Complex equipment support simulation deduction method based on AnyLogic

Abstract

The invention relates to a complex equipment support simulation deduction method based on AnyLogic. The method comprises the following steps of: performing process carding on a complex equipment support task; constructing a complex equipment support conceptual model based on a DoDAF of the Ministry of National Defense; modeling and optimizing a complex equipment support vehicle scheduling problem; and building a complex equipment support simulation deduction system based on AnyLogic software. According to the complex equipment support simulation deduction system established based on the AnyLogic software, the whole-process evaluation and visual dynamic demonstration of the support process are realized, the process of the support task is optimized, and the execution efficiency of the complex equipment support task is effectively improved.

Description

Technical Field

[0001] This invention relates to a simulation and deduction method for complex equipment support based on AnyLogic, belonging to the field of complex equipment support and simulation. Background Technology

[0002] With the development of technology and the transformation of warfare, the importance of complex equipment is constantly increasing, bringing enormous support pressure to relevant units. Complex equipment support is characterized by a wide variety of tasks, complex processes, and high levels of coordination. Many requirements arise during the support process. In terms of infrastructure construction, it is necessary to meet the relevant needs of various complex equipment, providing suitable facilities and equipment for its support. In terms of support processes, complex equipment support tasks include dozens of operations, covering different fields such as ordnance, communications and navigation, machinery, and electronic warfare. During the support process, it is crucial to coordinate professionals from various fields to complete the tasks under limited support conditions, making coordination highly challenging. Summary of the Invention

[0003] The technical problem solved by this invention is to overcome the shortcomings of the prior art and propose a simulation and deduction method for complex equipment support based on AnyLogic. This method solves the problem that it is difficult to reasonably evaluate the support process due to the large number of task types and complex procedures in the traditional support process, and effectively improves the support efficiency of complex equipment.

[0004] The technical solution of this invention is: a simulation and deduction method for complex equipment support based on AnyLogic, comprising:

[0005] The tasks of supporting complex equipment were reviewed;

[0006] Based on the characteristics and requirements of complex equipment support, a conceptual model for complex equipment support is established, including a top-level architecture model, scheduling rules, and performance evaluation model.

[0007] A mathematical model for the scheduling of support vehicles for complex equipment was established, and an optimization algorithm for the scheduling of support vehicles was designed to calculate the optimal route and reasonable allocation scheme for support vehicles when performing tasks.

[0008] Based on the conceptual model of complex equipment support and the optimization algorithm for vehicle scheduling, guided by the discrete event modeling theory of multi-agent systems, and using AnyLogic modeling software, a simulation and deduction system for complex equipment support was designed and built to visualize the process of complex equipment support tasks.

[0009] The document outlines the types, characteristics, and processes of support for complex equipment, including a review of the specific circumstances, overall processes, and basic mission scenarios for support for complex equipment.

[0010] The survey on the specific circumstances of complex equipment support includes support types, support characteristics, and the support equipment involved; the overall process of complex equipment support is outlined, including the demand analysis stage, the support object selection stage, the material loading and transportation planning stage, and the mobile support equipment resource allocation stage; the basic task scenarios of complex equipment support are outlined, based on the specific process of equipment support, basic task scenarios are determined, covering the entire stage of support preparation, support in progress, and support completion, and the support equipment involved and the support tasks to be performed are clearly defined.

[0011] The complex equipment support concept model includes a top-level architecture model, scheduling rules, and performance evaluation model.

[0012] Based on the streamlined complex equipment support mission process, a top-level architecture model is established using the DoDAF architecture framework, including an advanced operational concept diagram model, an operational resource flow description model, an organizational relationship diagram model, an operational activity decomposition tree model, an operational activity model, and a state transition description model.

[0013] Based on the top-level architecture model and support task process, process-oriented scheduling rules and object-oriented scheduling rules are established, including: establishing process-oriented scheduling rules according to the temporal scheduling rules in the support task execution process, describing the temporal scheduling rules in the support task execution process, and clarifying the purpose and content of each step in the support process; starting from the common support equipment scheduling problems in complex equipment support, establishing object-oriented scheduling rules, which are scheduling strategies and methods formulated for the interaction, coordination and resource allocation between objects under specified conditions, to ensure that objects can work collaboratively according to the predetermined logical order and behavior pattern.

[0014] Based on the top-level architecture model of complex equipment support, an effectiveness evaluation model for complex equipment support is constructed. The evaluation index system for complex equipment support tasks consists of three levels of indicators. The first level indicator is the effectiveness of the support task, which is calculated by summarizing the second level indicators. The second level indicators consist of support effect evaluation, support resource coordination capability, support timeliness evaluation, and combat readiness capability. The third level indicators are further refined based on the second level indicators, including the maintenance-free usage time compliance rate, unit usage time failure rate, average failure detection rate, average support task cost, sortie rate, support resource utilization rate, redeployment preparation time, average repair time, average inspection time, combat readiness rate, and availability.

[0015] The establishment of a mathematical model for the scheduling of support vehicles for complex equipment, and the design of an optimization algorithm for the scheduling of support vehicles, to calculate the optimal route and reasonable allocation scheme for support vehicles when performing tasks, includes:

[0016] Based on the vehicle routing problem approach with time windows, this paper models the vehicle scheduling problem for complex equipment support. The modeling background and assumptions, the range of decision variables, the objective function, and the constraints are determined, resulting in a mathematical model for vehicle scheduling for complex equipment support. The modeling background and assumptions are inferred based on the support task flow, extracting key factors such as single-vehicle support capacity, support time required, and vehicle operation logic to simplify the flow. The range of decision variables selects the most basic parameters that have the greatest impact on the objective function, including the selection of support vehicles and vehicle transfer. The objective function defines three categories: total support time, total travel distance, and total support cost. Considering that the support process has stricter requirements for total support time, reducing the total support time of vehicles is the primary objective in the optimization process. The constraints include the total number of support vehicles departing from the depot, the number of support vehicles used in a single support task, the amount of transported resources not exceeding the loading capacity, support vehicles returning to the vehicle center sequentially, support time being less than the support vehicle dwell time, and vehicles providing support within the specified support time window.

[0017] A genetic algorithm was employed to address the complex equipment support vehicle scheduling mathematical model. This involved determining the integer encoding method for vehicle execution routes as chromosomes, the fitness calculation method based on weighted processing of the objective function, and the specific implementation of constraints in the code. Functions for initializing the population, calculating fitness, selection, crossover, and mutation were written to complete each step of the overall genetic algorithm process. After population initialization, the fitness of different chromosomes was calculated and sorted. Subsequently, multiple operations such as selection, crossover, and mutation were performed on the population. The loop ended when the number of iterations reached a set value, and the calculated optimal solution, i.e., the optimal vehicle route satisfying the constraints, was output.

[0018] By combining specific examples, we simulate and deduce the mathematical model and algorithm for scheduling vehicles for complex equipment support, analyze the results, and achieve the goal of optimizing the overall vehicle scheduling route and obtaining the optimal vehicle scheduling plan.

[0019] Guided by the discrete event modeling theory of multi-agent systems, and using AnyLogic modeling software, a simulation and deduction system for complex equipment support was designed and built to visualize the process of complex equipment support tasks, including:

[0020] Intelligent agents are constructed to support the normal operation of the system. These intelligent agents are divided into system architecture intelligent agents, task intelligent agents, and support element intelligent agents. The system architecture intelligent agent includes a main interface, scenario settings, simulation operation, and data analysis, representing the overall framework of the system design and optimizing the user experience from the user's perspective. The task intelligent agent corresponds to the combat activity model of the top-level architecture model and is used to establish corresponding task processes in AnyLogic software based on modeling libraries of different domains. The support element intelligent agents correspond to various elements in the advanced combat graph model and establish their own behavioral logic based on the description of state transitions in the state transition description model.

[0021] Based on the basic attributes, behavioral logic, and external interfaces of the intelligent agent, event, state, and process attributes are defined for different intelligent agents. A virtual task scheduling center is set up in the simulated running intelligent agent. The virtual task scheduling center encapsulates a task selection algorithm to control the overall task process and complete the task allocation, vehicle scheduling, and status monitoring during the guarantee process to ensure the normal operation of the guarantee task.

[0022] Simulations are conducted for specific cases, task scenarios are set, simulations are performed, and the results generated during the simulation are analyzed. The task scenario includes building a scene map, setting the support task type, the quantity of support equipment, task points, and task planning scheme in the scenario setting interface. The simulation is a visual simulation and real-time simulation of the task flow based on AnyLogic software and an intelligent agent. The result analysis involves analyzing the execution information and completion status of various support tasks within the intelligent agent. By comparing the simulation results of different schemes, the optimal scenario scheme is comprehensively selected, achieving the goals of real-time observation of the support process, comprehensive control of task information, and comparison to obtain the optimal solution.

[0023] The advantages of this invention compared to the prior art are:

[0024] 1. Comprehensively enhance systematic modeling capabilities. By building a top-level architecture model using the DoDAF system architecture framework, we can achieve full-process structured modeling of complex equipment support tasks, solving the problems of fragmented processes and poor collaboration in traditional methods. At the same time, the constructed top-level architecture model supports rapid adaptation to different scenarios, reducing secondary development costs.

[0025] 2. Multi-objective scheduling optimization is precise and efficient. A genetic algorithm is used to optimize the vehicle scheduling problem, prioritizing total guarantee time while simultaneously reducing travel distance and cost. Matlab is used to simulate real-time responses to resource changes, ensuring vehicle allocation meets multiple constraints.

[0026] 3. The simulation system boasts outstanding interactivity and practicality. Based on AnyLogic software, it enables multi-agent modeling and dynamic demonstration of the assurance process, enhancing the intuitiveness of decision-making. It integrates a three-level performance evaluation index system, outputting key indicators in real time and supporting rapid solution iteration. Attached Figure Description

[0027] Figure 1 A top-level architecture model for supporting complex equipment missions.

[0028] Figure 2 An evaluation system for the support effectiveness of complex equipment.

[0029] Figure 3 The overall process of genetic algorithm for vehicle scheduling to ensure complex equipment.

[0030] Figure 4 Provide a simulation system architecture for complex equipment. Detailed Implementation

[0031] like Figure 1 As shown, this invention relates to a top-level architecture model for complex equipment support missions, built upon the U.S. Department of Defense System Architecture Framework (DoDAF), including a conceptual model, complex equipment support mission flow, mission tree, and state transition process. It employs a high-level operational concept diagram model, operational resource flow description model, operational activity decomposition tree model, operational activity model, and state transition model from the operational activity view to model the framework of complex equipment support missions under a specific context. The specific steps are as follows:

[0032] Step 1: Based on the overall mission flow of complex equipment support, construct an advanced operational concept map (OV-1) model.

[0033] Step 2: Based on the OV-1 model, the complex equipment support framework structure, and the complex equipment support task process, construct the Operational Resource Flow Description (OV-2) model.

[0034] Step 3: Based on the framework, task flow and model in Step 2, construct the complex equipment support task tree. On this basis, further construct the Operational Activity (OV-5) model, including the Operational Activity Decomposition Tree (OV-5a) model and the Operational Activity Flow (OV-5b) model.

[0035] Step 4: Based on the operational activity model constructed in Step 3, establish the Operational State Transition (OV-6) model, mainly the State Transition Description (OV-6b) model.

[0036] By following the above four steps, a top-level architecture model for complex equipment support is built, providing further guidance for the development of simulation systems for complex equipment support.

[0037] like Figure 2As shown, this invention provides a complex equipment support effectiveness evaluation model, including a complex equipment support task evaluation index system. This index system consists of three levels of indicators. The first-level indicator is support task effectiveness, which is calculated and aggregated from the second-level indicators. The second-level indicators consist of support effect evaluation, support resource coordination capability, support timeliness evaluation, and combat readiness capability. The third-level indicators further refine the second-level indicators, including: maintenance-free usage time compliance rate, unit usage time failure rate, average failure detection rate; average support task cost, sortie rate, support resource utilization rate; redeployment preparation time, average repair time, average inspection time; combat readiness rate, and availability. Through this evaluation model, support capabilities and levels are quantitatively analyzed for each stage of the support process, achieving the goals of optimizing the model structure and rationally allocating resources.

[0038] like Figure 3 As shown, this invention provides a vehicle scheduling optimization algorithm. It employs a genetic algorithm, using the total support time, total travel distance, and total support cost of each vehicle as optimization objectives. Considering the stringent requirements for total support time during the support process, reducing the total support time is the primary objective in the optimization process. In the scheduling of vehicles for complex equipment support, to achieve optimization analysis of the multi-objective function, it is necessary to control each parameter and decision variable within a certain range. Therefore, this invention defines the constraints in the complex equipment support vehicle scheduling optimization model. This invention uses Matlab software to program and deduce the complex equipment support vehicle scheduling optimization algorithm. The various stages of the overall genetic algorithm process are completed by writing functions for initializing the population and calculating fitness. After the population is initialized, the fitness of different chromosomes is calculated and sorted. Subsequently, selection, crossover, and mutation operations are performed on the population. When the number of iterations reaches a set value, the loop ends, and the calculated optimal solution is output.

[0039] like Figure 4 As shown, this invention provides an overall architecture for a complex equipment support simulation system. The AnyLogic-based complex equipment support simulation system includes three types of intelligent agents: system architecture intelligent agents, task intelligent agents, and support element intelligent agents.

[0040] The system architecture consists of four intelligent agents: main interface, scenario settings, simulation operation, and data analysis. These four agents represent the overall framework of the system design, optimizing the user experience from the user's perspective.

[0041] Corresponding to the Operational Activities (OV-5b) model of the top-level architecture model for mission intelligent agents and complex equipment support, corresponding mission processes were established under the guidance of the operational activities model.

[0042] The security element agents correspond to the various elements in the Advanced Operational Concept Map (OV-1) model. Simultaneously, based on the state transition descriptions in the State Transition Description (OV-6b) model, they establish their own behavioral logic.

[0043] The complex equipment support simulation system consists of four interfaces: main interface, scenario settings, simulation operation, and data analysis. The main interface displays the overall system status, the scenario settings are used to formulate scenarios under different task conditions, the simulation operation displays the entire simulation process, and the data analysis is used to analyze the various data generated during the simulation.

[0044] Based on the above system architecture, the complex equipment support simulation system can achieve the following three functions: formulate mission scenarios, simulate mission processes, and perform data analysis.

[0045] In the task scenario development function, the system supports users to develop various scenarios under different conditions, different support tasks and different support equipment, and supports saving and retrieving scenarios for simulation and evaluation under different situations.

[0046] In the simulation task flow function, the system establishes a corresponding model for complex equipment support and simulates the complete process of complex equipment support.

[0047] In the data analysis function, based on the complex equipment support assessment model, a data analysis module was established in the system to display various data indicators obtained after simulation, and to compare and analyze them.

[0048] Furthermore, this invention also provides a simulation and deduction method for complex equipment support based on AnyLogic, specifically including the following steps. Step 1: Analyze the complex equipment support task process.

[0049] During the process of sorting out the support tasks for complex equipment, the support types, support characteristics, and support processes for each task are sorted out in detail, providing structural support and theoretical basis for the establishment of a support model for complex equipment.

[0050] Specifically, it includes the following steps:

[0051] 1.1 Investigate the specific situation: Investigate the specific situation of support for complex equipment, including the type of support, the characteristics of support, and the equipment involved in support.

[0052] 1.2 Streamline the overall process: Streamline the overall process of complex equipment support, including the demand analysis stage, the support object selection stage, the material loading and transportation planning stage, and the mobile support equipment resource allocation stage;

[0053] 1.3 Identify basic task scenarios: Identify the basic task scenarios for complex equipment support. Based on the specific process of equipment support, identify the basic task scenarios, covering the entire stage of support preparation, support in progress, and support completion, and clarify the support equipment involved and the support tasks to be performed.

[0054] Step 2: Construction of a conceptual model for the support of complex equipment.

[0055] Based on the analyzed specific circumstances, overall process, and basic task scenarios of the support mission, a conceptual model for complex equipment support is established, including a top-level architecture model, scheduling rules, and performance evaluation model, focusing on the characteristics and needs of complex equipment support.

[0056] Specifically, it includes the following steps:

[0057] 2.1 Establishing a top-level architecture model: Based on the complex equipment support task process outlined in Step 1, a top-level architecture model is established using the DoDAF architecture framework, including an advanced operational concept diagram model, an operational resource flow description model, an organizational relationship diagram model, an operational activity decomposition tree model, an operational activity model, and a state transition description model.

[0058] 2.2 Establishing Scheduling Rules: Based on the top-level architecture model and support task flow, process-oriented scheduling rules and object-oriented scheduling rules are established, including: establishing process-oriented scheduling rules according to the temporal scheduling rules in the support task execution process, describing the temporal scheduling rules in the support task execution process, focusing on clarifying the purpose and content of each step in the support process; starting from the common support equipment scheduling problems in complex equipment support, establishing object-oriented scheduling rules, which are the scheduling strategies and methods formulated for the interaction, coordination and resource allocation between objects under specified conditions, to ensure that objects can work collaboratively according to the predetermined logical order and behavior pattern;

[0059] 2.3 Constructing an Effectiveness Evaluation Model: Based on the top-level architecture model of complex equipment support, an effectiveness evaluation model for complex equipment support is constructed. The evaluation index system for complex equipment support tasks consists of three levels of indicators. The first-level indicator is the effectiveness of the support task, which is calculated by summarizing the second-level indicators. The second-level indicators consist of support effect evaluation, support resource coordination capability, support timeliness evaluation, and combat readiness capability. The third-level indicators further refine the second-level indicators, including the maintenance-free usage time compliance rate, unit usage time failure rate, average failure detection rate; average support task cost, sortie rate, support resource utilization rate; redeployment preparation time, average repair time, average inspection time; combat readiness rate, and operational availability.

[0060] Step 3: Modeling the vehicle scheduling problem for complex equipment support.

[0061] A mathematical model for vehicle scheduling in complex equipment support is established, treating it as a multivariable, multi-constraint, and multi-objective vehicle scheduling problem. A genetic algorithm is then used to optimize the problem, aiming to achieve rational vehicle scheduling and improve support effectiveness.

[0062] Specifically, it includes the following steps:

[0063] 3.1 Establishing a Mathematical Model for Vehicle Scheduling in Complex Equipment Support: Based on the Vehicle Routing Problem with Time Windows (VRPTW), a mathematical model for vehicle scheduling in complex equipment support is established. The modeling background and assumptions, the range of decision variables, the objective function, and the constraints are determined, resulting in a mathematical model for vehicle scheduling in complex equipment support. The modeling background and assumptions are inferred based on the support task flow, extracting key factors such as single-vehicle support capacity, support time required, and vehicle operation logic to simplify the flow. The range of decision variables selects the most basic parameters that have the greatest impact on the objective function, including the selection of support vehicles and vehicle transfer. The objective function defines three categories: total support time, total travel distance, and total support cost. Considering the stricter requirements for total support time in the support process, reducing the total support time of vehicles is taken as the primary objective in the optimization process. The constraints include the total number of support vehicles departing from the depot, the number of support vehicles used in a single support task, the amount of transported resources not exceeding the loading capacity, support vehicles returning to the vehicle center sequentially, support time being less than the support vehicle dwell time, and vehicles providing support within the specified support time window.

[0064] 3.2 Determining the Overall Flow of the Algorithm: A genetic algorithm is employed. For the constructed mathematical model of complex equipment support vehicle scheduling, the following steps are determined: an integer encoding method using vehicle execution routes as chromosomes; a fitness calculation method based on weighted processing of the objective function; and the specific implementation of constraints in the code. Functions for initializing the population, calculating fitness, selection, crossover, and mutation are written to complete each stage of the overall genetic algorithm flow. After the population is initialized, the fitness of different chromosomes is calculated and sorted. Subsequently, multiple operations such as selection, crossover, and mutation are performed on the population. When the number of iterations reaches a set value, the loop ends, and the calculated optimal solution, i.e., the optimal vehicle route satisfying the constraints, is output.

[0065] 3.3 Feasibility and Effectiveness Analysis of Mathematical Model and Algorithm: Based on specific examples, the mathematical model and algorithm for scheduling complex equipment support vehicles are simulated and analyzed to optimize the overall vehicle scheduling routes and obtain the optimal vehicle scheduling scheme. Taking the adopted example, the support task is divided into four resources: ammunition, electricity, fuel, and gas, corresponding to four types of support vehicles: ammunition-carrying vehicles, electric vehicles, refueling vehicles, and gas-filling support vehicles. After setting specific simulation parameters, simulation results and travel paths for each type of support vehicle are obtained. The optimal simulation result is selected as the optimized vehicle scheduling scheme.

[0066] Step 4: Building a simulation and deduction system for complex equipment support.

[0067] Based on the above steps, guided by the discrete event modeling theory of multi-agent systems, and using AnyLogic modeling software, a simulation and deduction system for complex equipment support was designed and built to visualize the process of complex equipment support tasks.

[0068] Specifically, it includes the following steps:

[0069] 4.1 Building the Overall System: Constructing intelligent agents to support the normal operation of the system. Intelligent agents can be divided into three main categories: system architecture intelligent agents, task intelligent agents, and support element intelligent agents. The system architecture intelligent agent includes four components: main interface, scenario settings, simulation operation, and data analysis, representing the overall framework of the system design and optimizing the user experience from the user's perspective. The task intelligent agent corresponds to the combat activity model of the top-level architecture model, used to establish corresponding task flows in AnyLogic software based on modeling libraries from different domains. The support element intelligent agents correspond to various elements in the advanced combat graph model. Simultaneously, based on the state transition description model, they establish their own behavioral logic.

[0070] 4.2 Refining the Intelligent Agents: This section addresses the communication, interaction, and decision-making issues between intelligent agents, focusing on their behavioral logic and mutual interaction. Based on the basic attributes, behavioral logic, and external interfaces of the intelligent agents, event, state, and process attributes are defined for different agents. These agents are also embedded within other agents to demonstrate the relationships between them. Furthermore, a virtual task scheduling center is set up within the simulated intelligent agents. This virtual task scheduling center encapsulates task selection algorithms and its main task is to control the overall task flow and perform task allocation, vehicle scheduling, and status monitoring during the support process, ensuring the normal operation of the support mission.

[0071] 4.3 Feasibility Verification: Simulations are conducted for specific cases, task scenarios are set, simulations are performed, and the results are analyzed. The task scenario includes building a scene map, setting the support task type, quantity of support equipment, task points, and task planning scheme in the scenario settings interface; the simulation is a visual simulation and real-time simulation of the task flow based on AnyLogic software and the intelligent agent; the result analysis involves analyzing the execution information and completion status of various support tasks within the intelligent agent. By comparing the simulation results of different schemes, the optimal scenario scheme is comprehensively selected, achieving the goals of real-time observation of the support process, comprehensive control of task information, and comparison to obtain the optimal solution.

[0072] The present invention will be further illustrated below by way of examples.

[0073] A simulation method for military airport support based on AnyLogic includes the following steps:

[0074] Step 1: Review the procedures for military airport support missions.

[0075] The document provides a detailed overview of the types, characteristics, and procedures for supporting military airfields, including the following steps:

[0076] 1.1 Investigate the specific situation: Investigate the airport situation, analyze the types of airport support tasks, and summarize the characteristics of airport support.

[0077] 1.2 Streamline the overall process: Confirm the overall process of airport support, including the formulation of flight and operational plans, outbound from the warehouse, loading of ammunition, inspection, proceeding to the flight position, takeoff and landing, fault repair, maintenance, return to the warehouse, and redeployment.

[0078] 1.3 Analyze basic mission scenarios: Analyze the detailed mission processes for typical mission scenarios in airport support, including engine power supply, pilot self-support, transition from Class II to Class I, transition from Class I to takeoff, transition from Class II to takeoff, and post-flight inspection.

[0079] Step 2: Construction of the airport support concept model.

[0080] Using the DoDAF architecture framework, a corresponding top-level architecture model is established based on the characteristics and needs of airport support. This includes the following steps:

[0081] 2.1 Establishing a top-level architecture model: Based on the airport support mission process outlined in Step 1, a top-level architecture model is established using the U.S. Department of Defense System Architecture Framework (DoDAF).

[0082] 2.2 Establishing Scheduling Rules: Based on the time-series scheduling rules in the execution of airport support tasks, process-oriented scheduling rules are established. Simultaneously, starting with common equipment scheduling problems in airport support, object-oriented scheduling rules are established.

[0083] 2.3 Constructing an effectiveness evaluation model: Based on the top-level architecture model of airport support, construct an effectiveness evaluation model for airport support, and determine the significance and calculation methods of specific indicators.

[0084] Step 3: Modeling the airport support vehicle scheduling problem.

[0085] The problem of dispatching support vehicles involved in airport operations is modeled, and corresponding algorithms are designed for optimization. Specifically, the steps include:

[0086] 3.1 Establishing a mathematical model for airport support vehicle scheduling: Three objective functions were proposed: total support time, total travel distance, and total support cost. Based on the set constraints, the total support time was selected as the primary objective in the optimization process, and the airport support vehicle scheduling problem was modeled.

[0087] 3.2 Determine the overall process of the algorithm used: Using a genetic algorithm, design the steps and corresponding functions of the algorithm for the constructed mathematical model of airport support vehicle scheduling.

[0088] 3.3 Analysis of the feasibility and effectiveness of the mathematical model and algorithm: Based on a specific airport support case, the model and algorithm are simulated and analyzed to determine the results.

[0089] Step 4: Establish an airport support simulation system.

[0090] Building an airport support simulation system in AnyLogic software to visualize the airport support task process involves the following steps:

[0091] 4.1 System Construction: Considering user needs and research objectives, an airport support simulation system architecture was designed. Based on the airport support conceptual model, corresponding intelligent agents were established in AnyLogic software, and these agents were categorized into three types: system architecture intelligent agents, task intelligent agents, and support element intelligent agents.

[0092] 4.2 Refine the intelligent agent: Solve the communication, interaction, and decision-making problems between intelligent agents, and set the basic attributes, behavioral logic, and external interfaces of the intelligent agents.

[0093] 4.3 Feasibility Verification: In order to verify the integrity and feasibility of the system, a simulation was conducted for a specific case of airport support, and the simulation results were compared with the actual support situation.

[0094] Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make possible changes and modifications to the technical solutions of the present invention based on the above-disclosed technical content without departing from the spirit and scope of the present invention. Therefore, any simple modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solutions of the present invention shall fall within the protection scope of the technical solutions of the present invention.

Claims

1. A simulation and deduction method for complex equipment support based on AnyLogic, characterized in that, include: Sorting out complex equipment support tasks; Based on the characteristics and requirements of complex equipment support, a conceptual model for complex equipment support is established, including a top-level architecture model, scheduling rules, and performance evaluation model. A mathematical model for the scheduling of support vehicles for complex equipment was established, and an optimization algorithm for the scheduling of support vehicles was designed to calculate the optimal route and reasonable allocation scheme for support vehicles when performing tasks. Based on the conceptual model of complex equipment support and the optimization algorithm for vehicle scheduling, guided by the discrete event modeling theory of multi-agent systems, and using AnyLogic modeling software, a simulation and deduction system for complex equipment support was designed and built to visualize the process of complex equipment support tasks.

2. The method for simulation and deduction of complex equipment support based on AnyLogic according to claim 1, characterized in that, The document outlines the types, characteristics, and processes of support for complex equipment, including a review of the specific circumstances, overall processes, and basic mission scenarios for support for complex equipment.

3. The method for simulation and deduction of complex equipment support based on AnyLogic according to claim 2, characterized in that, The survey on the specific circumstances of complex equipment support includes support types, support characteristics, and the support equipment involved; the overall process of complex equipment support is outlined, including the demand analysis stage, the support object selection stage, the material loading and transportation planning stage, and the mobile support equipment resource allocation stage; the basic task scenarios of complex equipment support are outlined, based on the specific process of equipment support, basic task scenarios are determined, covering the entire stage of support preparation, support in progress, and support completion, and the support equipment involved and the support tasks to be performed are clearly defined.

4. The method for simulation and deduction of complex equipment support based on AnyLogic according to claim 1, characterized in that, The complex equipment support concept model includes a top-level architecture model, scheduling rules, and performance evaluation model.

5. The method for simulation and deduction of complex equipment support based on AnyLogic according to claim 4, characterized in that, Based on the streamlined complex equipment support mission process, a top-level architecture model is established using the DoDAF architecture framework, including an advanced operational concept diagram model, an operational resource flow description model, an organizational relationship diagram model, an operational activity decomposition tree model, an operational activity model, and a state transition description model.

6. The method for simulation and deduction of complex equipment support based on AnyLogic according to claim 4, characterized in that, Based on the top-level architecture model and support task process, process-oriented scheduling rules and object-oriented scheduling rules are established, including: establishing process-oriented scheduling rules according to the temporal scheduling rules in the support task execution process, describing the temporal scheduling rules in the support task execution process, and clarifying the purpose and content of each step in the support process; starting from the common support equipment scheduling problems in complex equipment support, establishing object-oriented scheduling rules, which are scheduling strategies and methods formulated for the interaction, coordination and resource allocation between objects under specified conditions, to ensure that objects can work collaboratively according to the predetermined logical order and behavior pattern.

7. The method for simulation and deduction of complex equipment support based on AnyLogic according to claim 4, characterized in that, Based on the top-level architecture model of complex equipment support, an effectiveness evaluation model for complex equipment support is constructed. The evaluation index system for complex equipment support tasks consists of three levels of indicators. The first level indicator is the effectiveness of the support task, which is calculated by summarizing the second level indicators. The second level indicators consist of support effect evaluation, support resource coordination capability, support timeliness evaluation, and combat readiness capability. The third-level indicators are further refined based on the second-level indicators, including the maintenance-free usage time compliance rate, unit usage time failure rate, average failure detection rate, average support mission cost, sortie rate, support resource utilization rate, redeployment preparation time, average repair time, average inspection time, combat readiness rate, and availability.

8. The method for simulation and deduction of complex equipment support based on AnyLogic according to claim 1, characterized in that, The establishment of a mathematical model for the scheduling of support vehicles for complex equipment, and the design of an optimization algorithm for the scheduling of support vehicles, to calculate the optimal route and reasonable allocation scheme for support vehicles when performing tasks, includes: Based on the vehicle routing problem approach with time windows, this paper models the vehicle scheduling problem for complex equipment support. The modeling background and assumptions, the range of decision variables, the objective function, and the constraints are determined, resulting in a mathematical model for vehicle scheduling for complex equipment support. The modeling background and assumptions are inferred based on the support task flow, extracting key factors such as single-vehicle support capacity, support time required, and vehicle operation logic to simplify the flow. The range of decision variables selects the most basic parameters that have the greatest impact on the objective function, including the selection of support vehicles and vehicle transfer. The objective function defines three categories: total support time, total travel distance, and total support cost. Considering that the support process has stricter requirements for total support time, reducing the total support time of vehicles is the primary objective in the optimization process. The constraints include the total number of support vehicles departing from the depot, the number of support vehicles used in a single support task, the amount of transported resources not exceeding the loading capacity, support vehicles returning to the vehicle center sequentially, support time being less than the support vehicle dwell time, and vehicles providing support within the specified support time window. A genetic algorithm was employed to address the complex equipment support vehicle scheduling mathematical model. This involved determining the integer encoding method for vehicle execution routes as chromosomes, the fitness calculation method based on weighted processing of the objective function, and the specific implementation of constraints in the code. Functions for initializing the population, calculating fitness, selection, crossover, and mutation were written to complete each step of the overall genetic algorithm process. After population initialization, the fitness of different chromosomes was calculated and sorted. Subsequently, multiple operations such as selection, crossover, and mutation were performed on the population. The loop ended when the number of iterations reached a set value, and the calculated optimal solution, i.e., the optimal vehicle route satisfying the constraints, was output. By combining specific examples, we simulate and deduce the mathematical model and algorithm for scheduling vehicles for complex equipment support, analyze the results, and achieve the goal of optimizing the overall vehicle scheduling route and obtaining the optimal vehicle scheduling plan.

9. The method for simulation and deduction of complex equipment support based on AnyLogic according to claim 1, characterized in that, Guided by the discrete event modeling theory of multi-agent systems, and using AnyLogic modeling software, a simulation and deduction system for complex equipment support was designed and built to visualize the process of complex equipment support tasks, including: Intelligent agents are constructed to support the normal operation of the system. These intelligent agents are divided into system architecture intelligent agents, task intelligent agents, and support element intelligent agents. The system architecture intelligent agent includes a main interface, scenario settings, simulation operation, and data analysis, representing the overall framework of the system design and optimizing the user experience from the user's perspective. The task intelligent agent corresponds to the combat activity model of the top-level architecture model and is used to establish corresponding task processes in AnyLogic software based on modeling libraries of different domains. The support element intelligent agents correspond to various elements in the advanced combat graph model and establish their own behavioral logic based on the description of state transitions in the state transition description model. Based on the basic attributes, behavioral logic, and external interfaces of the intelligent agent, event, state, and process attributes are defined for different intelligent agents. A virtual task scheduling center is set up in the simulated running intelligent agent. The virtual task scheduling center encapsulates a task selection algorithm to control the overall task process and complete the task allocation, vehicle scheduling, and status monitoring during the guarantee process to ensure the normal operation of the guarantee task. Simulations are conducted for specific cases, task scenarios are set, simulations are performed, and the results generated during the simulation are analyzed. The task scenario includes building a scene map, setting the support task type, the quantity of support equipment, task points, and task planning scheme in the scenario setting interface. The simulation is a visual simulation and real-time simulation of the task flow based on AnyLogic software and an intelligent agent. The result analysis involves analyzing the execution information and completion status of various support tasks within the intelligent agent. By comparing the simulation results of different schemes, the optimal scenario scheme is comprehensively selected, achieving the goals of real-time observation of the support process, comprehensive control of task information, and comparison to obtain the optimal solution.

Images