Port wharf material movement simulation control method

Abstract

The invention discloses a port wharf material movement simulation control method, which comprises the steps of constructing a simulation movement model, obtaining a first simulation path and a second simulation path, obtaining an explorable space based on the first simulation path and the second simulation path, and performing space optimization on the simulation movement model based on the explorable space. A distributed mobile strategy candidate set is established; penalty term accumulation is carried out on the distributed mobile strategy candidate set to obtain a penalty accumulation value; a composite evaluation network is constructed based on the penalty accumulation value; an expected value is obtained based on the composite evaluation network; and obtaining an optimal distributed movement strategy, and taking a combination of the movement path and the optimal distributed movement strategy as a material movement simulation control method. The method not only improves the efficiency and comprehensiveness of material movement simulation, but also has good interpretability, and can be directly applied to a port wharf material movement simulation control system.

Description

Technical Field

[0001] The invention relates to the field of mobile scheduling, and in particular to a port terminal material movement simulation control method. Background Art

[0002] With the rapid development of domestic and international trade exchanges, port terminals, as key areas of the logistics chain, have a direct impact on the efficiency and cost of the entire logistics chain. Therefore, optimizing the simulation control method of material movement at port terminals plays a vital role in ensuring fast, safe and efficient loading, unloading and transshipment of goods.

[0003] Traditional port terminal material movement control methods mainly rely on manual scheduling and experience judgment, which has many limitations, such as low scheduling efficiency, slow response speed, imprecise cost control and poor adaptability to emergencies. With the rapid development of Internet of Things technology, big data analysis and intelligent algorithms, port terminal material movement control is gradually moving towards automation and intelligence.

[0004] At present, some port material movement scheduling methods have adopted intelligent algorithms to improve the efficiency of material movement, but these methods still have some limitations. For example, existing port material movement scheduling methods usually use a single algorithm to plan paths based on a single optimization point or focus more on finding the shortest path, lacking comprehensive consideration of other factors. In addition, these methods lack a composite evaluation mechanism, and focus on ideal conditions during the movement simulation, lacking consideration of complex environments. Summary of the invention

[0005] The purpose of the present invention is to provide a port terminal material movement simulation control method.

[0006] To achieve the above object, the present invention is implemented according to the following technical solutions:

[0007] A first aspect of the present invention provides a port terminal material movement simulation control method, comprising the following steps:

[0008] Step S1, gridding the port terminal area, obtaining the starting position and target position nodes of material movement, constructing a simulated movement model, and performing path finding through the simulated movement model based on the shortest path priority and the best cost priority to obtain a first simulated path and a second simulated path;

[0009] Step S2, calculating the node probability distribution for the first simulation path and the second simulation path, obtaining an explorable space according to the node probability distribution, and performing spatial optimization on the simulated mobility model based on the explorable space to obtain a dual-objective balanced simulated mobility model;

[0010] Step S3, establishing a distributed mobility strategy candidate set, calculating penalty item accumulation for the distributed mobility strategy candidate set, constructing a composite evaluation network based on the penalty accumulation, calculating an expected value for the composite evaluation network, maximizing the expected value, and obtaining an optimal distributed mobility strategy;

[0011] Step S4, obtaining a material movement path based on the dual-objective balance simulation movement model, and combining the material movement path and the optimal distributed movement strategy as a material movement method.

[0012] Furthermore, the method for constructing the simulated mobility model in step S1 includes:

[0013] Based on the material's moving start and target nodes, use A * The algorithm performs global path planning, decomposes the global path into several local path segments based on the scheduling equipment resources, and smoothes the local path segments to reduce sharp turns and incoherent movements in the local path segments;

[0014] Obtain the obstacle location node and build an obstacle avoidance strategy in the local path segment to optimize the path. The path expression of the material after obstacle avoidance in the local path segment is:

[0015]

[0016] Where k is the obstacle avoidance strategy based on the Dijkstra algorithm, γ = 1 means obtaining the obstacle position node parameters starting from the first obstacle, and f γ is the physical distance between the material and the obstacle location node, d is the material movement parameter, a is the material movement planning coefficient, is the obstacle location node layout feature, and A is the obstacle avoidance behavior planning vector.

[0017] Furthermore, the method for finding a path through the simulated mobility model based on the shortest path priority and the best cost priority includes:

[0018] Get the nodes that the path passes through, and integrate the lengths of adjacent nodes as the shortest path evaluation function;

[0019] Obtain material parameters and material movement time, and construct the optimal cost evaluation function. The expression of the optimal cost evaluation function is:

[0020]

[0021] Among them, H is the material set, p h is the unit price of material h, is the demand frequency of material h, is the risk rate of material h during movement, D h is the demand change of material h, c is the number of dispatching equipment required for movement, f1 and f2 are the unit distance fuel consumption of the equipment when it is empty and fully loaded, respectively, S h is the time efficiency level of the path for the movement of material h, including the material departure, unloading and transportation time, The average cycle time for moving material along the path;

[0022] A path search tree is constructed to traverse all paths based on the shortest path evaluation function and the optimal cost evaluation function. After the traversal is completed, the paths with the smallest shortest path evaluation function value and the smallest optimal cost evaluation function value are selected as the first simulation path and the second simulation path.

[0023] Furthermore, the method for calculating the node probability distribution of the first simulation path and the second simulation path includes:

[0024] A probability distribution function is constructed to calculate the distribution probability of the nodes experienced in the first simulation path and the second simulation path. The expression of the probability distribution function is:

[0025]

[0026] in, is the ratio of the grid where the path passes through the node to all grids, x is the total number of nodes passed through the path, and p k and p i are the partition phases of two adjacent nodes k and i in the grid, D[u k -u i ] represents the Euclidean distance between two adjacent nodes k and i.

[0027] Furthermore, the method of obtaining an explorable space according to the node probability distribution and performing spatial optimization on the simulated mobility model based on the explorable space includes:

[0028] The confidence threshold is set to 0.62, and the confidence space analysis is performed on the nodes experienced in the first simulation path and the second simulation path. When the distribution probability of a node is less than the confidence threshold, it is considered that the confidence space of the node is small and the exploration value is high. The node is taken as an explorable node, and all explorable nodes are integrated to form a continuous explorable space.

[0029] The first simulation path and the second simulation path are taken as the parent generation, the reorganization of the paths is taken as the crossover operation, the adjustment of the nodes on the paths is taken as the mutation operation, and the crossover mutation operation is performed on the parent generation in the explorable space. The specific method of the crossover mutation operation is as follows:

[0030] The simulated binary crossover operator is used for crossover operation, and the calculation formula for the k+1th generation individuals is:

[0031]

[0032] Among them, δ 1,k+1 and δ 2,k+1 is the k+1th generation individual generated after crossover, β qi is the uniform distribution factor, δ 1,k and δ 2,k is the selected k-th generation individual, where the calculation formula of the uniform distribution factor is:

[0033]

[0034] Among them, u i is a random number in [0,1), η is the crossover distribution index;

[0035] The polynomial mutation factor is used as the standard mutation operator to perform mutation operations to generate new individuals. The calculation formula for the k+1 generation of individuals is:

[0036]

[0037] Among them, δ k+1 For the k The k+1th generation individuals obtained by mutation operation, δ k is the selected k-th generation individual, and is the maximum and minimum mutation factors allowed for the kth generation, ξ k is the variation balance factor, where ξ k The calculation formula is:

[0038]

[0039] Among them, r k is a random number uniformly distributed in [0,1], η is the variation distribution index;

[0040] After the crossover and mutation operation, several new paths are obtained. The fitness of the new paths is calculated using the fitness function, and the path with the largest fitness is selected as the optimal solution path. The expression of the fitness function is:

[0041]

[0042] Among them, θ1 and θ2 are the weight coefficients focusing on the shortest path and the optimal cost, respectively, L is the path length, x is the total number of nodes experienced by the path, P i is the total number of grids experienced in the path, d iis the sum of the Manhattan distances between adjacent nodes that have turns in the path, e i is the path smoothing factor. When the steering angle is less than or equal to 30°, e i Set to 100, when the steering angle is greater than 30°, e i Set to 1, It is the cost of moving materials within 1 hour.

[0043] Furthermore, the method of establishing a distributed mobility strategy candidate set and calculating the penalty item accumulation based on the distributed mobility strategy candidate set includes:

[0044] Based on the problem of multi-material movement, the Monte Carlo method is used to generate a candidate set of distributed movement strategies, and the dual-objective balance simulation movement model is combined to generate a path. The simulation platform is used to perform simulation operations based on the multi-material movement strategies and corresponding paths in the candidate set;

[0045] During the simulation, when a material movement conflict occurs, set a material waiting strategy to make low-priority materials wait for high-priority materials to pass through and obtain the conflict waiting time;

[0046] Define penalty rules and calculate the cumulative penalty items for the simulation operation. When the material successfully reaches the end point during the movement, a penalty item with a corresponding movement strategy value of 1 is given. When the material conflicts with other materials during the movement, a penalty item with a corresponding movement strategy value of -1 is given. For other situations, a penalty item with a corresponding movement strategy value of 0 is given.

[0047] Furthermore, the method for constructing a composite evaluation network based on the penalty term accumulation includes:

[0048]

[0049] Where γ is the discount factor, m r 、n r ,q r are the number of times the mobile strategy successfully reaches the end point, conflicts occur, and other situations occur, respectively, r is the global priority evaluation coefficient in the mobile strategy, Cumulative time waiting for conflicts.

[0050] Furthermore, the method of maximizing the expected value of the advantage function in the composite evaluation network to obtain the optimal distributed mobility strategy includes:

[0051] Calculate the softmax distribution and KL divergence of the composite evaluation network, and calculate the expected value based on the score of the composite evaluation network. The calculation formula is:

[0052]

[0053] Among them, φ is the expected value, ω(S) is the score of the composite evaluation network, and D KL is the KL divergence, It is represented as the softmax distribution of the composite evaluation network, Z(s t ) is the normalization factor, KL S is the KL divergence of the composite evaluation network;

[0054] According to the convex optimization theory, the gradient ascent method is used to maximize the expected value, minimize the negative consequences of conflicts, and maximize the positive consequences of successfully reaching the end point, thus obtaining the optimal distributed mobile strategy.

[0055] Furthermore, the method of combining the material movement path and the optimal distributed movement strategy as a material movement method includes: obtaining the material movement path of each material through a dual-objective balance simulation movement model, obtaining the handling sequence and conflict waiting time of each material from the optimal distributed movement strategy, and combining the movement path of each material with the handling sequence and conflict waiting time of each material to obtain a comprehensive material movement plan as a material movement method.

[0056] In a second aspect, an embodiment of the present application further provides a computer-readable storage medium, which stores one or more programs. When the one or more programs are executed by an electronic device including multiple applications, the electronic device executes the method steps described in the first aspect.

[0057] Compared with the prior art, the embodiments of the present invention have at least the following advantages or beneficial effects:

[0058] (1) The present invention provides a port terminal material movement simulation control method by combining A * The algorithm and smoothing algorithm are used for path optimization, the Dijkstra algorithm is used to build an obstacle avoidance strategy, and a variety of algorithms are combined for path finding, which can improve the adaptability and stability when facing different environments and conditions, enhance the robustness of the path finding algorithm, and effectively respond to the dynamic obstacle avoidance and path optimization needs in complex environments.

[0059] (2) The present invention obtains the explorable space of the nodes in the first simulation path and the second simulation path, and spatially optimizes the simulated movement model based on the explorable space to obtain a dual-objective balanced simulated movement model. The dual-objective balanced simulated movement model can simultaneously consider the factors of the shortest path and the optimal cost, and can be flexibly adjusted according to different application scenarios, thereby improving the efficiency and economy of material movement.

[0060] (3) The present invention accumulates penalty items for the distributed mobile strategy candidate set to obtain a penalty accumulation value, and further constructs a composite evaluation network based on the penalty accumulation value, taking into account various situations that may occur during the movement of multiple materials, and constructs a composite evaluation network based on the penalty items, so that the evaluation network takes into account factors such as cost, time, and resources, and obtains a more comprehensive strategy evaluation network. This method helps multiple material movements select a more comprehensive mobile strategy and improves the comprehensiveness of material movement. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 The present invention is a flow chart of the steps of a port terminal material movement simulation control method.

[0062] Figure 2 It is a schematic diagram of the structure of an electronic device in an embodiment of this specification. DETAILED DESCRIPTION

[0063] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0064] Reference Figure 1 As shown, the present invention provides a port terminal material movement simulation control method, comprising:

[0065] Step S1, gridding the port terminal area, obtaining the starting position and target position nodes of material movement, constructing a simulated movement model, and performing path finding through the simulated movement model based on the shortest path priority and the best cost priority to obtain a first simulated path and a second simulated path;

[0066] In the actual evaluation, the MATLAB Function tool is used to mesh the port area, obtain the starting position node A and the target position node B of the material movement, and based on node A and node B, use the improved A * The algorithm performs global path planning, decomposes the global path into several local path segments, uses the DWA algorithm to optimize the local path segments, builds an obstacle avoidance strategy based on the Dijkstra algorithm in the local path segments for path optimization, obtains a simulated mobility model, constructs shortest path first and optimal cost first evaluation functions, performs pathfinding operations through the simulated mobility model, and obtains the first simulated path and the second simulated path.

[0067] Step S2, calculating the node probability distribution for the first simulation path and the second simulation path, obtaining an explorable space according to the node probability distribution, and performing spatial optimization on the simulated mobility model based on the explorable space to obtain a dual-objective balanced simulated mobility model;

[0068] In the actual evaluation, the nodes and grids experienced by the first simulation path and the second simulation path are statistically recorded, and the probability distribution function is constructed to obtain the distribution of the experienced nodes. The confidence threshold is set to 0.62. When the distribution probability of a node is less than the confidence threshold, it is considered that the confidence space of the node is small and the exploration value is high. The node is regarded as an explorable node, and all explorable nodes are integrated to form a continuous explorable space.

[0069] In the actual evaluation, the first simulation path and the second simulation path are taken as parents, the reorganization of the paths is taken as a crossover operation, and the adjustment of the nodes on the paths is taken as a mutation operation. The crossover and mutation operations are performed on the parents in the explorable space, and the path with the largest fitness is selected as the optimal solution path. The optimal solution path balances the shortest path priority and the optimal cost priority. After spatial optimization of the simulated mobility model, a dual-objective balanced simulated mobility model is obtained.

[0070] Step S3, establishing a distributed mobility strategy candidate set, calculating penalty item accumulation for the distributed mobility strategy candidate set, constructing a composite evaluation network based on the penalty accumulation, calculating an expected value for the composite evaluation network, maximizing the expected value, and obtaining an optimal distributed mobility strategy;

[0071] In the actual evaluation, there are 20 kinds of materials that need to be dispatched in the port area. The Monte Carlo method is used for 50 iterations to generate a candidate set of distributed mobile strategies. A simulation model is built on the Simulink simulation platform based on the Windows system. Based on the dual-objective balance simulation mobile model, the corresponding mobile paths of the 20 kinds of materials are obtained. Simscape modules are added to the Simulink simulation platform to simulate transportation equipment. The Data Store Memory module is used to record the location of materials, detect conflict risks, and set conflict logic that makes low-priority materials wait for high-priority materials to pass. The To Workspace module is used to collect data on successful arrival at the destination, conflicts, and other situations during the simulation process. At the same time, penalty rules are constructed to record the accumulation of penalty items and waiting time.

[0072] In the actual evaluation, a composite evaluation network is constructed based on the accumulation of penalty items, and the expected value is further calculated based on the score of the composite evaluation network. According to the convex optimization theory, the expected value is maximized using the gradient ascent method to minimize the negative consequences of conflicts and maximize the positive consequences of successfully reaching the end point, thus obtaining the optimal distributed mobility strategy.

[0073] Step S4, obtaining a material movement path based on the dual-objective balance simulation movement model, and combining the material movement path and the optimal distributed movement strategy as a material movement method.

[0074] In the actual evaluation, 20 movement paths for 20 types of materials in the port area were obtained based on the dual-objective balance simulation mobility model, which were combined with the optimal distributed mobility strategy and used as the multi-material movement method.

[0075] In this embodiment, the method for constructing a simulated mobility model in step S1 includes:

[0076] Based on the material's moving start and target nodes, use A * The algorithm performs global path planning, decomposes the global path into several local path segments based on the scheduling equipment resources, and smoothes the local path segments to reduce sharp turns and incoherent movements in the local path segments;

[0077] Obtain the obstacle location node and build an obstacle avoidance strategy in the local path segment to optimize the path. The path expression of the material after obstacle avoidance in the local path segment is:

[0078]

[0079] Where k is the obstacle avoidance strategy based on the Dijkstra algorithm, γ = 1 means obtaining the obstacle position node parameters starting from the first obstacle, and f γ is the physical distance between the material and the obstacle location node, d is the material movement parameter, a is the material movement planning coefficient, is the obstacle location node layout feature, and A is the obstacle avoidance behavior planning vector.

[0080] In this embodiment, the method for finding a path through the simulated mobility model based on the shortest path priority and the best cost priority includes:

[0081] Get the nodes that the path passes through, and integrate the lengths of adjacent nodes as the shortest path evaluation function;

[0082] Obtain material parameters and material movement time, and construct the optimal cost evaluation function. The expression of the optimal cost evaluation function is:

[0083]

[0084] Among them, H is the material set, p h is the unit price of material h, is the demand frequency of material h, is the risk rate of material h during movement, D h is the demand change of material h, c is the number of dispatching equipment required for movement, f1 and f2 are the unit distance fuel consumption of the equipment when it is empty and fully loaded, respectively, S h is the time efficiency level of the path for the movement of material h, including the material departure, unloading and transportation time, The average cycle time for moving material along the path;

[0085] A path search tree is constructed to traverse all paths based on the shortest path evaluation function and the optimal cost evaluation function. After the traversal is completed, the paths with the smallest shortest path evaluation function value and the smallest optimal cost evaluation function value are selected as the first simulation path and the second simulation path.

[0086] In this embodiment, the method for calculating the node probability distribution for the first simulation path and the second simulation path includes:

[0087] A probability distribution function is constructed to calculate the distribution probability of the nodes experienced in the first simulation path and the second simulation path. The expression of the probability distribution function is:

[0088]

[0089] in, is the ratio of the grid where the path passes through the node to all grids, x is the total number of nodes passed through the path, and p k and p i are the partition phases of two adjacent nodes k and i in the grid, D[u k -u i ] represents the Euclidean distance between two adjacent nodes k and i.

[0090] In this embodiment, the method of obtaining an explorable space according to the node probability distribution and performing spatial optimization on the simulated mobility model based on the explorable space includes:

[0091] The confidence threshold is set to 0.62, and the confidence space analysis is performed on the nodes experienced in the first simulation path and the second simulation path. When the distribution probability of a node is less than the confidence threshold, it is considered that the confidence space of the node is small and the exploration value is high. The node is taken as an explorable node, and all explorable nodes are integrated to form a continuous explorable space.

[0092] The first simulation path and the second simulation path are taken as the parent generation, the reorganization of the paths is taken as the crossover operation, the adjustment of the nodes on the paths is taken as the mutation operation, and the crossover mutation operation is performed on the parent generation in the explorable space. The specific method of the crossover mutation operation is as follows:

[0093] The simulated binary crossover operator is used for crossover operation, and the calculation formula for the k+1th generation individuals is:

[0094]

[0095] Among them, δ 1,k+1 and δ 2,k+1 is the k+1th generation individual generated after crossover, β qi is the uniform distribution factor, δ 1,k and δ 2,k is the selected k-th generation individual, where the calculation formula of the uniform distribution factor is:

[0096]

[0097] Among them, u i is a random number in [0,1), η is the crossover distribution index;

[0098] The polynomial mutation factor is used as the standard mutation operator to perform mutation operations to generate new individuals. The calculation formula for the k+1 generation of individuals is:

[0099]

[0100] Among them, δ k+1 For the k The k+1th generation individuals obtained by mutation operation, δ k is the selected k-th generation individual, and is the maximum and minimum mutation factors allowed for the kth generation, ξ k is the variation balance factor, where ξ k The calculation formula is:

[0101]

[0102] Among them, r k is a random number uniformly distributed in [0,1], η is the variation distribution index;

[0103] After the crossover and mutation operation, several new paths are obtained. The fitness of the new paths is calculated using the fitness function, and the path with the largest fitness is selected as the optimal solution path. The expression of the fitness function is:

[0104]

[0105] Among them, θ1 and θ2 are the weight coefficients focusing on the shortest path and the optimal cost, respectively, L is the path length, x is the total number of nodes experienced by the path, P i is the total number of grids experienced in the path, d iis the sum of the Manhattan distances between adjacent nodes that have turns in the path, e i is the path smoothing factor. When the steering angle is less than or equal to 30°, e i Set to 100, when the steering angle is greater than 30°, e i Set to 1, It is the cost of moving materials within 1 hour.

[0106] In this embodiment, the method of establishing a distributed mobility strategy candidate set and calculating the penalty item accumulation based on the distributed mobility strategy candidate set includes:

[0107] Based on the problem of multi-material movement, the Monte Carlo method is used to generate a candidate set of distributed movement strategies, and the dual-objective balance simulation movement model is combined to generate a path. The simulation platform is used to perform simulation operations based on the multi-material movement strategies and corresponding paths in the candidate set;

[0108] During the simulation, when a material movement conflict occurs, set a material waiting strategy to make low-priority materials wait for high-priority materials to pass through and obtain the conflict waiting time;

[0109] Define penalty rules and calculate the cumulative penalty items for the simulation operation. When the material successfully reaches the end point during the movement, a penalty item with a corresponding movement strategy value of 1 is given. When the material conflicts with other materials during the movement, a penalty item with a corresponding movement strategy value of -1 is given. For other situations, a penalty item with a corresponding movement strategy value of 0 is given.

[0110] In this embodiment, the method for constructing a composite evaluation network based on the penalty term accumulation includes:

[0111]

[0112] Where γ is the discount factor, m r 、n r ,q r are the number of times the mobile strategy successfully reaches the end point, conflicts occur, and other situations occur, respectively, r is the global priority evaluation coefficient in the mobile strategy, Cumulative time waiting for conflicts.

[0113] In this embodiment, the method of maximizing the expected value of the advantage function in the composite evaluation network to obtain the optimal distributed mobility strategy includes:

[0114] Calculate the softmax distribution and KL divergence of the composite evaluation network, and calculate the expected value based on the score of the composite evaluation network. The calculation formula is:

[0115]

[0116] Among them, φ is the expected value, ω(S) is the score of the composite evaluation network, and D KL is the KL divergence, It is represented as the softmax distribution of the composite evaluation network, Z(s t ) is the normalization factor, KL S is the KL divergence of the composite evaluation network;

[0117] According to the convex optimization theory, the gradient ascent method is used to maximize the expected value, minimize the negative consequences of conflicts, and maximize the positive consequences of successfully reaching the end point, thus obtaining the optimal distributed mobile strategy.

[0118] In this embodiment, the method of combining the material movement path and the optimal distributed movement strategy as a material movement method includes: obtaining the material movement path of each material through a dual-objective balance simulation movement model, obtaining the handling order and conflict waiting time of each material from the optimal distributed movement strategy, and combining the movement path of each material with the handling order and conflict waiting time of each material to obtain a comprehensive material movement plan as a material movement method.

[0119] Figure 2 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. Figure 2 At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. The memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage. Of course, the electronic device may also include hardware required for other services.

[0120] The processor, network interface and memory can be interconnected through an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 2 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0121] The memory is used to store the program. Specifically, the program may include a program code, and the program code includes a computer operation instruction. The memory may include a memory and a non-volatile memory, and provides instructions and data to the processor.

[0122] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming an automatic constant temperature device based on the Internet of Things and fuzzy judgment at the logical level. The processor executes the program stored in the memory and is specifically used to execute any of the above-mentioned port terminal material movement simulation control methods.

[0123] The above application Figure 1 The embodiment shown discloses a method for simulating the movement of materials at a port terminal, which can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or an instruction in the form of software. The above processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in the embodiment of the present application can be directly embodied as being executed by a hardware decoding processor, or executed by a combination of hardware and software modules in a decoding processor. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0124] The electronic device may also perform Figure 1 A simulation control method for material movement in a port terminal is implemented Figure 1 The functions of the illustrated embodiment will not be described in detail in the embodiments of the present application.

[0125] An embodiment of the present application also proposes a computer-readable storage medium, which stores one or more programs, and the one or more programs include instructions. When the instructions are executed by an electronic device including multiple application programs, any one of the aforementioned port terminal material movement simulation control methods is executed.

[0126] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0127] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A system that specifies the functions of a box or multiple boxes.

[0128] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction system, which is implemented in the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0129] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0130] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0131] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0132] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0133] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity 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, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0134] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0135] The above contents are merely examples and explanations of the structure of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the claims, they should all fall within the protection scope of the present invention.

Claims

1. A port terminal material movement simulation control method, characterized in that: The following steps are involved: Step S1, gridding the port terminal area, obtaining the starting position and target position nodes of material movement, constructing a simulated movement model, and performing path finding through the simulated movement model based on the shortest path priority and the best cost priority to obtain a first simulated path and a second simulated path; Step S2, calculating the node probability distribution for the first simulation path and the second simulation path, obtaining an explorable space according to the node probability distribution, and performing spatial optimization on the simulated mobility model based on the explorable space to obtain a dual-objective balanced simulated mobility model; Step S3, establishing a distributed mobility strategy candidate set, calculating penalty item accumulation for the distributed mobility strategy candidate set, constructing a composite evaluation network based on the penalty accumulation, calculating an expected value for the composite evaluation network, maximizing the expected value, and obtaining an optimal distributed mobility strategy; Step S4, obtaining a material movement path based on the dual-objective balance simulation movement model, and combining the material movement path and the optimal distributed movement strategy as a material movement method.

2. A port terminal material movement simulation control method according to claim 1, characterized in that: The method for constructing the simulated mobility model in step S1 includes: Based on the material's moving start and target nodes, use A * The algorithm performs global path planning, decomposes the global path into several local path segments based on the scheduling equipment resources, and smoothes the local path segments to reduce sharp turns and incoherent movements in the local path segments; Obtain the obstacle location node and build an obstacle avoidance strategy in the local path segment to optimize the path. The path expression of the material after obstacle avoidance in the local path segment is: Where k is the obstacle avoidance strategy based on the Dijkstra algorithm, γ = 1 means obtaining the obstacle position node parameters starting from the first obstacle, and f γ is the physical distance between the material and the obstacle location node, d is the material movement parameter, a is the material movement planning coefficient, is the obstacle location node layout feature, and A is the obstacle avoidance behavior planning vector.

3. A port terminal material movement simulation control method according to claim 1, characterized in that: The method for finding a path through the simulated mobility model based on the shortest path priority and the optimal cost priority includes: Get the nodes that the path passes through, and integrate the lengths of adjacent nodes as the shortest path evaluation function; Obtain material parameters and material movement time, and construct the optimal cost evaluation function. The expression of the optimal cost evaluation function is: Among them, H is the material set, p h is the unit price of material h, is the demand frequency of material h, is the risk rate of material h during movement, D h is the demand change of material h, c is the number of dispatching equipment required for movement, f1 and f2 are the unit distance fuel consumption of the equipment when it is empty and fully loaded, respectively, S h is the time efficiency level of the path for the movement of material h, including the material departure, unloading and transportation time, The average cycle time for moving material along the path; A path search tree is constructed to traverse all paths based on the shortest path evaluation function and the optimal cost evaluation function. After the traversal is completed, the paths with the smallest shortest path evaluation function value and the smallest optimal cost evaluation function value are selected as the first simulation path and the second simulation path.

4. A port terminal material movement simulation control method according to claim 1, characterized in that: The method for calculating the node probability distribution of the first simulation path and the second simulation path includes: A probability distribution function is constructed to calculate the distribution probability of the nodes experienced in the first simulation path and the second simulation path. The expression of the probability distribution function is: in, is the ratio of the grid where the path passes through the node to all grids, x is the total number of nodes passed through the path, and p k and p i are the partition phases of two adjacent nodes k and i in the grid, D[u k -u i ] represents the Euclidean distance between two adjacent nodes k and i.

5. A port terminal material movement simulation control method according to claim 1, characterized in that: The method of obtaining an explorable space according to the node probability distribution and performing spatial optimization on the simulated mobility model based on the explorable space includes: The confidence threshold is set to 0.62, and the confidence space analysis is performed on the nodes experienced in the first simulation path and the second simulation path. When the distribution probability of a node is less than the confidence threshold, it is considered that the confidence space of the node is small and the exploration value is high. The node is taken as an explorable node, and all explorable nodes are integrated to form a continuous explorable space. The first simulation path and the second simulation path are taken as the parent generation, the reorganization of the paths is taken as the crossover operation, the adjustment of the nodes on the paths is taken as the mutation operation, and the crossover mutation operation is performed on the parent generation in the explorable space. The specific method of the crossover mutation operation is as follows: The simulated binary crossover operator is used for crossover operation, and the calculation formula for the k+1th generation individuals is: Among them, δ 1,k+1 and δ 2,k+1 is the k+1th generation individual generated after crossover, β qi is the uniform distribution factor, δ 1,k and δ 2,k is the selected k-th generation individual, where the calculation formula of the uniform distribution factor is: Among them, u i is a random number in [0,1), η is the crossover distribution index; The polynomial mutation factor is used as the standard mutation operator to perform mutation operations to generate new individuals. The calculation formula for the k+1 generation of individuals is: Among them, δ k+1 For the k The k+1th generation individuals obtained by mutation operation, δ k is the selected k-th generation individual, and is the maximum and minimum mutation factors allowed for the kth generation, ξ k is the variation balance factor, where ξ k The calculation formula is: Among them, r k is a random number uniformly distributed in [0,1], η is the variation distribution index; After the crossover and mutation operation, several new paths are obtained. The fitness of the new paths is calculated using the fitness function, and the path with the largest fitness is selected as the optimal solution path. The expression of the fitness function is: Among them, θ1 and θ2 are the weight coefficients focusing on the shortest path and the optimal cost, respectively, L is the path length, x is the total number of nodes experienced by the path, P i is the total number of grids experienced in the path, d i is the sum of the Manhattan distances between adjacent nodes that have turns in the path, e i is the path smoothing factor. When the steering angle is less than or equal to 30°, e i Set to 100, when the steering angle is greater than 30°, e i Set to 1, It is the cost of moving materials within 1 hour.

6. A port terminal material movement simulation control method according to claim 1, characterized in that: The method of establishing a distributed mobility strategy candidate set and calculating the penalty item accumulation based on the distributed mobility strategy candidate set includes: Based on the problem of multi-material movement, the Monte Carlo method is used to generate a candidate set of distributed movement strategies, and the dual-objective balance simulation movement model is combined to generate a path. The simulation platform is used to perform simulation operations based on the multi-material movement strategies and corresponding paths in the candidate set; During the simulation, when a material movement conflict occurs, set a material waiting strategy to make low-priority materials wait for high-priority materials to pass through and obtain the conflict waiting time; Define penalty rules and calculate the cumulative penalty items for the simulation operation. When the material successfully reaches the end point during the movement, a penalty item with a corresponding movement strategy value of 1 is given. When the material conflicts with other materials during the movement, a penalty item with a corresponding movement strategy value of -1 is given. For other situations, a penalty item with a corresponding movement strategy value of 0 is given.

7. A port terminal material movement simulation control method according to claim 1, characterized in that: The method for constructing a composite evaluation network based on the penalty term accumulation includes: Where γ is the discount factor, m r 、n r ,q r are the number of times the mobile strategy successfully reaches the end point, conflicts occur, and other situations occur, respectively, r is the global priority evaluation coefficient in the mobile strategy, Cumulative time waiting for conflicts.

8. A port terminal material movement simulation control method according to claim 1, characterized in that: The method of maximizing the expected value of the advantage function in the composite evaluation network to obtain the optimal distributed mobility strategy includes: Calculate the softmax distribution and KL divergence of the composite evaluation network, and calculate the expected value based on the score of the composite evaluation network. The calculation formula is: Among them, φ is the expected value, ω(S) is the score of the composite evaluation network, and D KL is the KL divergence, It is represented as the softmax distribution of the composite evaluation network, Z(s t ) is the normalization factor, KL S is the KL divergence of the composite evaluation network; According to the convex optimization theory, the gradient ascent method is used to maximize the expected value, minimize the negative consequences of conflicts, and maximize the positive consequences of successfully reaching the end point, thus obtaining the optimal distributed mobile strategy.

9. A port terminal material movement simulation control method according to claim 1, characterized in that: The method of combining the material movement path and the optimal distributed movement strategy as a material movement method includes: obtaining the material movement path of each material through a dual-objective balance simulation movement model, obtaining the handling sequence and conflict waiting time of each material from the optimal distributed movement strategy, and combining the movement path of each material with the handling sequence and conflict waiting time of each material to obtain a comprehensive material movement plan as a material movement method.

10. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of application programs, enables the electronic device to execute the method according to any one of claims 1 to 8.

Images