Gas explosion accident emergency resource scheduling optimization method, system and device based on improved particle swarm optimization, and medium

Abstract

The invention discloses a gas explosion accident emergency resource scheduling optimization method, system and device based on an improved particle swarm optimization algorithm, and a medium, and the method comprises the following steps: constructing a gas explosion region emergency resource scheduling model, determining a target function with the minimization of rescue time as a target, and setting a constraint condition; carrying out model particle swarm parameter initialization, and mapping each particle into an effective task sequence by adopting a position-based mapping method so as to form an initial population representing a rescue scheme; a greedy heuristic algorithm is combined with an improved particle swarm algorithm to solve the gas explosion area emergency resource scheduling model, the greedy heuristic algorithm obtains a local optimal solution of a target function through iterative search, the improved particle swarm algorithm finds a global optimal particle through algorithm iteration, and finally an optimal rescue scheme and a corresponding target value are obtained. According to the algorithm, emergency resource scheduling of the gas explosion accident is optimized, and the timeliness of emergency response and the rescue efficiency can be remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of optimization scheduling, and in particular to a method, system, device and medium for optimizing emergency resource scheduling of gas explosion accidents based on an improved particle swarm algorithm. Background Art

[0002] With the acceleration of urbanization, the risk of gas accidents is also increasing. Once a gas accident occurs, emergency resources need to be dispatched quickly and effectively to reduce the damage and impact of the accident. Therefore, it is of great significance to study the emergency dispatch of gas accidents, which can improve the efficiency and effectiveness of emergency rescue and protect people's life safety and property safety.

[0003] Gas explosions are sudden and rapidly spreading, often occurring without warning and causing serious damage. Emergency resource scheduling faces huge challenges, which need to consider cost, energy consumption and time. Current research focuses on scheduling optimization, where time urgency is crucial. Particle Swarm Optimization (PSO) can effectively handle multi-objective optimization problems by simulating the behavior of bird flocks, facilitating rapid and low-cost rescue.

[0004] Technical solution of prior art 1: Application number 202311467918 proposes a method for constructing emergency materials-paths in mine accident areas based on an improved PSO-BA algorithm. This method solves the nonlinear programming problem of the mathematical model by integrating two algorithms to obtain the optimal value of the objective function, and calculates the dispatch quantity and multi-level dispatching scheme of emergency materials. This invention adopts multi-objective scheduling optimization, taking into account factors such as cost, time, and resource utilization, to achieve reasonable resource allocation and adapt to different emergency events. However, there is a risk of falling into a local optimum rather than a global optimum.

[0005] Technical solution of the second prior art: Application number 2022107958800 proposes a method for allocating environmental emergency materials at multiple demand points based on a complex network. The allocation decision of emergency materials is optimized by establishing a threat assessment system for chemical water pollution incidents. However, this method relies too much on parameter settings, and these parameters require a lot of experiments to adjust, which may lead to certain risks in the accuracy of the scheduling plan, which may lead to less than expected results in actual emergency situations. Summary of the invention

[0006] The purpose of the present invention is to provide a method, system, device and medium for optimizing the dispatch of emergency resources for gas explosion accidents based on an improved particle swarm optimization algorithm. The algorithm of the present invention optimizes the dispatch of emergency resources for gas explosion accidents, can significantly improve the timeliness of emergency response and rescue efficiency, and its solution quality and computational efficiency are better than those of traditional particle swarm optimization algorithms.

[0007] To achieve the above purpose, the technical solution provided by the present invention is:

[0008] The first aspect of the present application provides a method for optimizing emergency resource scheduling for gas explosion accidents using an improved particle swarm algorithm, comprising the following steps:

[0009] Construct an emergency resource dispatch model for gas explosion areas, establish an objective function to minimize rescue time, and set constraints;

[0010] Initialize the model particle swarm parameters and use a position-based mapping method to map each particle to a valid task sequence, thereby forming an initial population representing the rescue plan;

[0011] The greedy heuristic algorithm combined with the improved particle swarm algorithm is used to solve the emergency resource scheduling model in the gas explosion area. The greedy heuristic algorithm obtains the local optimal solution of the objective function through iterative search, and the improved particle swarm algorithm finds the global optimal particle through algorithm iteration, and finally obtains the best rescue plan and the corresponding target value.

[0012] To optimize the above technical solutions, the specific measures taken also include:

[0013] The parameter initialization described above uses a position-based mapping method to map each particle to a valid task sequence, thereby forming an initial population representing a rescue solution, including:

[0014] Using the particle swarm optimization algorithm, all particles in the particle swarm are randomly initialized so that each particle represents a possible emergency resource scheduling solution, and the random position and speed, maximum position, minimum position, maximum speed, minimum speed, and maximum number of iterations are initialized;

[0015] Map the position information of each particle into an effective rescue plan;

[0016] The heap sorting strategy is used to generate the initial rescue plan as the initial value of the current best solution.

[0017] Furthermore, suppose there is a group ψ particles consisting of all |ψ|, each particle ψ t (t=1,2,…,|ψ|) and position p t and speed v t are associated, represented as n-dimensional tuples and The position of the personal best particle is given by The position of the global best particle tracked by the group is represented by Representation; Restriction and In the interval [p min ,p max ] and [vmin ,v max ]Inside;

[0018] In the PSO framework, particles move toward the personal best particle and the global best particle through the traditional particle update strategy; during each iteration, the particle velocity and position updates can be expressed as:

[0019]

[0020] Among them, ω represents the inertia weight, c1 and c2 represent the individual cognitive component and social communication component respectively; r1 and r2 are two uniformly distributed numbers in [0,1]; the particle's motion speed in the i-th dimension is Mainly depends on and The value of .

[0021] Furthermore, assuming that the current best rescue solution is ζ * It means that for each particle ψ t (t=1,2,…,ψ), the mapping method used is to solve ζ from the empty t Start with and make it a complete solution through a two-stage procedure;

[0022] In the first stage, * Each task in Attach to t In, we have: When ρ∈(0,1) is true, the position minimum p is restricted min > 0; copy of the current best rescue plan Eliminate all these additional tasks in order to avoid * The destruction is used to generate a corresponding rescue plan for each particle;

[0023] In the second stage, Each of the remaining tasks in is inserted into ζ in a uniformly distributed manner t In The probability of each task being located at each position in is 1 / |ζ t |,ζ t Becoming a complete task arrangement is the final result of the mapping method.

[0024] Furthermore, the greedy heuristic algorithm is applied to solve the emergency resource scheduling model in the gas explosion area, and the local optimal solution of the objective function is obtained through iterative search. The process is as follows:

[0025] In order to calculate the target value obj of the rescue plan generated in the previous mapping process, a greedy heuristic algorithm is used. The accident points of a given rescue plan are assigned to each emergency material depot one by one in a greedy manner. When the target is finally obtained, the task is completed;

[0026] For a specific solution t Tasks in Task target value By placing the accident point Allocated to emergency supply depots j To represent, the index y of the allocated emergency resource is expressed as:

[0027]

[0028] Furthermore, the improved particle swarm algorithm is applied to find the global optimal particle through algorithm iteration, including:

[0029] Determine the global optimal solution search conditions for each particle and update the global best particle;

[0030] Dynamically adjust particle speed and position;

[0031] For each particle, determine the local optimal solution search conditions and update the personal best particle;

[0032] For each particle, the global optimal solution search condition is judged, and the current best rescue plan, target value and global best particle are updated.

[0033] The improved particle swarm algorithm starts with the parameter initialization process. The particles in the particle swarm are randomly generated, and each particle is regarded as its personal best particle. The current best solution is initialized using heap sorting. * , whose target value is calculated by a greedy heuristic algorithm, and all particles are evaluated through an iterative process, in which the global best particle is initialized and each particle is mapped to the corresponding rescue solution; in this process, if a better particle is found, the personal best particle is updated; if a new and better rescue solution is found, the current best rescue solution, target value and global best particle are updated accordingly.

[0034] The second aspect of the present application provides a gas explosion accident emergency resource scheduling optimization system based on an improved particle swarm algorithm, comprising:

[0035] The model building module is used to build an emergency resource dispatch model for gas explosion areas, establish an objective function with the goal of minimizing rescue time, and set constraints; initialize the model particle swarm parameters, use a position-based mapping method, map each particle to a valid task sequence, and thus form an initial population representing the rescue plan;

[0036] The model solving module is used to apply the greedy heuristic algorithm combined with the improved particle swarm algorithm to solve the emergency resource scheduling model in the gas explosion area. The greedy heuristic algorithm obtains the local optimal solution of the objective function through iterative search, and the improved particle swarm algorithm finds the global optimal particles through algorithm iteration, and finally obtains the best rescue plan and the corresponding target value.

[0037] The third aspect of the present application provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for optimizing emergency resource scheduling for gas explosion accidents based on the improved particle swarm algorithm as described above is implemented.

[0038] A fourth aspect of the present application provides a computer-readable storage medium storing a computer program, wherein the computer program enables a computer to execute the above-mentioned improved particle swarm algorithm method for optimizing emergency resource scheduling for gas explosion accidents.

[0039] Compared with the prior art, the present invention has the following beneficial effects:

[0040] Aiming at the multi-task-multi-emergency resource scheduling problem in gas explosion accidents, the present invention constructs a mathematical model with the goal of minimizing rescue time, uses greedy heuristics and particle swarm optimization (PSO) to find the optimal solution, and can dynamically adjust the solution according to the situation at the accident site. Combined with the location-based mapping method and heap sorting, the timeliness of the PSO algorithm in the emergency resource scheduling process is improved, and it is superior to the traditional particle swarm optimization algorithm in terms of solution quality and computational efficiency, and can be widely used.

[0041] The algorithm in the present invention adopts a position-based mapping method to map each particle in the particle swarm to the corresponding rescue plan, ensuring the correspondence between the particle position and the rescue plan. At the same time, by using a greedy heuristic algorithm, the algorithm can calculate the target value of the rescue plan generated during the mapping process, thereby providing a basis for particle update, effectively responding to emergencies, and improving rescue efficiency.

[0042] The particle swarm optimization algorithm of the present invention has the following advantages and effects in solving the multi-task-multi-emergency resource scheduling problem: Solution quality: The algorithm is superior to the traditional particle swarm optimization algorithm in terms of solution quality, and can effectively respond to emergency situations and improve rescue efficiency. Computational efficiency: The designed algorithm achieves good computational efficiency by adopting this low-complexity mapping operator. Diversity preservation: Through the location-based mapping method, the algorithm can maintain the diversity of the population and avoid premature convergence of the algorithm. Local optimal problem solving: Through the heap sorting algorithm, the possibility of finding the global optimal solution is improved.

[0043] The method of the present invention has broad application prospects and can effectively cope with the challenges brought by gas explosion accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 : Schematic diagram of the flow chart of the gas explosion accident emergency resource scheduling optimization method based on the improved particle swarm algorithm of the present invention.

[0045] Figure 2 : Schematic diagram of the specific implementation process of the gas explosion accident emergency resource scheduling optimization method based on the improved particle swarm algorithm of the present invention. DETAILED DESCRIPTION

[0046] The above contents of the present invention are further described in detail below in the form of embodiments, but this should not be understood as the scope of the above subject matter of the present invention being limited to the following embodiments, and all technologies realized based on the above contents of the present invention belong to the scope of the present invention.

[0047] Some of the terms involved in the solution of the present invention are explained as follows:

[0048] The particle swarm optimization algorithm (PSO) simulates the behavior of bird flocks to effectively handle multi-objective optimization problems and facilitate rapid and low-cost rescue.

[0049] In the multi-task and multi-emergency resource scheduling problem in gas explosion accidents, n resource request tasks are issued by the accident point, and the command center receives the request, clarifies the relevant information (including task number, required resource type and quantity, task location, task urgency, etc.), and then promptly analyzes the relevant information of each emergency material depot (including resource number, resource quantity, emergency material depot address information, transportation speed, etc.), selects the corresponding emergency material depot and resources, and allocates vehicles for delivery.

[0050] The present invention constructs a mathematical model with the goal of minimizing rescue time, combines the location-based mapping method and heap sorting to solve the diversity reduction and local optimality problems of the particle swarm algorithm. The greedy heuristic and PSO algorithm are used to find the optimal or approximately optimal resource scheduling solution, and the solution can be dynamically adjusted according to the on-site situation.

[0051] In one embodiment of the present invention, an improved particle swarm algorithm is proposed to optimize the dispatching of emergency resources for gas explosion accidents. The flowchart is as follows: Figure 1 As shown, the whole method includes the following steps:

[0052] Construct an emergency resource dispatch model for gas explosion areas, establish an objective function to minimize rescue time, and set constraints;

[0053] Initialize the model particle swarm parameters and use a position-based mapping method to map each particle to a valid task sequence, thereby forming an initial population representing the rescue plan;

[0054] The greedy heuristic algorithm combined with the improved particle swarm algorithm is used to solve the emergency resource scheduling model in the gas explosion area. The greedy heuristic algorithm obtains the local optimal solution of the objective function through iterative search, and the improved particle swarm algorithm finds the global optimal particle through algorithm iteration, and finally obtains the best rescue plan and the corresponding target value.

[0055] The specific steps of the gas explosion accident emergency resource scheduling optimization method based on the improved particle swarm algorithm of the present invention are as follows:

[0056] Step 1: Construct an emergency resource dispatch model for the gas explosion area, establish an objective function to minimize the rescue time, and set constraints.

[0057] Step 2: Initialize the parameters and use the position-based mapping method to map each particle to a valid task sequence, thereby forming an initial population representing the rescue plan, and on this basis, find the initial optimal rescue plan.

[0058] Step 2.1: Using the particle swarm optimization algorithm, randomly initialize all particles in the particle swarm (the population size is n), and each particle represents a possible emergency resource scheduling solution. And initialize the random position and speed, maximum position, minimum position, maximum speed, minimum speed, maximum number of iterations, etc.;

[0059] Step 2.2: To evaluate the fitness of each particle, map the position information of each particle into an effective rescue plan, which requires an initial optimal rescue plan.

[0060] Step 2.3: Use the heap sort strategy to generate an initial rescue plan as the initial value of the current best solution.

[0061] Step 3: Apply the greedy heuristic algorithm to solve the mathematical model, and obtain the local optimal solution of the objective function through iterative search to provide a reference for subsequent optimization.

[0062] Step 4: Use the improved particle swarm algorithm to solve the scheduling problem, find the global optimal particle through algorithm iteration, and then obtain the best rescue plan and the corresponding target value, and dynamically adjust the plan according to the on-site situation.

[0063] Step 4.1: Determine the global optimal solution search conditions for each particle and update the global best particle;

[0064] Step 4.2: Dynamically adjust particle speed and position;

[0065] Step 4.3: For each particle, determine the local optimal solution search conditions and update the personal best particle;

[0066] Step 4.4: For each particle, determine the global optimal solution search conditions and update the current best rescue plan, target value and global best particle.

[0067] In another embodiment, the present invention proposes a gas explosion accident emergency resource scheduling optimization system based on an improved particle swarm algorithm, comprising:

[0068] The model building module is used to build an emergency resource dispatch model for gas explosion areas, establish an objective function with the goal of minimizing rescue time, and set constraints; initialize the model particle swarm parameters, use a position-based mapping method, map each particle to a valid task sequence, and thus form an initial population representing the rescue plan;

[0069] The model solving module is used to apply the greedy heuristic algorithm combined with the improved particle swarm algorithm to solve the emergency resource scheduling model in the gas explosion area. The greedy heuristic algorithm obtains the local optimal solution of the objective function through iterative search, and the improved particle swarm algorithm finds the global optimal particles through algorithm iteration, and finally obtains the best rescue plan and the corresponding target value.

[0070] In another embodiment of the present invention, an electronic device is proposed, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the improved particle swarm algorithm-based method for optimizing emergency resource scheduling for gas explosion accidents as described above is implemented.

[0071] In another embodiment of the present invention, a computer-readable storage medium is provided, which stores a computer program, wherein the computer program enables a computer to execute the above-mentioned improved particle swarm algorithm method for optimizing emergency resource scheduling for gas explosion accidents.

[0072] The following combination Figure 2 The technical solution of the present invention is further described in detail with specific implementation modes:

[0073] 1. Problem description and modeling

[0074] There are n independent tasks at the accident site that require m emergency resources to support. The order of the tasks is represented by a task sequence ζ = (ζ1, ζ2, …ζ n ). Assume that the task arrangement includes all scheduled n tasks without duplication.

[0075] Task allocation: Let the decision variable x ij Represents the distribution relationship between tasks and emergency resources. i Allocate emergency resourcesj (j=1,2,…m), x ij =1; otherwise x ij = 0, the allocation relationship of emergency resources y = {j|x ij =1,j=1,2,…m}.

[0076] Path planning: Let the decision variable h jl Indicates emergency resources j Transport to mission i The path relationship is to use the path p l Indicates that if this path is selected, h jl =1; otherwise h jl = 0, and the corresponding path planning strategy is z = {l|h jl =1,l=1,2,…k}.

[0077] Time calculation: Let the decision variable t ij Indicates emergency resources j Transport from the emergency material warehouse to the mission point i rescue time.

[0078] If the task i Allocated to emergency resources j The time taken is T ijl The present invention models the problem by using an objective function that minimizes the rescue time:

[0079]

[0080] 2. Algorithm Design

[0081] The present invention designs a novel particle swarm optimization algorithm, aiming to improve the efficiency and accuracy of emergency response; the algorithm adopts a position-based mapping method to map each particle in the particle swarm to the corresponding rescue plan, ensuring the correspondence between the particle position and the rescue plan; at the same time, by using a greedy heuristic algorithm, the algorithm can calculate the target value of the rescue plan generated in the mapping process, thereby providing a basis for particle updating; through these innovations, the improved particle swarm algorithm designed by the present invention has important application value in the field of emergency material dispatching, can effectively respond to emergency situations, and improve rescue efficiency.

[0082] Each task arrangement is considered as a rescue solution in the scheduling optimization algorithm designed by the present invention; an effective task arrangement should include all scheduled n tasks without duplication; suppose there is a group ψ particles composed of all |ψ|, each particle ψ t (t=1,2,…,|ψ|) and position p t and speed v t are associated, and can be represented as n-dimensional tuples and Furthermore, the position of the personal best particle is given by The position of the global best particle tracked by the group is represented by In order to avoid excessive roaming of particles outside the search space, the present invention limits and In the interval [p min ,p max ] and [v min ,v max ]Inside.

[0083] In the PSO framework, particles move toward the personal best particle and the global best particle through the traditional particle update strategy. During each iteration, the velocity and position updates of the particles can be expressed as:

[0084]

[0085] ω represents the inertia weight, c1 and c2 represent the individual cognitive component and social communication component respectively; r1 and r2 are two uniformly distributed numbers in [0,1]; the particle's speed in the i-th dimension is Mainly depends on and The value of .

[0086] 2.1 Location-based mapping method

[0087] PSO randomly initializes all particles in the group; in order to evaluate the fitness of particles, each particle is mapped to an effective rescue plan; the present invention solves the problem of reduced diversity and local optimality of particle swarm algorithm by using a location-based mapping method, maps particles to an effective emergency resource scheduling plan, and generates the initial optimal rescue plan (based on the time required for all tasks T ijl In the evolution process, the particle positions are analyzed to calculate the probability of task replication, inherit good scheduling patterns, and improve the quality of the solution; the algorithm iteratively optimizes the rescue plan, maintains diversity, avoids local optimality, and schedules resources quickly and efficiently to minimize the rescue time.

[0088] Assume that the current best rescue plan is ζ * It means that for each particle ψ t (t=1,2,…,ψ), the mapping method used is to solve ζ from the empty t starts with and makes it a complete solution through a two-stage procedure.

[0089] In the first stage, * Each task in Attach to t In, we have: When ρ∈(0,1) is true; therefore, the limit position minimum p min > 0; copy of the current best rescue plan Eliminate all these additional tasks in order to avoid * destruction, which is used to generate a corresponding rescue plan for each particle.

[0090] In the second stage, Each of the remaining tasks in is inserted into ζ in a uniformly distributed manner t In The probability of each task being located at each position in is 1 / |ζ t |; Therefore, ζ t Becoming a complete task arrangement is the final result of the mapping method; Algorithm 1 is the complete process of the position-based mapping method, where lines 2-6 represent the first stage and lines 7-8 represent the second stage.

[0091] Table 1 Algorithm 1 Calculation process

[0092]

[0093]

[0094] According to the previous analysis, the inheritance of good patterns by generating rescue solutions mainly occurs in the first stage, because the additional tasks in the mapping rescue solution follow their relative order in the current best rescue solution. In order to inherit good patterns more effectively, the present invention provides any particle ψ t set up This allows appending more than half of the tasks to the map-rescue scheme without changing their relative order.

[0095] 2.2 Greedy Heuristic

[0096] In order to calculate the target value obj of the rescue solution generated in the previous mapping process, the present invention uses a greedy heuristic algorithm, in which the accident points of a given rescue solution are assigned to each emergency material depot one by one in a greedy manner, and the task is completed when the target is finally obtained. t Tasks in By placing the accident point Allocated to emergency supply depots j The index y of the allocated emergency resource can be expressed as

[0097]

[0098] Algorithm 2 gives the complete algorithm process:

[0099] Table 2 Algorithm 2 calculation process

[0100]

[0101]

[0102] 2.3 New Particle Swarm Optimization Algorithm

[0103] The improved particle swarm algorithm used in the present invention starts with a parameter initialization process (line 1), where MG represents the maximum number of iterations; all particles in the particle swarm are randomly generated (line 2), and each particle is regarded as its personal best particle (line 3); the improved particle swarm algorithm uses heap sorting to initialize the current best solution ζ * (Line 4), whose target value can be calculated by the greedy heuristic used (Line 5); all particles are evaluated through the iterative process described in Lines 6-15, where the global best particle is initialized; the evolution process is shown in Lines 16-28, where each particle is mapped to the corresponding rescue solution (Line 18), and ζ is calculated by the greedy heuristic t The target value of (line 19); in this process, if a better particle is found, the personal best particle is updated (line 20); if a new and better rescue plan is found (line 21), the current best rescue plan, target value and global best particle are updated accordingly (lines 22-24). Algorithm 3 gives the complete algorithm process.

[0104] Table 3 Algorithm 3 calculation process

[0105]

[0106]

[0107] 2.4 Algorithm Complexity

[0108] In emergency dispatch, real-time response capability is very important, and the computation time and complexity of the algorithm may affect its response speed to emergencies;

[0109] The computational complexity of all operators and algorithms of the present invention is as follows: the complexity of heap sort is O(n·logn); the mapping method described in Algorithm 1 has a linear complexity of O(n), and as the experimental results show, the designed algorithm achieves good computational efficiency by adopting this low-complexity mapping operator; the complexity of the greedy heuristic in Algorithm 2 is O(m·n); the complexity of the improved particle swarm algorithm in Algorithm 3 is O(MG·ψ|·mn 2 ), where MG and ψ| represent the maximum number of iterations and the group size, respectively.

[0111] Taking the emergency command and dispatch system as an example, by constructing a mathematical model with the goal of minimizing the rescue time and integrating the improved particle swarm algorithm, it was found that the optimal recommended scheduling scheme has great practical application in practical applications during the dispatch process. Specifically, the algorithm was used for modeling, which successfully reduced the decision-making time of the command center and improved the rescue efficiency.

[0112] Two examples are provided below to further illustrate:

[0113] 3.1 Example 1

[0114] (1) System construction

[0115] Design an emergency command and dispatch system, including modules such as event reporting, emergency resources, dispatch decision-making, task allocation, execution records, and post-disaster assessment.

[0116] Construct a mathematical model with the goal of minimizing rescue time, including rescue resource constraints, rescue mission requirements, and rescue path optimization.

[0117] (2) Algorithm Implementation

[0118] The improved particle swarm algorithm is used to solve the mathematical model. The particles represent a rescue dispatch scheme, and the optimal solution is found through iteration.

[0119] (3) Implementation process

[0120] When a rescue mission is received, the system automatically extracts relevant data and inputs it into the mathematical model.

[0121] The model is solved by improving the particle swarm algorithm to obtain the optimal recommended scheduling solution.

[0122] The scheduling plan is output to the command center for reference by decision makers.

[0123] (4) Implementation results

[0124] Through practical application, it is found that the rescue dispatching scheme using the optimization method of this embodiment has great practicality in actual operation.

[0125] Compared with the traditional dispatching method, this embodiment successfully reduces the decision-making time of the command center and improves the rescue efficiency.

[0126] 3.2 Example 2

[0127] (1) System construction

[0128] On the basis of Example 1, the emergency resources are expanded to add more types and quantities of emergency resources.

[0129] (2) Algorithm Implementation

[0130] For the improved particle swarm algorithm, a dynamic adjustment strategy is introduced to adapt to different types of rescue tasks.

[0131] (3) Implementation process

[0132] For specific types of rescue missions, the system automatically adjusts the algorithm parameters to obtain a better scheduling solution.

[0133] (4) Implementation results

[0134] By improving the particle swarm algorithm, the global optimal rescue plan and the local optimal rescue plan are continuously updated, and the plan can be dynamically adjusted according to the situation at the accident site.

[0135] This embodiment further improves the practicability of the rescue dispatching scheme in practical applications. Compared with Embodiment 1, this embodiment reduces the rescue time by an average of 15% and improves the timely rescue rate by 10% in complex rescue scenarios.

[0136] These two embodiments successfully optimize the emergency command and dispatch system by constructing a mathematical model that minimizes the rescue time and integrating the improved particle swarm algorithm. In practical applications, the present invention has the following advantages:

[0137] It has greatly reduced the decision-making time of the command center and improved rescue efficiency; optimized the allocation of rescue resources and reduced rescue costs; and increased the rescue success rate, providing strong support for my country's emergency command and dispatch field.

[0138] In the embodiments disclosed in the present application, the computer storage medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. The computer storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the above. More specific examples of computer storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above.

[0139] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Any technician familiar with the profession, without departing from the scope of the technical solution of the present invention, according to the technical essence of the present invention, any simple modification, equivalent replacement and improvement made to the above embodiment still falls within the protection scope of the technical solution of the present invention.

Claims

1. An optimization method for emergency resource scheduling of gas explosion accidents based on an improved particle swarm algorithm, characterized in that: The following steps are involved: Construct an emergency resource dispatch model for gas explosion areas, establish an objective function to minimize rescue time, and set constraints; Initialize the model particle swarm parameters and use a position-based mapping method to map each particle to a valid task sequence, thereby forming an initial population representing the rescue plan; The greedy heuristic algorithm combined with the improved particle swarm algorithm is used to solve the emergency resource scheduling model in the gas explosion area. The greedy heuristic algorithm obtains the local optimal solution of the objective function through iterative search, and the improved particle swarm algorithm finds the global optimal particle through algorithm iteration, and finally obtains the best rescue plan and the corresponding target value.

2. The gas explosion accident emergency resource scheduling optimization method based on the improved particle swarm algorithm according to claim 1 is characterized by: The parameter initialization described above uses a position-based mapping method to map each particle to a valid task sequence, thereby forming an initial population representing a rescue solution, including: Using the particle swarm optimization algorithm, all particles in the particle swarm are randomly initialized so that each particle represents a possible emergency resource scheduling solution, and the random position and speed, maximum position, minimum position, maximum speed, minimum speed, and maximum number of iterations are initialized; Map the position information of each particle into an effective rescue plan; The heap sorting strategy is used to generate the initial rescue plan as the initial value of the current best solution.

3. The gas explosion accident emergency resource scheduling optimization method based on improved particle swarm algorithm according to claim 2 is characterized by: Suppose there is a group ψ particles consisting of all |ψ|, each particle ψ t (t=1,2,…,|ψ|) and position p t and speed v t are associated, represented as n-dimensional tuples and The position of the personal best particle is given by express; The position of the global best particle for swarm tracking is given by Representation; Restriction and In the interval [p min ,p max ] and [v min ,v max ]Inside; In the PSO framework, particles move toward the personal best particle and the global best particle through the traditional particle update strategy; During each iteration, the particle's velocity and position are updated as: Among them, ω represents the inertia weight, c1 and c2 represent the individual cognitive component and social communication component respectively; r1 and r2 are two uniformly distributed numbers in [0,1]; the particle's motion speed in the i-th dimension is Mainly depends on and The value of .

4. The gas explosion accident emergency resource scheduling optimization method based on the improved particle swarm algorithm according to claim 3 is characterized by: Assume that the current best rescue plan is ζ * It means that for each particle ψ t (t=1,2,…,ψ), the mapping method used is to solve ζ from the empty t Start with and make it a complete solution through a two-stage procedure; In the first stage, * Each task in Attach to t In, we have: When ρ∈(0,1) is true, the position minimum p is restricted min > 0; copy of the current best rescue plan Eliminate all these additional tasks in order to avoid * The destruction is used to generate a corresponding rescue plan for each particle; In the second stage, Each of the remaining tasks in is inserted into ζ in a uniformly distributed manner t In The probability of each task being located at each position in is 1 / |ζ t |,ζ t Becoming a complete task arrangement is the final result of the mapping method.

5. The gas explosion accident emergency resource scheduling optimization method based on improved particle swarm algorithm according to claim 1 is characterized by: The greedy heuristic algorithm is used to solve the emergency resource scheduling model in the gas explosion area, and the local optimal solution of the objective function is obtained through iterative search. The process is as follows: In order to calculate the target value obj of the rescue plan generated in the previous mapping process, a greedy heuristic algorithm is used. The accident points of a given rescue plan are assigned to each emergency material depot one by one in a greedy manner. When the target is finally obtained, the task is completed; For a specific solution t Tasks in Task target value By placing the accident point Allocated to emergency supply depots j To represent, the index y of the allocated emergency resource is expressed as:

6. The gas explosion accident emergency resource scheduling optimization method based on improved particle swarm algorithm according to claim 1 is characterized by: The improved particle swarm algorithm is applied to find the global optimal particle through algorithm iteration, including: Determine the global optimal solution search conditions for each particle and update the global best particle; Dynamically adjust particle speed and position; For each particle, determine the local optimal solution search conditions and update the personal best particle; For each particle, the global optimal solution search condition is judged, and the current best rescue plan, target value and global best particle are updated.

7. The gas explosion accident emergency resource scheduling optimization method based on improved particle swarm algorithm according to claim 6 is characterized by: The improved particle swarm algorithm starts with the parameter initialization process. The particles in the particle swarm are randomly generated, and each particle is regarded as its personal best particle. The current best solution is initialized using heap sorting. * , whose target value is calculated by a greedy heuristic algorithm, and all particles are evaluated through an iterative process, in which the global best particle is initialized and each particle is mapped to the corresponding rescue solution; in this process, if a better particle is found, the personal best particle is updated; if a new and better rescue solution is found, the current best rescue solution, target value and global best particle are updated accordingly.

8. An improved particle swarm algorithm for optimizing emergency resource scheduling in gas explosion accidents, characterized in that: include: The model building module is used to build an emergency resource dispatch model for gas explosion areas, establish an objective function with the goal of minimizing rescue time, and set constraints; initialize the model particle swarm parameters, use a position-based mapping method, map each particle to a valid task sequence, and thus form an initial population representing the rescue plan; The model solving module is used to apply the greedy heuristic algorithm combined with the improved particle swarm algorithm to solve the emergency resource scheduling model in the gas explosion area. The greedy heuristic algorithm obtains the local optimal solution of the objective function through iterative search, and the improved particle swarm algorithm finds the global optimal particles through algorithm iteration, and finally obtains the best rescue plan and the corresponding target value. The system is used to execute the gas explosion accident emergency resource scheduling optimization method based on the improved particle swarm algorithm as described in any one of claims 1 to 7.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method for optimizing emergency resource scheduling for gas explosion accidents based on the improved particle swarm algorithm as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, wherein the computer program enables a computer to execute the method for optimizing emergency resource scheduling for gas explosion accidents based on an improved particle swarm algorithm according to any one of claims 1 to 7.

Images