Railway construction optimization method and system based on improved grey wolf algorithm

Abstract

The application discloses a railway construction optimization method and system based on an improved grey wolf algorithm, and the method comprises the following steps: constructing a railway construction model according to the time required by each process, the cost required by each process, the quality coefficient of each process and the safety coefficient of each process, wherein the model parameters in the railway construction model comprise the time required by a project, the cost required by the project, the quality coefficient of the project and the safety coefficient of the project; and the railway construction model is solved according to the improved grey wolf algorithm, so that the project process duration is obtained. The railway infrastructure construction model can be simplified, the railway infrastructure project construction management efficiency is improved, and the decision maker can better formulate a construction scheme.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of construction project management, and particularly relates to a railway construction optimization method and system based on an improved grey wolf algorithm. BACKGROUND

[0002] The railway construction optimization method involves the combination of intelligent technology and construction management methods, and is mainly used to improve construction efficiency, reduce resource waste, reduce costs, ensure engineering quality, and provide protection in terms of safety and environmental protection. Railway infrastructure construction usually involves complex engineering tasks, such as track construction, bridge and tunnel construction, road and electrification engineering, etc. Traditional construction organization design methods rely on manual planning and experience-based judgment, which may have the following problems: (1) delay in construction period: due to the inability to accurately predict various variables in the construction process, the construction period often cannot be completed as planned; (2) resource waste: due to the lack of accurate resource scheduling and demand forecasting, there may be problems such as idle equipment and material waste; (3) safety hazards: in the traditional construction process, real-time monitoring of safety management and construction process is often insufficient, resulting in many safety hazards; (4) difficulty in quality control: in the construction process, quality may be affected by human factors or inappropriate construction technology. SUMMARY

[0003] The application provides a railway construction optimization method and system based on an improved grey wolf algorithm, which is used to solve the technical problem of different synchronization of quality, safety, construction period and cost management in railway engineering construction projects.

[0004] In a first aspect, the application provides a railway construction optimization method based on an improved grey wolf algorithm, comprising:

[0005] A railway construction model is constructed according to the time required for each process, the cost required for each process, the quality coefficient of each process and the safety coefficient of each process, wherein the model parameters in the railway construction model include the time required for the project , the cost required for the project , the quality coefficient of the project and the safety coefficient of the project ;

[0006] The railway construction model is solved according to the improved grey wolf algorithm to obtain the project process construction period, wherein the solving of the railway construction model according to the improved grey wolf algorithm is specifically as follows:

[0007] The time required for the project , the cost required for the project , the quality coefficient of the project and the safety coefficient of the project Defined as the position of the gray wolf, i.e., the sequence of work processes and durations in the coded project;

[0008] Based on the location of individual gray wolves, multiple groups of different gray wolf individuals are generated according to the non-uniform sampling adaptive population initialization strategy;

[0009] Calculate the individual information of each gray wolf, namely the time required for the specific process of the project, the cost required for the process, the quality coefficient of the process, and the safety coefficient of the process, filter out the process of the target project, and classify the corresponding gray wolf information into the elite archive;

[0010] Based on the improved hunting mechanism using a random heuristic jumping strategy, update the individual information of gray wolves outside the elite archive;

[0011] In the elite archive, multiple gray wolf information is used to find the alpha wolf's position based on the multi-scale collaborative mutation operator, and it is determined whether the maximum number of iterations has been reached;

[0012] If the maximum number of iterations is reached, the alpha wolf's position information is decoded to obtain the project process duration with the shortest construction period, lowest cost, and best quality and safety.

[0013] If the maximum number of iterations has not been reached, the position of the gray wolf outside the elite archive will be updated again, and the position of the alpha wolf will be filtered in the elite archive until the maximum number of iterations is reached.

[0014] Secondly, this invention provides a railway construction optimization system based on an improved gray wolf algorithm, comprising:

[0015] The construction module is configured to build a railway construction model based on the time required for each process, the cost required for each process, the quality coefficient for each process, and the safety coefficient for each process. The model parameters in the railway construction model include the project's required time. Project cost Project quality coefficient and project safety factor ;

[0016] The solution module is configured to solve the railway construction model using the improved Grey Wolf algorithm to obtain the project's work sequence duration. Specifically, solving the railway construction model using the improved Grey Wolf algorithm involves:

[0017] The time required for the project Project cost Project quality coefficient and project safety factor Defined as the position of the gray wolf, i.e., the sequence of work processes and durations in the coded project;

[0018] Based on the location of individual gray wolves, multiple groups of different gray wolf individuals are generated according to the non-uniform sampling adaptive population initialization strategy;

[0019] Calculate the information of each gray wolf individual, that is, the time required for the specific process of the project, the cost required for the process, the process quality coefficient and the process safety coefficient, screen out the target project process, and classify the corresponding gray wolf information into the elite archive;

[0020] According to the improved hunting mechanism of the random heuristic jump strategy, the information of the gray wolf individual outside the elite archive is updated;

[0021] In the elite archive, multiple gray wolf information finds the position of the head wolf according to the multi-scale cooperative mutation operator, and judges whether the maximum iteration number is reached;

[0022] If the maximum iteration number is reached, the position information of the head wolf is decoded to obtain the project process duration with the minimum duration, the lowest cost and the best quality and safety;

[0023] If the maximum iteration number is not reached, the position of the gray wolf outside the elite archive is updated, and the position of the head wolf is screened in the elite archive until the maximum iteration number is reached.

[0024] In a third aspect, an electronic device is provided, comprising at least one processor, and a memory connected in communication with the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the steps of the railway construction optimization method based on the improved gray wolf algorithm of any embodiment of the present application.

[0025] In a fourth aspect, the present application also provides a computer readable storage medium having a computer program stored thereon, and the program instructions are executed by a processor to enable the processor to perform the steps of the railway construction optimization method based on the improved gray wolf algorithm of any embodiment of the present application.

[0026] The railway construction optimization method and system based on the improved gray wolf algorithm of the present application can simplify the railway infrastructure construction model and improve the efficiency of railway infrastructure project construction management by constructing a railway construction model according to the time required for each process, the cost required for each process, the quality coefficient of each process and the safety coefficient of each process, and help decision makers to better develop construction schemes. BRIEF DESCRIPTION OF DRAWINGS

[0027] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed in the embodiment description. Obviously, the drawings in the following description are some embodiments of the present application, and those skilled in the art can also obtain other drawings according to these drawings without creative labor.

[0028] Figure 1A flow chart of a railway construction optimization method based on an improved grey wolf algorithm is provided for an embodiment of the present application.

[0029] Figure 2 An improved algorithm convergence curve result graph of a specific embodiment is provided for an embodiment of the present application.

[0030] Figure 3 A structural block diagram of a railway construction optimization system based on an improved grey wolf algorithm is provided for an embodiment of the present application.

[0031] Figure 4 A structural schematic diagram of an electronic device is provided for an embodiment of the present application. DETAILED DESCRIPTION

[0032] To make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described below in conjunction with the accompanying drawings of the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0033] Please refer to Figure 1 , which shows a flow chart of a railway construction optimization method based on an improved grey wolf algorithm.

[0034] As shown in Figure 1 , the railway construction optimization method based on the improved grey wolf algorithm specifically includes the following steps:

[0035] Step S101, constructing a railway construction model according to required time of each process, required cost of each process, quality coefficient of each process and safety coefficient of each process, wherein model parameters in the railway construction model include required time of the project , required cost of the project , quality coefficient of the project and safety coefficient of the project .

[0036] In this step, the expression of the railway construction model is:

[0037] ,

[0038] In the formula, is a project process function, is required time of the project, is required time of the process, is all processes on the critical line, is required cost of the project, Cost for the process, Quality coefficient of the project, Quality coefficient of the process, Safety coefficient of the project, Quality coefficient of the process, Delay days, Delay penalty cost coefficient, Delay penalty quality coefficient, Delay penalty safety coefficient.

[0039] In one specific embodiment, a certain railway track project is taken as the object, the project engineering total length is 121.625km, the main line lays 242.29km of ballastless track, the station line lays 4.96km of ballastless track, 5.74km of ballast track, 41 groups of switches are laid, 12215.68m3 of ballast is laid, in the actual engineering of railway engineering construction management, the railway construction model is constructed, the railway construction process is optimized through systematic and digital means, the construction efficiency is improved, the cost is controlled, the risk is reduced, and a scientific basis is provided for decision-making, considering the construction period, cost quality and safety and other factors, so as to guarantee the efficient construction of the railway track project.

[0040] Step S102, solving the railway construction model according to the improved grey wolf algorithm to obtain the project process period.

[0041] In this step, the railway construction model is solved according to the improved grey wolf algorithm, specifically:

[0042] The time required by the project , the cost required by the project , the quality coefficient of the project and the safety coefficient of the project are defined as the position of the grey wolf, that is, the coded project process period sequence.

[0043] In this embodiment, the parameters of a certain railway track project required by the railway construction model are input, such as process period, cost, quality level and safety level; at the same time, the project stipulates that the longest period does not exceed 135 days, the project cost does not exceed 42 million yuan, the quality coefficient is not less than 0.85, and the safety coefficient is not less than 0.85; the optimization result of the algorithm needs to be within the project indicators, otherwise it is considered as invalid result.

[0044] For the position of the grey wolf individual, a plurality of different grey wolf individuals are generated according to the non-uniform sampling adaptive population initialization strategy.

[0045] In the embodiment, some railway track engineering project parameters required for inputting a railway construction model, such as process duration, cost, quality level and safety level, are inputted; meanwhile, the project stipulates that the longest duration is not more than 135 days, the project cost is not more than 42 million yuan, the quality coefficient is not less than 0.85, and the safety coefficient is not less than 0.85; the optimization result of the algorithm needs to be within the project indicators, otherwise it is regarded as an invalid result; the position of the grey wolf is defined, that is, the time required by the model , the cost required by the project , the quality coefficient of the project and the safety coefficient of the project .

[0046] Initialize the population, and the quality of the initial population will affect the performance of the algorithm to some extent. If only a random generation method is used, it is difficult to obtain a high-quality initial solution. The non-uniform sampling adaptive population initialization strategy is combined to improve the probability of generating high-quality grey wolf individuals. By purposefully allocating a higher sampling probability in the high-potential area of the solution space, and combining a dynamic adjustment mechanism, the quality and diversity of the initial population can be significantly improved, the algorithm convergence can be accelerated, and the invalid search can be reduced.

[0047] The initial population with a size of M is generated as follows:

[0048] ,

[0049] In the formula, is the position of the i-th grey wolf; The four kinds of grey wolves (in the initialized population individuals) are used to simulate the leadership level, in which

[0050] the position of the wolf is the best position of the whole wolf group, that is, the optimal solution, the positions of the wolf and the wolf are the second optimal solution and the third optimal solution, respectively, the fitness values of the grey wolf individuals are sorted, and the top three grey wolf individuals are recorded as , and the corresponding position information is . Specifically, the expression of the non-uniform sampling adaptive population initialization strategy is as follows:

[0051]

[0052] ,

[0053] ,

[0054] In the formula, is a random individual, is an adaptive step size, is the first candidate point, is a weighted index, and ​​​is an average fitness, is a second candidate point, is a perturbation factor, is a random mapping value, is a fourth type distribution correction factor, is a selection intensity parameter, is a small perturbation term, is a local density.

[0055] It should be noted that: when the grey wolf algorithm initializes the population, firstly, an adaptive step size is constructed , the average fitness is considered to reflect the population fitness level, the candidate point is introduced, the sampling direction is guided, the norm of the perturbation factor and the random mapping value is used to shape the non-uniform characteristics, and then the weighted exponential is integrated; on this basis, in order to generate a random individual , the fourth type distribution correction factor is introduced to adjust the distribution, the selection intensity parameter is used to strengthen the selection characteristics, the small perturbation term is used to increase the population diversity, and the local density is used to constrain the individual distribution; through the exponential operation and the proportional relationship, the following equation is derived , so as to realize the adaptive initialization of the random individual according to the population state, and balance the exploration and development ability.

[0056] The information of each grey wolf individual, i.e. the time required by the specific process of the project, the cost required by the process, the process quality coefficient and the process safety coefficient, is calculated, the target project process is screened, and the corresponding grey wolf information is classified into the elite archive.

[0057] According to the improved hunting mechanism of the random heuristic jumping strategy, the grey wolf individual information outside the elite archive is updated.

[0058] In this embodiment, when the wolf pack is hunting wolves, wolves, wolves command wolves to attack the prey, and the grey wolves surround the prey and continuously shorten the distance between the prey during the hunting process. The behavior of shortening the distance between the prey is mathematically modeled, and the expression is as follows:

[0059] ,

[0060] ,

[0061] ,

[0062] In the formula, is the current iteration number, , are coefficient vectors, is the prey position, is the distance vector of the wolf pack movement, is the distance vector of the wolf pack individual and the prey, is the convergence factor, linearly reduced from 2 to 0, , are random vectors;

[0063] Because the grey wolf algorithm relies too much on , , Three-headed leaders guide the search direction, if these leaders gather in a suboptimal area too early, the whole population will be quickly pulled to that position, resulting in the loss of the algorithm's exploration ability. To avoid the algorithm falling into local optimum, a random jump is used to jump out of the local optimum, and the search direction is improved with the help of heuristic rules, so as to perform well in global optimization, dynamic environment adaptation and calculation efficiency, and to enhance the robustness and reduce the sensitivity to initial conditions. A random heuristic jump strategy is proposed. For the leader, according to the probability of 50%, the random heuristic jump strategy or the hunting mechanism of moving according to the original way is used for optimization, and the information of the grey wolf individual outside the updated elite archive is obtained. The expression of the hunting mechanism is:

[0064] ,

[0065] ,

[0066] ,

[0067] ,

[0068] ,

[0069] ,

[0070] In the formula, , , are the distance vectors of the prey and wolf, wolf, wolf, , , are constant vectors, , , They are respectively Wolf, Wolf, The vector of the wolf's location. This indicates the current position of the individual gray wolf. , , These are the positions of the first, second, and third gray wolves, respectively. To control the weight of the step size, For heuristic functions, A random number in the range [0,1]. , , Prey and Wolf, Wolf, Wolf-based hierarchical adaptive step size For density-driven disturbance regulators, To inspire the balance factor, This represents the actual percentage. To allow for a certain percentage, Territory boundaries For collision frequency, To mark the intensity, For the risk of conflict, For resource density coefficient, For sensitive values, This is the distance vector of the wolf pack's movement.

[0071] It should be noted that, in order to simulate the hunting behavior of gray wolf packs to solve the optimization problem, a gray wolf optimization model is constructed; firstly, the prey and... Wolf, Wolf, Wolf distance vector , , ,based on Wolf, Wolf, Wolf position vector , , Current location of the individual gray wolf and constant vector , , Calculate distance , , Secondly, consider random numbers. (Range [0,1]) Control strategy branch, combined with adaptive step size , , Controlling step size weights With heuristic functions ,right Wolf, Wolf, The wolf-guided gray wolf's position is updated when... When the value is ≥0.5, the position of the first gray wolf is The second gray wolf's position is The third gray wolf's position is ;when When <0.5, the position of the first gray wolf is The second gray wolf's position is The third gray wolf's position is To achieve a balance between exploration and development; then, construct heuristic functions. Integrate actual proportion With the permitted proportion Deviation, introducing territorial boundaries Conflict frequency Environmental constraints, using heuristic balance factors Density-driven disturbance regulator Finally, the location information of the three types of wolves is integrated, and practical application limitations are introduced. The algorithm calculates the wolf pack's position at the next moment, simulates group cooperation, and gradually approaches the optimization target, forming an intelligent optimization search mechanism adapted to constrained fields.

[0072] In the elite archive, multiple gray wolf information is used to find the alpha wolf's position based on the multi-scale collaborative mutation operator, and it is determined whether the maximum number of iterations has been reached.

[0073] In this embodiment, the traditional Grey Wolf algorithm lacks mutation and random perturbation, leading to a lack of population diversity in the later stages of evolution. To overcome this deficiency, a multi-scale cooperative mutation operator is proposed to dynamically adjust population mutation based on the advantages of mutation weights at different search orders, thereby increasing the algorithm's population diversity. This aims to maintain a balance between population diversity and algorithm convergence during evolution, effectively improving the algorithm's ability to escape local optima and preventing premature convergence. The expression for the multi-scale cooperative mutation operator is:

[0074] ,

[0075] ,

[0076] In the formula, for The wolf uses its mutated position, which is the globally optimal solution. for The wolf's location before the mutation. For variation weights, for random distribution at time, To adjust the parameters, the value range is [30, 100]. This represents the current iteration number. The maximum number of iterations, For mutually exclusive activity, For the exclusion position, For mutually exclusive gradients, These are mutually exclusive adjustment parameters. For attractiveness.

[0077] It should be noted that: in order to optimize the gray wolf optimization algorithm Based on the wolf's search capabilities, a multi-scale collaborative mutation mechanism was designed to update its location: Wolf's location before mutation Based on this, mutation weights are introduced. and random distribution of time Construct the mutated position Mutation weights Integrating iterative information with ecological behavior constraints, based on the number of iterations Maximum number of iterations Adjust parameters Constructing the exponential decay term Reflecting the impact of the iteration process, and then through mutual exclusion activity. Rejection site Mutual Exclusive Gradients Mutual exclusion adjustment parameters Build Simulate population mutual exclusion-attraction constraints, and divide the two to obtain ,make Wolf positions dynamically vary based on multi-scale information, balancing algorithm exploration and development capabilities to form a complete system. The derivation logic of wolf position variation;

[0078] If the maximum number of iterations is reached, the alpha wolf's position information is decoded to obtain the project process duration with the shortest construction period, lowest cost, and best quality and safety.

[0079] If the maximum number of iterations has not been reached, the position of the gray wolf outside the elite archive will be updated again, and the position of the alpha wolf will be filtered in the elite archive until the maximum number of iterations is reached.

[0080] In one specific embodiment, when the algorithm reaches the maximum number of iterations, the optimal grey wolf individual position is output, the algorithm ends, and the project process duration with the minimum duration, the lowest cost, the best quality and safety is obtained; the improved grey wolf algorithm obtains the result that the duration is 116 days, the cost is 3617.3 million yuan, the quality coefficient is 0.9608, and the safety coefficient is 0.9578, the result meets the project index, and the improved algorithm convergence curve is as shown in Figure 2 .

[0081] In summary, the method of the present application analyzes the influencing factors of railway construction duration, cost, quality and safety, establishes a railway construction model, then proposes a non-uniform sampling adaptive population initialization strategy to initialize the grey wolf population, secondly, based on the hunting mechanism improved by the random heuristic jump strategy, the position of the grey wolf individual is updated, finally, the multi-scale cooperative mutation operator is added to prevent the algorithm from converging too early, find the position of the head wolf, and obtain the project process duration with the minimum duration, the lowest cost, the best quality and safety. The railway infrastructure construction model can be simplified, the efficiency of railway infrastructure project construction management can be improved, and decision makers can better develop construction schemes.

[0082] Please refer to Figure 3 , which shows a structure block diagram of a railway construction optimization system based on an improved grey wolf algorithm.

[0083] As shown in Figure 3 , the railway construction optimization system 200 includes a construction module 210 and a solution module 220.

[0084] The construction module 210 is configured to construct a railway construction model according to the time required by each process, the cost required by each process, the quality coefficient of each process, and the safety coefficient of each process. The model parameters in the railway construction model include the time required by the project , the cost required by the project , the quality coefficient of the project , and the safety coefficient of the project ; the solution module 220 is configured to solve the railway construction model according to the improved grey wolf algorithm to obtain the project process duration, wherein solving the railway construction model according to the improved grey wolf algorithm is specifically: the time required by the project , the cost required by the project , the quality coefficient of the project , and the safety coefficient of the project The position of the gray wolf is defined as the position of the coded project process duration sequence; for the position of the gray wolf individual, a plurality of different gray wolf individuals are generated according to a non-uniform sampling adaptive population initialization strategy; the information of each gray wolf individual, i.e., the time required for the specific project process, the cost required for the process, the process quality coefficient and the process safety coefficient, is calculated, the target project process duration is screened out, and the corresponding gray wolf information is classified into the elite archive; the information of the gray wolf individuals outside the elite archive is updated according to a hunting mechanism improved according to a random heuristic jumping strategy; in the elite archive, the position of the alpha wolf is found according to a multi-scale cooperative mutation operator, and it is judged whether the maximum number of iterations is reached; if the maximum number of iterations is reached, the position information of the alpha wolf is decoded to obtain the project process duration with the minimum duration, the lowest cost and the best quality and safety; if the maximum number of iterations is not reached, the position of the gray wolf outside the elite archive is updated, and the position of the alpha wolf is screened in the elite archive until the maximum number of iterations is reached.

[0085] It should be understood that Figure 3 the modules described in the Figure 1 correspond to the respective steps in the method described with reference to Figure 3 . Thus, the operations and features described above for the method, as well as the corresponding technical effects, apply equally to the modules in , without being repeated here.

[0086] In some embodiments, the application also provides a computer readable storage medium having stored thereon a computer program, the program instructing a processor to execute the improved gray wolf algorithm-based railway construction optimization method in any of the method embodiments described above when the program is executed by the processor.

[0087] As an implementation form, the computer readable storage medium of the application stores computer executable instructions, which are configured to:

[0088] construct a railway construction model according to the time required for each process, the cost required for each process, the quality coefficient of each process and the safety coefficient of each process, wherein the model parameters in the railway construction model include the time required for the project , the cost required for the project , the quality coefficient of the project and the safety coefficient of the project ;

[0089] solve the railway construction model according to the improved gray wolf algorithm to obtain the project process duration, wherein solving the railway construction model according to the improved gray wolf algorithm specifically includes:

[0090] updating the time required for the project , the cost required for the project , the quality coefficient of the project and the safety coefficient of the project defined as the position of the gray wolf, that is, the coding project process duration sequence;

[0091] For the position of the gray wolf individual, a plurality of different gray wolf individuals are generated according to a non-uniform sampling adaptive population initialization strategy;

[0092] The information of each gray wolf individual, that is, the time required for the specific process of the project, the cost required for the process, the process quality coefficient and the process safety coefficient, is calculated, the target project process duration is screened out, and the corresponding gray wolf information is classified into the elite archive;

[0093] According to the improved hunting mechanism of the random heuristic jump strategy, the information of the gray wolf individuals outside the elite archive is updated;

[0094] In the elite archive, the information of multiple gray wolves is found according to the multi-scale cooperative mutation operator, and it is judged whether the maximum iteration number is reached;

[0095] If the maximum iteration number is reached, the information of the head wolf position is decoded to obtain the project process duration with the minimum duration, the lowest cost and the best quality and safety;

[0096] If the maximum iteration number is not reached, the position of the gray wolf outside the elite archive is updated, and the position of the head wolf is screened in the elite archive until the maximum iteration number is reached.

[0097] The computer readable storage medium can include a program storage area and a data storage area, wherein the program storage area can store an operating system and at least one application required by a function; the data storage area can store data created according to the use of the railway construction optimization system based on the improved gray wolf algorithm and the like. In addition, the computer readable storage medium can include a high-speed random access memory, and can also include a memory such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state memory device. In some embodiments, the computer readable storage medium can optionally include a memory remotely arranged relative to the processor, and these remote memories can be connected to the railway construction optimization system based on the improved gray wolf algorithm through a network. Examples of the above network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network and a combination thereof.

[0098] Figure 4 is a structural schematic diagram of an electronic device provided by an embodiment of the application, as Figure 4 shown, the device includes a processor 310 and a memory 320. The electronic device can also include an input device 330 and an output device 340. The processor 310, the memory 320, the input device 330 and the output device 340 can be connected by a bus or other means, Figure 4The bus connection is taken as an example. The memory 320 is the computer readable storage medium described above. The processor 310 performs various function applications and data processing of the server by running the non-volatile software programs, instructions and modules stored in the memory 320, that is, implements the railway construction optimization method based on the improved grey wolf algorithm described above. The input device 330 can receive input digital or character information and generate key signal input related to user settings and function control of the railway construction optimization system based on the improved grey wolf algorithm. The output device 340 can include a display device such as a display screen.

[0099] The electronic device described above can execute the method provided by the embodiments of the present application, and has the corresponding function modules and beneficial effects of the execution method. Technical details not described in detail in the present embodiment can be referred to the method provided by the embodiments of the present application.

[0100] As an implementation manner, the electronic device described above is applied to the railway construction optimization system based on the improved grey wolf algorithm, and is used for a client, and includes: at least one processor; and a memory in communication connection with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to:

[0101] A railway construction model is constructed according to the time required by each process, the cost required by each process, the quality coefficient of each process and the safety coefficient of each process, wherein the model parameters in the railway construction model include the time required by the project , the cost required by the project , the quality coefficient of the project and the safety coefficient of the project ;

[0102] The railway construction model is solved according to the improved grey wolf algorithm to obtain the project process period, wherein the solving of the railway construction model according to the improved grey wolf algorithm is specifically:

[0103] The time required by the project , the cost required by the project , the quality coefficient of the project and the safety coefficient of the project are defined as the position of the grey wolf, that is, the coded project process period sequence;

[0104] According to the non-uniform sampling adaptive population initialization strategy, a plurality of different grey wolf individuals are generated for the position of the grey wolf individual;

[0105] Calculate each gray wolf individual information, i.e. the time required for the specific process of the project, the cost required for the process, the process quality coefficient and the process safety coefficient, screen out the target project duration process, and the corresponding gray wolf information is classified into the elite archive;

[0106] According to the random heuristic jump strategy improved hunting mechanism, the gray wolf individual information outside the elite archive is updated;

[0107] In the elite archive, multiple gray wolf information finds the position of the head wolf according to the multi-scale cooperative mutation operator, and judges whether the maximum iteration number is reached;

[0108] If the maximum iteration number is reached, the position information of the head wolf is decoded to obtain the project process duration with the minimum duration, the lowest cost and the best quality and safety;

[0109] If the maximum iteration number is not reached, the position of the gray wolf outside the elite archive is updated, and the position of the head wolf is screened in the elite archive until the maximum iteration number is reached.

[0110] Through the description of the above embodiments, those skilled in the art can clearly understand that the embodiments can be realized by means of software and the necessary general hardware platform, and of course, they can also be realized by hardware. Based on such understanding, the above technical solutions or the essential part of the prior art can be embodied in the form of software products, which can be stored in a computer readable storage medium such as ROM / RAM, magnetic disk, optical disk, etc., including a plurality of instructions to make a computer device (which can be a personal computer, server, or network device, etc.) execute the method of each embodiment or some part of the embodiment.

[0111] Finally, it should be noted that: the above examples are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing examples, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing examples, or make equivalent replacement for some technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A railway construction optimization method based on an improved grey wolf algorithm, characterized in that, The method comprises the following steps: According to the time required by each process, the cost required by each process, the quality coefficient of each process and the safety coefficient of each process, a railway construction model is constructed, wherein the model parameters in the railway construction model include the time required by the project , the cost required by the project , the quality coefficient of the project and the safety coefficient of the project ; According to the improved grey wolf algorithm, the railway construction model is solved to obtain the project process duration, wherein the solving of the railway construction model according to the improved grey wolf algorithm specifically comprises the following steps: time required for the project cost required for the project quality coefficient of the project and safety coefficient of the project defined as the position of the grey wolf, i.e. the coded project activity duration sequence; For the position of the grey wolf individual, a non-uniform sampling adaptive population initialization strategy is used to generate multiple groups of different grey wolf individuals; The information of each grey wolf individual, i.e., the time required by the specific project process, the cost required by the process, the process quality coefficient and the process safety coefficient, is calculated, the target project process duration is screened out, and the corresponding grey wolf information is classified into the elite archive; According to the hunting mechanism improved based on the random heuristic jump strategy, the information of the grey wolf individuals outside the elite archive is updated; In the elite archive, multiple grey wolf information finds the position of the alpha wolf according to the multi-scale cooperative mutation operator, and whether the maximum iteration number is reached is judged; If the maximum iteration number is reached, the position information of the alpha wolf is decoded to obtain the project process duration with the smallest duration, the lowest cost and the best quality and safety; If the maximum iteration number is not reached, the position of the grey wolf outside the elite archive is updated, and the position of the alpha wolf is screened out in the elite archive until the maximum iteration number is reached.

2. The railway construction optimization method based on the improved grey wolf algorithm according to claim 1, characterized in that, The expression of the railway construction model is: The expression of the non-uniform sampling adaptive population initialization strategy is: ， wherein, is the project process function, is the project time required, is the process time required, is all processes on the critical path, is the project cost required, is the process cost required, is the project quality factor, is the process quality factor, is the project safety factor, is the process safety factor, is the number of days delayed, is the delay penalty cost factor, is the delay penalty quality factor, is the delay penalty safety factor.

3. The railway construction optimization method based on the improved grey wolf algorithm according to claim 1, characterized in that, The hunting mechanism improved based on the random heuristic jump strategy for updating the information of the grey wolf individuals outside the elite archive comprises the following steps: ， ， wherein is a random individual, is an adaptive step size, is a first candidate point, is a weighting exponent, is an average fitness, is a random map value, is a second candidate point, is a perturbation factor, is a fourth type of distribution correction factor, is a selection intensity parameter, is a small perturbation term, is a local density.

4. The railway construction optimization method based on the improved grey wolf algorithm according to claim 1, characterized in that, For the leader, a random heuristic jump strategy or a hunting mechanism in the original way is used to optimize the movement according to a probability of 50% to obtain the updated information of the grey wolf individuals outside the elite archive, and the expression of the hunting mechanism is: when the wolf pack is hunting wolf, wolf, wolf command wolf attacks the prey, the grey wolf encircles the prey during the hunting process and continuously shortens the distance from the prey, the behavior of shortening the distance from the prey is mathematically modeled, and the expression is: ， ， ， wherein is the current iteration number, , are coefficient vectors, is the prey position, is the distance vector of the wolf pack movement, is the distance vector of the wolf pack individuals from the prey, is a convergence factor, linearly decreasing from 2 to 0, , are random vectors; The expression of the multi-scale cooperative mutation operator is: ， ， ， ， ， ， wherein, , , are the distance vectors of the prey and the wolf, wolf, wolf respectively, , , are constant vectors, , , are the position vectors of the wolf, wolf, wolf respectively, is the current position of the gray wolf individual, , , are the positions of the first, second and third gray wolf respectively, is the weight of the control step size, is the heuristic function, is a random number in [0, 1], , , are the adaptive step sizes of the prey and the wolf, wolf, wolf respectively, is the density-driven disturbance regulator, is the heuristic balance factor, is the actual proportion, is the allowed proportion, is the territory range, is the conflict frequency, is the marking strength, is the conflict risk, is the resource density coefficient, is the sensitivity value, is the distance vector of the wolf pack movement.

5. The railway construction optimization method based on the improved grey wolf algorithm according to claim 1, characterized in that, The method comprises the following steps: The solving module is configured to solve the railway construction model according to the improved grey wolf algorithm to obtain the project process duration, wherein the solving of the railway construction model according to the improved grey wolf algorithm specifically comprises the following steps: ， ， wherein, is the wolf uses the position after mutation, i.e. the global optimum solution, is the wolf uses the position before mutation, is the mutation weight, is the random distribution at time t, is the adjustment parameter, with a value range of [30, 100], is the current iteration number, is the maximum iteration number, is the mutual repulsion activity, is the repulsion position, is the mutual repulsion gradient, is the mutual repulsion adjustment parameter, is the attraction degree.

6. A railway construction optimization system based on an improved grey wolf algorithm, characterized by, For the position of the grey wolf individual, a non-uniform sampling adaptive population initialization strategy is used to generate multiple groups of different grey wolf individuals; The construction module is configured to construct a railway construction model according to the time required for each process, the cost required for each process, the quality coefficient of each process, and the safety coefficient of each process, wherein model parameters in the railway construction model include the time required for the project , the cost required for the project , the quality coefficient of the project , and the safety coefficient of the project . The information of each grey wolf individual, i.e., the time required by the specific project process, the cost required by the process, the process quality coefficient and the process safety coefficient, is calculated, the target project process duration is screened out, and the corresponding grey wolf information is classified into the elite archive; time required for the project cost required for the project quality coefficient of the project and safety coefficient of the project defined as the position of the grey wolf, i.e. the coded project activity duration sequence; According to the hunting mechanism improved based on the random heuristic jump strategy, the information of the grey wolf individuals outside the elite archive is updated; In the elite archive, multiple grey wolf information finds the position of the alpha wolf according to the multi-scale cooperative mutation operator, and whether the maximum iteration number is reached is judged; If the maximum iteration number is reached, the position information of the alpha wolf is decoded to obtain the project process duration with the smallest duration, the lowest cost and the best quality and safety; If the maximum iteration number is not reached, the position of the grey wolf outside the elite archive is updated, and the position of the alpha wolf is screened out in the elite archive until the maximum iteration number is reached. The method comprises the following steps: ​ 7. An electronic device, comprising: ​ at least one processor, and a memory connected with the at least one processor in communication, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 5.

8. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program, when executed by a processor, implements the method of any one of claims 1 to 5. The program, when executed by a processor, implements the method of any one of claims 1 to 5.

Images