A method for simulating and controlling the movement of materials at a port terminal

Abstract

The present invention discloses a method for simulating and controlling the movement of materials at a port terminal, which includes constructing a simulation movement model, obtaining a first simulation path and a second simulation path, obtaining an exploitable space based on the first simulation path and the second simulation path, optimizing the space of the simulation movement model based on the exploitable space to obtain a double-objective balanced simulation movement model, establishing a distributed movement strategy candidate set, accumulating penalty terms for the distributed movement strategy candidate set to obtain a penalty accumulation value, constructing a composite evaluation network based on the penalty accumulation value, obtaining an expected value based on the composite evaluation network, performing a maximization operation on the expected value to obtain an optimal distributed movement strategy, and taking the combination of the movement path and the optimal distributed movement strategy as the method for simulating and controlling the movement of materials. This method not only improves the efficiency and comprehensiveness of material movement simulation, but also has good interpretability and can be directly applied to the material movement simulation control system at the port terminal.

Description

Technical Field

[0001] The present invention relates to the field of mobile scheduling, and particularly to a method for simulating and controlling the movement of materials in a port terminal. Background Art

[0002] With the rapid development of domestic and international trade exchanges, as a key area of the logistics chain, the efficiency of material movement in port terminals directly affects the operation efficiency and cost of the entire logistics chain. Therefore, optimizing the method for simulating and controlling the movement of materials in port terminals plays a crucial role in ensuring the rapid, safe, and efficient loading, unloading, and transfer of goods.

[0003] Traditional methods for controlling the movement of materials in port terminals mainly rely on manual scheduling and empirical judgment, and have many limitations. For example, the scheduling efficiency is low, the response speed is slow, the cost control is inaccurate, and the adaptability to emergencies is poor. With the rapid development of Internet of Things technology, big data analysis, and intelligent algorithms, the control of material movement in port terminals is gradually developing towards automation and intelligence.

[0004] Currently, some methods for scheduling the movement of port materials have adopted intelligent algorithms to improve the efficiency of material movement, but these methods still have some limitations. For example, existing methods for scheduling the movement of port materials usually perform path planning based on a single algorithm and 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 the movement simulation process focuses on the ideal state, lacking consideration of complex environments. Summary of the Invention

[0005] The object of the present invention is to provide a method for simulating and controlling the movement of materials in a port terminal.

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

[0007] The first aspect of the present invention provides a method for simulating and controlling the movement of materials in a port terminal, including the following steps:

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

[0009] Step S2, calculating the node probability distribution for the first simulated path and the second simulated path, obtaining the explorability space according to the node probability distribution, and optimizing the space of the simulated movement model based on the explorability space to obtain a dual-objective balanced simulated movement model;

[0010] Step S3, establish a candidate set of distributed movement strategies, calculate the cumulative penalty term for the candidate set of distributed movement strategies, construct a composite evaluation network based on the penalty accumulation, calculate the expected value for the composite evaluation network, perform a maximization operation on the expected value, and obtain the optimal distributed movement strategy;

[0011] Step S4, obtain the material movement path based on the dual-objective balanced simulated movement model, and combine the material movement path and the optimal distributed movement strategy as the material movement method.

[0012] Further, the method for constructing the simulated movement model in step S1 includes:

[0013] Based on the starting position and target position nodes of the material movement, use the A * algorithm for global path planning, decompose the global path into several local path segments based on the scheduling device resources, and perform smoothing processing on the local path segments to reduce sharp turns and incoherent movements in the local path segments;

[0014] Obtain the obstacle position nodes, construct an obstacle avoidance strategy in the local path segments for path optimization, where the path expression of the material after obstacle avoidance processing in the local path segment is:

[0015]

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

[0017] Further, the method for finding a path through the simulated movement model based on the shortest path first and the optimal cost first includes:

[0018] Obtain the nodes passed by the path, and integrate the length between adjacent nodes as the shortest path evaluation function;

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

[0020]

[0021] where 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 during the movement of material h, D h is the change in demand for material h, c is the number of scheduling devices required for movement, f1 and f2 are the fuel consumption per unit distance under no-load and full-load conditions of the device, S h is the timeliness level of the path for the movement of material h, including the starting, unloading, and carrying times of the material, is the average cycle time for moving the material along the path;

[0022] Construct a path search tree to traverse all paths based on the shortest path evaluation function and the optimal cost evaluation function. After the traversal is completed, select the paths with the minimum shortest path evaluation function value and the minimum optimal cost evaluation function value as the first simulation path and the second simulation path respectively.

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

[0024] Construct a probability distribution function 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] Where, is the proportion of the grid where the path-experienced node is located in all grids, x is the total number of nodes experienced by the path, p k and p i are the division phases of two adjacent nodes k and i in the grid respectively, D[u k -u i represents the Euclidean distance value between two adjacent nodes k and i.

[0027] Further, the method for obtaining the exploitable space according to the node probability distribution and optimizing the space of the simulation movement model based on the exploitable space includes:

[0028] Set the confidence threshold to 0.62, perform confidence space analysis 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 this node is small and the exploitable value is high. Take this node as an exploitable node, and integrate all exploitable nodes to form a continuous exploitable space;

[0029] Take the first simulation path and the second simulation path as parents, take the recombination of the paths as the crossover operation, take the adjustment of the nodes on the path as the mutation operation, and perform crossover and mutation operations on the parents in the exploitable space. The specific method of the crossover and mutation operations is:

[0030] The crossover operation is carried out using the simulated binary crossover operator, and the calculation formula for the individuals in the (k + 1)-th generation is as follows:

[0031]

[0032] where δ 1,k+1 and δ 2,k+1 are the individuals in the (k + 1)-th generation generated after crossover, β qi is the uniform distribution factor, δ 1,k and δ 2,k are the selected individuals in the k-th generation. The calculation formula for the uniform distribution factor is as follows:

[0033]

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

[0035] The mutation operation is carried out using the polynomial mutation factor as the standard mutation operator to generate new individuals. The calculation formula for the individuals in the (k + 1)-th generation is as follows:

[0036]

[0037] where δ k+1 is the individual in the (k + 1)-th generation obtained after the mutation operation of δ k , δ k is the selected individual in the k-th generation, and are the maximum and minimum mutation factors allowed for mutation in the k-th generation, ξ k is the mutation balance factor. The calculation formula for ξ k is as follows:

[0038]

[0039] where r k is a random number uniformly distributed in [0, 1], and η is the mutation distribution index;

[0040] After the crossover and mutation operations, several new paths are obtained. The fitness function is used to calculate the fitness of the several new paths, and the path with the maximum fitness is selected as the optimal solution path. The expression of the fitness function is as follows:

[0041]

[0042] where θ1 and θ2 are the weight coefficients emphasizing the shortest path and the optimal cost respectively, L is the path length, x is the total number of nodes passed by the path, P i is the total number of grids passed by the path, and d iis the sum of Manhattan distances between adjacent nodes with turns in the path, e i is the path smoothing factor. When the turning angle is less than or equal to 30 °C, set e i to 100. When the turning angle is greater than 30 °C, set e i to 1. is the cost of material movement within 1 h.

[0043] Furthermore, the method for establishing a distributed movement strategy candidate set and calculating the cumulative penalty term based on the distributed movement strategy candidate set includes:

[0044] Based on the problem of multi-material movement, use the Monte Carlo method to generate a distributed movement strategy candidate set, generate a path by combining a two-objective balanced simulated movement model, and perform simulation runs on the simulation platform 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 the low-priority material wait for the high-priority material to pass, and obtain the conflict waiting time;

[0046] Define a penalty rule to calculate the cumulative penalty term for the simulation running situation. When the material successfully reaches the end point during movement, give a penalty term with a value of 1 to the corresponding movement strategy. When the material conflicts with other materials during movement, give a penalty term with a value of -1 to the corresponding movement strategy. For other situations, give a penalty term with a value of 0 to the corresponding movement strategy.

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

[0048]

[0049] where γ is the discount factor, m r 、n r 、q r are the number of times of successfully reaching the end point, having conflicts, and having other situations in the movement strategy respectively, P r is the global priority evaluation coefficient in the movement strategy, is the cumulative time of conflict waiting.

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

[0051] Calculate the softmax distribution and KL divergence of the composite evaluation network, and calculate the expected value based on the scores 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, is represented as the softmax distribution of the composite evaluation network, and Z(s t ) is the normalization factor, and 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 results of conflicts, and maximize the positive results of successfully reaching the end point, so as to obtain the optimal distributed movement strategy.

[0055] Further, the method of combining the material movement path and the optimal distributed movement strategy as the material movement method includes: obtaining the material movement path of each material through the dual-objective balanced 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 the material movement method.

[0056] In a second aspect, an embodiment of the present application further provides a computer-readable storage medium, and the computer-readable storage medium stores one or more programs. When the one or more programs are executed by an electronic device including a plurality of application programs, the electronic device is caused to execute 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 method for simulating and controlling the movement of materials in a port terminal. By combining the A * algorithm and the smoothing processing algorithm for path optimization, using the Dijkstra algorithm to construct an obstacle avoidance strategy, and combining multiple algorithms for path finding, the adaptability and stability in the face of different environments and conditions can be improved, the robustness of the path finding algorithm can be enhanced, and the dynamic obstacle avoidance and path optimization requirements in a complex environment can be effectively met.

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

[0060] (3) By accumulating penalty terms for the candidate set of distributed movement strategies, the present invention obtains a penalty accumulation value, and further constructs a composite evaluation network based on the penalty accumulation value. It considers various situations that occur during the movement of multiple materials, and constructs a composite evaluation network based on penalty terms, enabling the evaluation network to consider factors such as cost, time, and resources, and obtaining a more comprehensive strategy evaluation network. This method helps to select a more comprehensive movement strategy for the movement of multiple materials, improving the comprehensiveness of material movement. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 It is a flowchart of the steps of a method for simulating and controlling the movement of materials in a port terminal according to the present invention.

[0062] Figure 2 It is a schematic structural diagram of an electronic device in an embodiment of this specification. DETAILED DESCRIPTION OF THE INVENTION

[0063] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0064] Referring to Figure 1 as shown, the present invention provides a method for simulating and controlling the movement of materials in a port terminal, including:

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

[0066] In actual evaluation, the MATLAB Function tool is used to divide the port area into grids, obtain the starting position node A and the target position node B of the material movement. Based on node A and node B, the improved A * algorithm is used for global path planning, the global path is decomposed into several local path segments, the DWA algorithm is used to optimize the local path segments, and an obstacle avoidance strategy is constructed based on the Dijkstra algorithm in the local path segments for path optimization to obtain a simulation movement model. An evaluation function of the shortest path first and the optimal cost first is constructed, and path finding operations are performed through the simulation movement model to obtain a first simulation path and a second simulation path.

[0067] Step S2: Calculate the node probability distribution for the first simulation path and the second simulation path, obtain the exploration space based on the node probability distribution, and perform spatial optimization on the simulation movement model based on the exploration space to obtain a two-objective balanced simulation movement model;

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

[0069] In actual evaluation, take the first simulation path and the second simulation path as parents, the recombination of the paths as the crossover operation, and the adjustment of the nodes on the path as the mutation operation. Perform crossover and mutation operations on the parents in the exploration space, select the path with the maximum fitness as the optimal solution path, balance the shortest path first and the optimal cost first for the optimal solution path, and perform spatial optimization on the simulation movement model to obtain a two-objective balanced simulation movement model.

[0070] Step S3: Establish a distributed movement strategy candidate set, calculate the cumulative penalty term for the distributed movement strategy candidate set, construct a composite evaluation network based on the penalty accumulation, calculate the expected value for the composite evaluation network, and perform a maximization operation on the expected value to obtain the optimal distributed movement strategy;

[0071] In actual evaluation, there are 20 types of materials to be scheduled in the port area. Use the Monte Carlo method for 50 iterations to generate a distributed movement strategy candidate set. Build a simulation model on the Simulink simulation platform based on the Windows system. Based on the two-objective balanced simulation movement model, obtain the movement paths corresponding to 20 types of materials. Add the Simscape module on the Simulink simulation platform to simulate the transportation equipment, record the material positions through the Data Store Memory module, detect conflict risks, set the conflict logic that allows low-priority materials to wait for high-priority materials to pass, use the To Workspace module to collect data on successful arrival at the end point, occurrence of conflicts, and other situations during the simulation process. At the same time, construct a penalty rule to record the cumulative penalty term and waiting time;

[0072] In actual evaluation, construct a composite evaluation network based on the cumulative penalty term, further calculate the expected value based on the score of the composite evaluation network. According to the convex optimization theory, use the gradient ascent method to perform a maximization operation on the expected value, minimize the negative result of conflicts, and maximize the positive result of successful arrival at the end point to obtain the optimal distributed movement strategy.

[0073] Step S4: Obtain the material movement path based on the dual-objective balanced simulated moving model, and combine the material movement path and the optimal distributed movement strategy as the material movement method.

[0074] In the actual evaluation, 20 movement paths of 20 types of materials in the port area are obtained based on the dual-objective balanced simulated moving model, combined with the optimal distributed movement strategy, and the combined movement method is used as the movement method for multiple materials.

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

[0076] Based on the starting position and target position nodes of the material movement, use the A * algorithm for global path planning, decompose the global path into several local path segments based on the scheduling device resources, and smooth the local path segments to reduce sharp turns and discontinuous movements in the local path segments;

[0077] Obtain the obstacle position nodes, and construct an obstacle avoidance strategy in the local path segments for path optimization. The path expression of the material after obstacle avoidance processing in the local path segment is:

[0078]

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

[0080] In this embodiment, the method for finding a path through the simulated moving model based on the shortest path first and the optimal cost first includes:

[0081] Obtain the nodes passed by the path, and integrate the lengths between adjacent nodes as the shortest path evaluation function;

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

[0083]

[0084] where 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 during the movement of material h, D h is the change in demand for material h, c is the number of scheduling devices required for movement, f1 and f2 are the fuel consumption per unit distance under no-load and full-load conditions of the device, S h is the timeliness level of the path for the movement of material h, including the material departure, unloading, and carrying time, is the average cycle time for moving materials on the path;

[0085] Construct a path search tree to traverse all paths based on the shortest path evaluation function and the optimal cost evaluation function. After the traversal, select the paths with the minimum shortest path evaluation function value and the minimum optimal cost evaluation function value as the first simulation path and the second simulation path respectively.

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

[0087] Construct a probability distribution function 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] Among them, is the ratio of the grid where the path-experienced node is located to all grids, x is the total number of path-experienced nodes, p k and p i are the division phases of two adjacent nodes k and i in the grid respectively, D[u k -u i represents the Euclidean distance value between two adjacent nodes k and i.

[0090] In this embodiment, the method for obtaining the exploitable space according to the node probability distribution and optimizing the space of the simulation movement model based on the exploitable space includes:

[0091] Set the confidence threshold to 0.62, perform confidence space analysis 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 this node is small and the exploitable value is high. Take this node as an exploitable node, and integrate all exploitable nodes to form a continuous exploitable space;

[0092] Take the first simulation path and the second simulation path as parents, take the recombination of the paths as the crossover operation, and take the adjustment of the nodes on the path as the mutation operation. Perform crossover and mutation operations on the parents in the exploitable space. The specific method of the crossover and mutation operations is:

[0093] The crossover operation is performed using the simulated binary crossover operator. The calculation formula for the individuals in the (k + 1)-th generation is as follows:

[0094]

[0095] Among them, δ 1,k+1 and δ 2,k+1 are the individuals in the (k + 1)-th generation generated after crossover. β qi is the uniform distribution factor. δ 1,k and δ 2,k are the selected individuals in the k-th generation. The calculation formula for the uniform distribution factor is as follows:

[0096]

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

[0098] The mutation operation is performed using the polynomial mutation factor as the standard mutation operator to generate new individuals. The calculation formula for the individuals in the (k + 1)-th generation is as follows:

[0099]

[0100] Among them, δ k+1 is the individual in the (k + 1)-th generation obtained after the mutation operation of δ k . δ k is the selected individual in the k-th generation, and are the maximum and minimum mutation factors allowed for mutation in the k-th generation. ξ k is the mutation balance factor. The calculation formula for ξ k is as follows:

[0101]

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

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

[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 passed by the path, P i is the total number of grids passed by the path, and d iis the sum of the Manhattan distances between adjacent nodes where the path turns, e i is the path smoothing factor. When the turning angle is less than or equal to 30 °C, set e i to 100. When the turning angle is greater than 30 °C, set e i to 1. is the cost of material movement within 1 h.

[0106] In this embodiment, the method for establishing a distributed movement strategy candidate set and calculating the cumulative penalty term based on the distributed movement strategy candidate set includes:

[0107] Based on the problem of multi-material movement, use the Monte Carlo method to generate a distributed movement strategy candidate set, generate a path by combining a two-objective balanced simulated movement model, and perform simulation runs on the simulation platform based on the multi-material movement strategies and corresponding paths in the candidate set;

[0108] During the simulation process, when a material movement conflict occurs for the material, set a material waiting strategy to make the material with a lower priority wait for the material with a higher priority to pass, and obtain the conflict waiting time;

[0109] Define a penalty rule to calculate the cumulative penalty term for the simulation running situation. When the material successfully reaches the end point during movement, give a penalty term with a value of 1 to the corresponding movement strategy. When the material conflicts with other materials during movement, give a penalty term with a value of -1 to the corresponding movement strategy. For other situations, give a penalty term with a value of 0 to the corresponding movement strategy.

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

[0111]

[0112] where γ is the discount factor, m r 、n r 、q r are the number of times of successfully reaching the end point, having conflicts, and having other situations in the movement strategy respectively, P r is the global priority evaluation coefficient in the movement strategy, is the cumulative time of conflict waiting.

[0113] In this embodiment, the method for maximizing the expected value of the advantage function in the composite evaluation network to obtain the optimal distributed movement 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, is expressed as the softmax distribution of the composite evaluation network, and Z(s t ) is the normalization factor, and KL S is the KL divergence of the composite evaluation network;

[0117] According to the convex optimization theory, the expected value is maximized by the gradient ascent method, the negative results of conflicts are minimized, and the positive results of successfully reaching the end point are maximized to obtain the optimal distributed movement strategy.

[0118] In this embodiment, the method of combining the material movement path and the optimal distributed movement strategy as the material movement method includes: obtaining the material movement path of each material through the dual-objective balanced 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 the material movement method.

[0119] Figure 2 is a schematic structural diagram of an electronic device according to an embodiment of the present application. Please refer to 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. Among them, the memory may include a memory, such as a high-speed random access memory (Random-Access Memory, RAM), and may also include a non-volatile memory, such as at least one disk memory, etc. Of course, the electronic device may also include other hardware required for other services.

[0120] The processor, network interface, and memory can be interconnected through the internal bus, and the internal bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of representation, Figure 2 only a bidirectional arrow is used in

[0121] A memory for storing programs. Specifically, the program may include program code, and the program code includes computer operation instructions. The memory may include a memory and a non-volatile memory, and provide 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 determination at the logical level. The processor executes the program stored in the memory and is specifically used to execute any one of the foregoing port terminal material movement simulation control methods.

[0123] The above as in this application Figure 1 A port terminal material movement simulation control method disclosed in the embodiments shown in this application can be applied to 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 the integrated logic circuit in the hardware of the processor or the instructions 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 gate or transistor logic devices, discrete hardware components. It can implement or execute each method, step and logic block diagram disclosed in the embodiments of this application. 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 combination with the embodiments of this application can be directly embodied as being executed and completed by the hardware decoding processor, or executed and completed by the combination of the hardware and software modules in the decoding processor. The software module may be located in a mature storage medium 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. This storage medium is located in the memory, and the processor reads the information in the memory and combines its hardware to complete the steps of the above method.

[0124] The electronic device can also execute Figure 1 a port terminal material movement simulation control method in Figure 1 and implement the functions of the embodiments shown in this application. The embodiments of this application will not be described in detail here.

[0125] The embodiments of the present application also propose a computer-readable storage medium, which stores one or more programs. The one or more programs include instructions that, when executed by an electronic device including multiple application programs, perform any of the foregoing port terminal material movement simulation control methods.

[0126] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take 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.) containing computer-usable program code.

[0127] The present application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be realized by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a system for realizing the functions specified in Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0128] These computer program instructions can 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 generate a manufactured product including an instruction system that realizes the functions specified in Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0129] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide steps for realizing the functions specified in Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0130] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and a 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 content is only an example and illustration of the structure of the present invention. Those skilled in the art to which the present technology pertains can make various modifications, supplements, or use similar methods for substitution to the specific embodiments described, as long as they do not deviate from the structure of the invention or exceed the scope defined by this claims, it shall 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; The method of obtaining the material movement starting position and target position nodes to construct a simulated movement model specifically includes: based on the material movement starting position and target position nodes, using The algorithm performs global path planning, decomposes the global path into several local path segments based on the scheduling equipment resources, uses the DWA algorithm to optimize the local path segments, and builds an obstacle avoidance strategy based on the Dijkstra algorithm in the local path segments to optimize the path and obtain a simulated mobility model; Obstacle position nodes are obtained, and obstacle avoidance strategies are constructed in the local path segment for path optimization. The path expression of the material after obstacle avoidance processing in the local path segment is: in, It is an obstacle avoidance strategy based on Dijkstra algorithm. It means to obtain the obstacle position node parameters starting from the first obstacle. Define a function for the physical distance between the material and the obstacle location node, is the material movement parameter, is the material movement planning coefficient, is the obstacle location node layout feature, Plan vectors for obstacle avoidance behavior; 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 item 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 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: in, is a collection of materials, For materials The unit price, For materials The demand frequency, For materials The risk rate during the movement, For materials The change in demand, The number of dispatched devices required for the move, and They are the fuel consumption per unit distance when the equipment is empty and fully loaded, For the path to the material The timeliness level of movement, including material loading, 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.

3. 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, is the total number of nodes that the path passes through, and Two adjacent nodes and The phase division in the grid, Represents two adjacent nodes and The Euclidean distance value of .

4. 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. The calculation formula for the generation of individuals is: in, and is the first On behalf of individuals, is the uniform distribution factor, and Is the selected The calculation formula of uniform distribution factor is: in, for The random numbers in is the cross-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 generation of individuals is: in, For the Sutra The mutation operation obtains On behalf of individuals, For the selected On behalf of individuals, and For the The maximum and minimum mutation factors allowed for each generation. is the variation balance factor, where The calculation formula is: in, for A uniformly distributed random number in 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: in, and are the weight coefficients focusing on the shortest path and the optimal cost respectively, is the path length, is the total number of nodes traversed by the path, is the total number of grids experienced in the path, is the sum of the Manhattan distances between adjacent nodes where a turn occurs in the path, is the path smoothing factor. When the steering angle is less than or equal to 30 degrees, Set to 100, when the steering angle is greater than 30 degrees, Set to 1, The cost of moving materials within 1 hour.

5. 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.

6. 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: in is the score of the composite evaluation network, ' is the discount factor, , , are the number of times the mobile strategy successfully reaches the end point, conflicts occur, and other situations occur. is the global priority evaluation coefficient in the mobile strategy, Cumulative time waiting for conflicts.

7. A port terminal material movement simulation control method according to claim 6, characterized in that: The method of calculating the expected value of the composite evaluation network and maximizing the expected value to obtain the optimal distributed mobile 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: in, is the expected value, is the KL divergence, Represented as the softmax distribution of the composite evaluation network, is the normalization factor, 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.

8. 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.

9. 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