boundary in the layout optimization result, and record the object position information of the kth layout in the database table posLog; if this iteration meets the preset iteration termination condition T, stop the layout iteration optimization and enter step 5 for layout evaluation; otherwise, return to step 2.6.

[0092] 5. Layout evaluation, including the following steps:

[0093] 5.1 Rationality of Detection Layout Optimization

[0094] Evaluate the layout optimization results every N iterations to check whether the objects corresponding to all equipment exceed the boundary range of the workshop layout. If the required results cannot be obtained after N consecutive layout optimization rationality checks, it may be necessary to re-simulate the model, adjust the process route, or expand the workshop layout size;

[0095] 5.2 Calculation of space utilization value U

[0096] The Ui panel in the digital twin space displays the curve graph of the simulation result S, the curve graph of the space utilization rate U, and the curve graph of the comprehensive index I, which is convenient for analyzing and selecting appropriate layout optimization results. When necessary, data can be read from the database table posLog to restore and reproduce the equipment layout;

[0097] The calculation formula of comprehensive index I is as follows:

[0098]

[0099] Among them, S min represents the minimum value of the simulation results among all device layout optimization solutions, S represents the current simulation result, and U max represents the maximum value of space utilization among all equipment layout optimization solutions, U represents the space utilization of the current equipment layout optimization solution, and γ: [0.5, 0.7] represents the weight coefficient;

[0100] 5.3 Determine whether the layout optimization process has converged by observing the layout space utilization curve, simulation time curve and comprehensive index curve; when the three tend to be stable, it indicates that the optimization iteration has converged. At this time, you can manually terminate the iteration and select the reasonable data in the most recent iteration as the final device layout optimization plan; if the iteration has not stopped and the convergence conditions have not been met, return to step 2.6 to continue the iterative optimization process.

[0101] It should be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "includes..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0102] The above-mentioned embodiments only express the specific implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the protection scope of the present application. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the technical solution concept of the present application, and these all belong to the protection scope of the present application.

Claims

1. A method for optimizing the physical layout of production workshop equipment based on digital twins, characterized in that: The following steps are involved: S1 Simulation Modeling Based on the processing technology of the equipment, the entire production process is modeled using simulation software; By inputting the equipment processing time and material transportation method, the simulation results of the set production process are calculated and output to provide data support for subsequent layout optimization; S2 workspace construction S2.1 Carry out physical modeling of the three-dimensional workspace and define the spatial dimensions of the equipment and workshop; S2.2 Each device has a unique number and a collision body. By initializing the device model in the virtual environment, an optimized three-dimensional model corresponding to the real device is established; S2.3 collects the position information of the object to be optimized each time, and passes this data as input to the particle swarm intelligent optimization algorithm, which is used in the subsequent iterative optimization process; S3 layout optimization Set the iteration termination condition T, use the particle swarm optimization algorithm PSO to optimize the equipment layout, and feed back the optimized equipment location information to the digital twin space; The iteration termination condition T is: Where: k represents the number of times the layout has been iterated, T k represents the total number of optimization iterations, S represents the current simulation result, and S min represents the minimum value of the simulation results among all layout schemes, U represents the space utilization of the current layout scheme, and U max represents the maximum space utilization rate among all layout schemes, I represents the comprehensive index of the current layout scheme, and I best represents the best comprehensive indicator at present, and ε represents the convergence threshold; S4 Collision Detection When a device collides with other devices or boundaries during movement, the layout is optimized and adjusted according to a layout reorganization algorithm, and the layout reorganization algorithm includes: Each time a collision occurs, the current count of collisions between the two collision objects and the total count of collisions are recorded, and the value of "current count ÷ total count" is calculated and judged; When the value of "Current count ÷ Total count" is less than the set recombination probability value, if there is a suitable vacancy at the displacement point pointed by the velocity vector, the moving object will move directly to that position; if there is no suitable vacancy at the target vacancy pointed by the velocity vector, the moving object will search for a suitable vacancy along the edge of the collided object along the shortest path until it reaches the target vacancy; if no suitable vacancy is found until it reaches the target vacancy, the move will be abandoned; When the value of "Current count ÷ Total count" is greater than or equal to the set reorganization probability value, the forced layout reorganization operation is performed; when entering the forced layout reorganization stage, if the target space is a suitable space, the object can be directly placed in the target space; if the target space is not a suitable space, the object is directly placed in the target space, and then the layout adjustment operation is performed; the layout adjustment includes determining the position and overlap of the collision objects, and making corresponding adjustments in each direction to eliminate overlap and optimize the overall layout; The final stage of layout reorganization is center positioning, which includes: calculating the geometric center of the entire equipment layout to make it coincide with the geometric center point of the workshop layout; if this iteration meets the preset iteration termination condition T, the layout iteration optimization is stopped and step S5 is entered for layout evaluation; otherwise, it returns to step S2.3; S5 Layout Evaluation Calculate the total occupied space of the equipment and evaluate the space utilization of the workshop layout to determine whether the layout optimization result meets the preset iteration termination condition T. If not, return to step S2.

3.

2. The method according to claim 1, characterized in that: The update formula of the j-dimensional coordinate of the ith particle of the t+1th generation in the particle swarm intelligent optimization algorithm is: x ij (t+1)=x ij (t)+v ij (t+1) where, v ij (t + 1)= wv ij (t)+ c1r1(t)[p ij (t)- x ij (t)]+ c2r2(t)[p gj (t)- x ij (t)] v ij (t) represents the j-th dimension velocity of the ith particle in the current generation (the tth generation); v ij (t+1) represents the j-dimensional velocity of the ith particle in the next generation (t+1th generation); w represents the inertia weight, which controls the influence of the current velocity of the particle in the next generation and is used to balance the global and local search capabilities of the algorithm; c1 represents the self-cognition coefficient, which is used to adjust the particle's own optimal position p ij (t) the effect on its speed; p ij (t) represents the individual historical best position of the i-th particle in the j-th dimension of the t-th generation; c2 represents the self-cognition coefficient, which is used to adjust the particle's own best position p ij (t) the effect on its speed; p gj (t) represents the global optimal position of the jth dimension, which means the best position historically reached by all particles in the particle swarm; r1(t) and r2(t) represent random numbers between 0 and 1, ensuring the diversity of particles in the search space.

3. The method according to claim 1, characterized in that In step S1: The material transportation mode is used to calculate the material transportation time between devices; the material transportation mode includes two types: straight-line transportation and two-segment broken-line transportation; the material transportation time between devices is calculated based on the two-dimensional world coordinate system; when the line between the devices is parallel to the coordinate system, the material transportation mode between the devices is only straight-line transportation; when the line between the devices intersects the coordinate system, the material transportation mode includes straight-line transportation or two-segment broken-line transportation; the material transportation time between devices is determined by the total length of the transportation line segment; The two-segment broken-line transport mode means that when the connecting line between the equipment intersects the coordinate system, the transport path of the material is connected by two straight line segments which are parallel to the coordinate axis in sequence, so as to avoid obstacles or adapt to the actual layout.

4. The method according to claim 2, characterized in that: The global best position in the global search process refers to the best position among all the preceding and succeeding devices of the current device.

5. The method according to claim 1, characterized in that Step S4 also includes: The objects corresponding to all equipment cannot exceed the boundary range of the workshop layout; if the objects exceed the boundary, choose to re-optimize or select the reasonable data in the most recent iteration process as the final optimization result; if there is no reasonable iterative data after multiple retries, choose different process rules to re-simulate the model or expand the workshop layout size.

6. The method according to claim 1, characterized in that Step S5 also includes: Calculate the space utilization value U, and display the curve graph of the simulation result S, the curve graph of the space utilization U, and the curve graph of the comprehensive index I through the Ui panel in the digital twin space, which is convenient for analyzing and selecting appropriate layout optimization results; the calculation formula of the comprehensive index I is as follows: Among them, S min represents the minimum value of the simulation results among all device layout optimization solutions, S represents the current simulation result, and U max represents the maximum value of space utilization among all equipment layout optimization schemes, U represents the space utilization of the current equipment layout optimization scheme, and γ represents the weight coefficient; By observing the layout space utilization, simulation time curve and comprehensive index curve, determine whether the layout optimization process has converged; when the space utilization, simulation time curve and comprehensive index curve tend to be stable, it indicates that the optimization iteration has converged. At this time, manually terminate the iteration and select the reasonable data in the most recent iteration as the final device layout optimization plan; if the iteration is not stopped and the convergence condition is not met, return to step 2.

3.

7. The method according to claim 1, characterized in that: The suitable empty space refers to a position where the object does not overlap with other surrounding objects after being placed; The target empty position refers to the displacement position pointed to by the particle velocity vector calculated by the particle swarm intelligent optimization algorithm or the movement position across the boundary of the collided object along the direction of the velocity vector; The shortest path means that when a moving object is searching for a suitable empty space around a collided object, starting from the center point of the moving object, a ray with a velocity vector as the direction will divide the collided object into two parts, and the moving object will preferentially move along the boundary of the area with a smaller area to shorten the path for searching for a suitable empty space.

8. The method according to claim 1, characterized in that Step S4 also includes: The layout adjustment comprises the following steps: Calculate the size of the overlapping area between the current object and the surrounding collision objects directly above, below, to the left, and to the right of the space; According to the positions of the objects in the overlapping area, all the objects located at the corresponding positions above, below, to the left and to the right of the current object are determined; The moving distance of the objects in the corresponding position is calculated according to the projection of the overlapping area on the position to eliminate the overlap and restore the rationality of the layout.

9. The method according to any one of claims 1 to 8, characterized in that: In step S2: Establishing a three-dimensional model corresponding to the real equipment includes setting the height of the equipment model to a uniform standard value during the construction of the workspace; the size of the collision body increases the range of the equipment working space accordingly; The simulation software used to model the entire production process is Plant Simulation; The physical modeling of the three-dimensional workspace utilizes Unity3d; The value of ε is [0.1, 10].

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: The computer program is executed by a processor to implement the steps of a method for optimizing the physical layout of production workshop equipment based on digital twins as described in any one of claims 1 to 9.

Images