Multi-bucket wheel machine collaborative operation scheduling system and method based on swarm intelligence algorithm

Abstract

The invention provides a multi-bucket wheel machine collaborative operation scheduling system and method based on a swarm intelligence algorithm, and relates to the technical field of electronic information. Inputting the equipment information, the stacking information and the environment information into a first model to generate constraint conditions; performing global search based on an artificial bee colony algorithm introducing harmony search, and screening solutions according to constraint conditions in each iteration to obtain a group of feasible solutions; performing local search in each feasible solution neighborhood by adopting mixed integer programming to obtain a globally optimal solution; and generating working parameters of the equipment according to the globally optimal solution, and performing job scheduling. The artificial bee colony algorithm is improved by introducing a harmony search mechanism, the global search capability is enhanced, and premature convergence is avoided; and meanwhile, local optimization is carried out in combination with mixed integer programming, so that the solution accuracy is improved, the algorithm can adapt to yard scheduling requirements of different scales and different constraint conditions, and the overall operation efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of electronic information technology, and in particular, to a multi-bucket wheel machine collaborative operation scheduling system and method based on a swarm intelligence algorithm. Background Art

[0002] A bucket wheel machine is a bulk material loading and unloading device with efficient continuous operation, which is widely used in large bulk material yards such as ports, power plants, and steel mills, and undertakes tasks such as stacking, reclaiming, and material transfer. During the reclaiming operation, the bucket wheel mechanism rotates to reclaim materials, and the materials are output through a belt conveyor running forward. At the same time, the operation range is adjusted by slewing and pitching; during the stacking operation, the belt conveyor runs in the reverse direction to convey the materials to the designated position, and the stacking trajectory is adjusted by means of the slewing and pitching mechanisms.

[0003] Generally, multiple bucket wheel machines are arranged in a stacking yard for collaborative operation. Multiple bucket wheel machines usually need to be dynamically scheduled among multiple stockpiles to meet the material requirements of different production links. However, during the scheduling process, there may be spatial interference or motion conflicts between multiple bucket wheel machines. With the improvement of the automation and intelligence level of the yard, the collaborative operation requirements of multiple bucket wheel machines are increasing day by day. How to optimize the scheduling strategy, avoid interference and improve the overall operation efficiency has become a key issue in the operation management of bulk material yards. Summary of the Invention

[0004] The purpose of the present invention is to provide a multi-bucket wheel machine collaborative operation scheduling system and method based on a swarm intelligence algorithm to improve the above problems. To achieve the above purpose, the technical solutions adopted by the present invention are as follows:

[0005] In a first aspect, the present application provides a multi-bucket wheel machine collaborative operation scheduling method based on a swarm intelligence algorithm, including:

[0006] Obtain equipment information, stacking information, and environmental information;

[0007] Input the equipment information, stacking information, and environmental information into a first model to generate constraint conditions;

[0008] Perform global search based on an artificial bee colony algorithm introducing harmony search, wherein in each iteration, the solutions are screened according to the constraint conditions to obtain a set of feasible solutions;

[0009] Perform local search in the neighborhood of each feasible solution by using mixed integer programming to obtain the global optimal solution;

[0010] Generate the working parameters of the equipment according to the global optimal solution for operation scheduling.

[0011] In a second aspect, the present application further provides a multi-bucket wheel machine collaborative operation scheduling system based on a swarm intelligence algorithm, including:

[0012] The first module is used to obtain device information, stockpiling information, and environmental information;

[0013] The second module is used to input the device information, stockpiling information, and environmental information into the first model to generate constraint conditions;

[0014] The third module is used to perform global search based on the artificial bee colony algorithm introduced with harmony search. Among them, in each iteration, the solutions are screened according to the constraint conditions to obtain a set of feasible solutions;

[0015] The fourth module is used to perform local search in the neighborhood of each feasible solution by using mixed integer programming to obtain the global optimal solution;

[0016] The fifth module is used to generate the working parameters of the device according to the global optimal solution and perform job scheduling.

[0017] The beneficial effects of the present invention are as follows:

[0018] In this application, the artificial bee colony algorithm is improved by introducing a harmony search mechanism to enhance the global search ability and avoid premature convergence; at the same time, local optimization is combined with mixed integer programming to improve the accuracy of the solution, enabling the algorithm to adapt to the yard scheduling requirements of different scales and different constraint conditions, quickly generate high-quality scheduling schemes under complex constraint conditions, optimize the collaborative operation sequence and path of multiple bucket wheel stacker reclaimers, reduce the idling and waiting time of equipment, and improve the overall operation efficiency.

[0019] Other features and advantages of the present invention will be described in the subsequent specification, and part of them will become obvious from the specification or be understood by implementing the embodiments of the present invention. Description of the Drawings

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0021] Figure 1 It is a flowchart of the collaborative operation scheduling method for multiple bucket wheel stacker reclaimers based on the swarm intelligence algorithm in the embodiments of this application;

[0022] Figure 2 It is a structural diagram of the collaborative operation scheduling system for multiple bucket wheel stacker reclaimers based on the swarm intelligence algorithm in the embodiments of this application;

[0023] Symbols in the figure: 100 - First module; 200 - Second module; 300 - Third module; 310 - First unit; 320 - Second unit; 330 - Third unit; 331 - First subunit; 332 - Second subunit; 333 - Third subunit; 340 - Fourth unit; 350 - Fifth unit; 360 - Sixth unit; 370 - Seventh unit; 400 - Fourth module; 500 - Fifth module. Detailed implementation manners

[0024] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are some but not all of the embodiments of the present invention. The components of the embodiments of the present invention usually described and illustrated in the accompanying drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely represents the selected embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without making creative efforts fall within the scope of protection of the present invention.

[0025] It should be noted that: similar reference numerals and letters denote similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0026] Embodiment 1

[0027] Refer to Figure 1 , this embodiment provides a multi-bucket wheel collaborative operation scheduling method based on a swarm intelligence algorithm, including: steps S100, S200, S300, S400 and S500;

[0028] S100. Obtain equipment information, stockpiling information and environmental information;

[0029] The equipment information includes information such as equipment type information, equipment failure information, temperature information of main components of the equipment, and current position of the equipment.

[0030] The stockpiling information includes stockpiling position, stockpiling geometric parameters, material type, priority identification, and corresponding stacking rules (layering requirements, slope limit, anti-collapse safety angle).

[0031] The environmental information includes temperature, humidity, wind speed, rainfall, dust concentration, etc.; among them, factors such as temperature, humidity, wind speed and rainfall will affect the operation duration and height of the equipment, and areas with too high dust concentration will be divided into operation restricted areas. The specific division threshold is related to the stockpiling type and will not change until the concentration decreases after sprinkling.

[0032] S200. Input the device information, stockpiling information, and environmental information into the first model to generate constraint conditions;

[0033] The first model is pre - constructed based on historical data and expert knowledge. On the one hand, hard constraints are defined through expert knowledge, such as the safety distance between devices, stockpiling height constraints under corresponding weather conditions, operation height constraints under certain wind speeds and humidities, the maximum temperature limit of main components, the operation radius constraint of the bucket wheel stacker - reclaimer, and the maximum operation time of the device under a certain temperature, etc.

[0034] In addition to conventional physical constraints, due to the different geological structures and the changing distribution of obstacles in each stockpiling yard, it may be necessary to disable some devices or demarcate temporary restricted areas at certain times. Therefore, this step also needs to collect historical data and corresponding disabling information to construct a corresponding disabling list as one of the constraint conditions.

[0035] The first model can combine a preset rule table with a pre - trained neural network. The rule table is used to query hard constraints that cannot be violated; the neural network is constructed by training with historical data and is used to generate other constraint items based on the input information.

[0036] S300. Conduct a global search based on the artificial bee colony algorithm introduced with the harmony search. Among them, in each iteration, the solutions are screened according to the constraint conditions to obtain a set of feasible solutions, specifically as follows:

[0037] S310. Randomly generate an initial population, conduct a search based on the initial population, obtain feasible solutions, and store them in the harmony memory bank;

[0038] The encoding of the initial population needs to include information such as the task assignment of each device, the execution task sequence, the working speed of the device, and the task start time, which includes discrete variables and continuous variables; this step uses a matrix mixing method for encoding. Each row of the matrix corresponds to a device, and each row successively includes the task sequence, working speed, and task start time.

[0039] The artificial bee colony algorithm (ABC) is a swarm intelligence optimization algorithm based on the honey - collecting behavior of bees. It simulates the behavior of a bee colony searching for nectar sources (solutions) and includes three types of bee roles:

[0040] Employed Bees: Responsible for exploiting known nectar sources (local search).

[0041] Onlooker Bees: Select high - quality nectar sources for further exploitation according to the roulette wheel selection (global exploration).

[0042] Scout Bees: Abandon low-quality nectar sources and randomly search for new ones (to avoid getting stuck in local optima).

[0043] Among them, employed bees search near the initial nectar source to find better ones. Employed bees return the information of the nectar source and fitness to the observing bees. The observing bees determine the selection probability based on the fitness of each nectar source. Each observing bee selects a nectar source, and the selected nectar source generates a new solution and updates it in the same way as in the employed bee stage. If the quality of a nectar source has not improved after n iterations, then the nectar source is abandoned, and the observing bee becomes a scout bee, randomly selecting a new nectar source globally.

[0044] For each solution obtained by the artificial bee colony algorithm search, the maximum working duration, operation height, minimum distance between devices, maximum load, and other operation information corresponding to each device of this solution can be obtained, so as to determine whether the operation information corresponding to this solution violates the constraint conditions. If so, it means that this solution is infeasible.

[0045] S320. In each iteration, for each variable in each feasible solution, determine whether to select a corresponding variable from the harmony memory bank with a first probability to replace it to obtain a replacement new solution; if not, randomly select in the value range of this variable to generate a random new solution;

[0046] Harmony Search (HS) is a heuristic global search algorithm, which realizes optimization through the following steps:

[0047] Initialize the harmony memory bank: Generate a certain number of initial solutions (harmonies) and store them in the Harmony Memory (HM).

[0048] Generate a new harmony: Determine whether to select a variable from the HM according to the harmony memory bank value probability (HMCR). If selected, it may be fine-tuned (the adjustment probability is PAR, and the adjustment range is the bandwidth BW), otherwise, randomly generate a variable in the solution space.

[0049] Update the harmony memory bank: If the newly generated harmony is better than the worst harmony in the HM, then replace it.

[0050] Iterative optimization: Repeat the above process until the predetermined number of iterations is reached.

[0051] This application combines harmony search into the artificial bee colony algorithm, continuously updates the harmony memory bank, and retains the better solutions;

[0052] During each iteration search, the employed bees search around the center nectar source with the solution in the updated harmony memory library. In the traditional observer bee stage, high-quality solutions are selected through roulette wheel selection, which may over-focus on local areas. The randomness and diversity of HS can make up for the defect that ABC is prone to falling into local optima. The "improvisation" mechanism (randomly replacing variables) of the harmony memory library can quickly generate diverse solutions, quickly explore the solution space, and have low dependence on the quality of the initial solution.

[0053] The first probability is the harmony memory library value probability (HMCR). In the initial stage of exploration, a relatively small first probability value (such as 0.6 - 0.7) can be set to quickly explore the solution space. In the later stage, a relatively large first probability (such as 0.95) can be set to highlight the local development ability of ABC and refine the later solutions.

[0054] S330. Adjust each variable of the alternative new solution through Kent mapping with the second probability. If the adjusted new solution is better than the worst solution in the harmony memory library, then replace the worst solution.

[0055] The second probability is the adjustment probability PAR. When a variable of the solution is replaced, it is decided whether to adjust the variable with probability PAR. The variables in the solution are divided into discrete variables and continuous variables, and the adjustment methods for the two types of variables are slightly different. The specific adjustment methods are as follows:

[0056] S331. Construct an adaptive bandwidth function based on the number of iterations, population diversity, and convergence status;

[0057] Population diversity is the standard deviation of the fitness of the current population. If the population diversity is high, a relatively large bandwidth should be maintained to encourage exploration; if the diversity is low, the bandwidth should be reduced to strengthen local development. As the number of iterations progresses, the bandwidth should also be gradually reduced to enhance local development.

[0058] The convergence status is to detect whether it has fallen into local optima. If the change in the fitness values in the recent k generations is too small, it is considered that convergence has stagnated and the bandwidth needs to be increased to jump out.

[0059] Let the number of iterations be t, the population diversity be D t , and the convergence status be C t ,. Consider three adjustment terms to construct an adaptive bandwidth function:

[0060] BW t = B0 × α(t) × β(D t )) × γ(C t );

[0061] Among them, B0 is the initial bandwidth;

[0062] α(t) is the iteration number decay term:

[0063]

[0064] Among them, λ is the attenuation rate, usually taken from [1, 5]; t max is the preset maximum number of iterations;

[0065] β(D t ) is the population diversity adjustment term:

[0066]

[0067] Among them, η is the adjustment coefficient, taken from [0, 1]; D min and D max are the historical minimum and maximum values of the population diversity.

[0068] γ(C t ) is the convergence state adjustment term:

[0069]

[0070] Among them, κ is the steepness coefficient; C th is the convergence threshold (empirical value, such as 10 -5 ).

[0071] S332. Dynamically adjust the bandwidth parameter of the harmony search based on the adaptive bandwidth function, and determine the adjustment range based on the bandwidth parameter;

[0072] Calculate the bandwidth parameter BW of this iteration according to the above adaptive bandwidth function t ;

[0073] Determine the adjustment range based on the bandwidth parameter:

[0074] For continuous variables: the adjustment range is BW t ×N(-1, 1);

[0075] For discrete variables: the adjustment range is round(BW t ×N(-1, 1)); Round means rounding to the nearest integer. It should be noted that discrete variables generally have only a few consecutive integer values. If integer values are directly added to or subtracted from discrete variables, it may exceed the solution space range of the discrete variables. Therefore, the adjustment range of discrete variables defined in this application refers to the number of positions moved to the left and right of the discrete variable. For example, if a discrete variable takes values {1, 2, 3, 4}, the adjustment range is ±1. Based on the variable 4 for adjustment, the selectable range for adjustment is the two values on the left and right of 4, that is, 3 and 1 (when the value is at the first / last position, the last / first value is considered its adjacent value).

[0076] It should be noted that the initial bandwidth B0 of different variables is different and needs to be set separately.

[0077] S333. Determine whether to make an adjustment according to the second probability. If so, within the adjustment range, generate a random number using the Kent map and add the random number to the variable.

[0078] The Kent map is a pseudo-random number generation method based on chaotic dynamics. The random numbers generated by the Kent map have the characteristic of uniform distribution. In this application, a random number sequence is pre-generated using the Kent map, and the random number sequence is shuffled to obtain a random number set for backup.

[0079] In the iteration of the harmony search, each time a random number is needed, the first random number is extracted from the random number set and mapped to the required range through modulo operation or hash mapping. After extraction, the used random number is deleted from the random number set to ensure the randomness of each adjustment.

[0080] S340. Divide the solution space into multiple grid regions, and statistically calculate the improvement scores of each region based on the distribution of the historical optimal solutions.

[0081] Statistically calculate the number of historical optimal solution distributions in each region, and use the ratio of the number of historical optimal solutions in this region to the total number of historical optimal solutions as the improvement score of this region. The larger the improvement score, the greater the possibility of the optimal solution appearing in this region.

[0082] S350. Construct a fitness function based on the total operation time, energy consumption weighted sum, and equipment load variance.

[0083] The optimization goal of this application is to minimize the total operation time and energy consumption, and at the same time balance the loads of each device to ensure the performance of the device. The energy consumption can be calculated according to the operation time and load information of each device. The sum of the operation time, energy consumption weighted sum, and equipment load variance is calculated by weighted calculation, and the smaller the obtained fitness, the better.

[0084] S360. In the observing bee stage, calculate the similarity between each solution and the historical optimal solution, and at the same time calculate the fitness value of the solution according to the fitness function.

[0085] In the traditional method, each observing bee selects a high-quality nectar source for further development according to the search results of the employed bees, that is, calculates the fitness of each nectar source to obtain the probability of selecting the nectar source. In this application, the fitness of the solution and its similarity to the historical optimal solution are considered simultaneously, so that the observing bees are more inclined to select solutions close to the historical optimal solution.

[0086] S370. Obtain the improvement score of the region where the solution is located, calculate the weighted sum of the fitness and similarity value of the solution according to the improvement score, and the observing bees select the solution according to the weighted sum.

[0087] Specifically, in this step, the region where the current solution is located is considered. If the improvement score of the region where it is located is high, the priority of the similarity value can be increased, that is, the weight of the similarity value is increased.

[0088] In the standard ABC, the employed bees perform neighborhood search around the current solution, and the search step size is random within a fixed range, which may lead to low search efficiency (too large a step size skips the optimal solution, and too small a step size results in slow convergence). To balance the global exploration and local exploitation capabilities, this application adopts a strategy of dynamically adjusting the search step size in the employed bee stage:

[0089] Statistically analyze the search step size distribution corresponding to the successfully updated solutions in the current generation;

[0090] Based on the search step size distribution, establish a kernel density estimation model; use φ to represent the search step size, and specifically adopt a Gaussian kernel function:

[0091]

[0092] where W is the total number of step sizes of the successfully updated solutions, φ i is the i-th step size, h = W -1 / 5 ·σ, σ is the sample standard deviation, u is the sample mean; K(u) is the probability density function of a standard normal distribution; f(φ) is the estimated probability density of the step size φ.

[0093] Adjust the search step size parameter of the observing bees in the next iteration according to the kernel density estimation model. That is, draw a new step size from the kernel density estimation model and preferentially select the value in the high probability density region.

[0094] S400. Perform local search in the neighborhood of each feasible solution using mixed integer programming to obtain the global optimal solution;

[0095] Divide the integer variables and continuous variables in each solution; construct corresponding boundary constraints for each variable;

[0096] Determine the values of the integer variables by the branch and bound method; first relax the integer variables to continuous variables, construct a continuous optimization problem, preferentially process the node with the smallest lower bound, and preferentially select the integer variable with the fractional part closest to 0.5 in the relaxed solution when selecting the branching variable, perform binary division on the selected variable to generate left and right child nodes, compare the lower bound of the node and the current optimal solution, and perform branch pruning.

[0097] After fixing the integer variables, use the interior point method to optimize the continuous variables to obtain the global optimal solution.

[0098] S500. Generate the working parameters of the device according to the global optimal solution and perform job scheduling.

[0099] Embodiment 2

[0100] SeeFigure 2 , this embodiment provides a multi-bucket wheel machine collaborative operation scheduling system based on a swarm intelligence algorithm, including:

[0101] The first module 100 is used to obtain equipment information, stockpiling information, and environmental information;

[0102] The second module 200 is used to input the equipment information, stockpiling information, and environmental information into the first model to generate constraint conditions;

[0103] The third module 300 is used to perform global search based on the artificial bee colony algorithm introduced with harmony search. Among them, in each iteration, the solutions are screened according to the constraint conditions to obtain a set of feasible solutions;

[0104] The fourth module 400 is used to perform local search in the neighborhood of each feasible solution by using mixed integer programming to obtain the global optimal solution;

[0105] The fifth module 500 is used to generate the working parameters of the equipment according to the global optimal solution for operation scheduling.

[0106] As an alternative embodiment, the third module 300 includes:

[0107] The first unit 310 is used to randomly generate an initial population, perform search based on the initial population to obtain feasible solutions, and store them in the harmony memory bank;

[0108] The second unit 320 is used to, in each round of iteration, for each variable in each feasible solution, determine with a first probability whether to select a corresponding variable from the harmony memory bank to replace it to obtain a new replacement solution; if not, randomly select within the value range of the variable to generate a random new solution;

[0109] The third unit 330 is used to adjust each variable of the new replacement solution with a second probability through Tent mapping. If the adjusted new solution is better than the worst solution in the harmony memory bank, the worst solution is replaced.

[0110] As an alternative embodiment, the third unit includes:

[0111] The first subunit 331 is used to construct an adaptive bandwidth function based on the number of iterations, population diversity, and convergence state;

[0112] The second subunit 332 is used to dynamically adjust the bandwidth parameter of the harmony search based on the adaptive bandwidth function, and determine the adjustment range based on the bandwidth parameter;

[0113] The third subunit 333 is used to determine whether to perform adjustment according to the second probability. If so, within the adjustment range, generate a random number by using Tent mapping and add the random number to the variable.

[0114] As an alternative embodiment, the third module 300 includes:

[0115] A fourth unit 340, configured to divide the solution space into a plurality of grid regions and statistically calculate the improvement scores of each region based on the distribution of historical optimal solutions;

[0116] A fifth unit 350, configured to construct a fitness function based on the total operation time, energy consumption weighting, and equipment load variance;

[0117] A sixth unit 360, configured to calculate the similarity between each solution and the historical optimal solution during the observation bee stage, and simultaneously calculate the fitness value of the solution according to the fitness function;

[0118] A seventh unit 370, configured to obtain the improvement score of the region where the solution is located, calculate the weighted sum of the fitness and similarity values of the solution according to the improvement score, and the observation bee selects and updates the solution according to the weighted sum.

[0119] It should be noted that in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the phrase "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the element.

[0120] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, and all of them should be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A multi-bucket wheel machine collaborative operation scheduling method based on swarm intelligence algorithm, characterized in that Including: Obtain device information, stockpiling information, and environmental information; Input the device information, stockpiling information, and environmental information into a first model to generate constraint conditions; Perform global search based on an artificial bee colony algorithm incorporating harmony search, where in each iteration, solutions are screened according to the constraint conditions to obtain a set of feasible solutions; Use mixed-integer programming to perform local search in the neighborhood of each feasible solution to obtain the global optimal solution; Generate the working parameters of the device according to the global optimal solution for job scheduling.

2. The multi-bucket wheel machine collaborative operation scheduling method based on the swarm intelligence algorithm according to claim 1, wherein Performing global search based on an artificial bee colony algorithm incorporating harmony search includes: Randomly generate an initial population, perform search based on the initial population to obtain feasible solutions and store them in the harmony memory bank; In each round of iteration, for each variable in each feasible solution, determine with a first probability whether to select a corresponding variable from the harmony memory bank to replace it to obtain a replacement new solution; if not, randomly select within the value range of the variable to generate a random new solution; Adjust each variable of the replacement new solution with a second probability through Tent mapping. If the adjusted new solution is better than the worst solution in the harmony memory bank, replace the worst solution.

3. The multi-bucket-wheel collaborative operation scheduling method based on swarm intelligence algorithm according to claim 2, wherein Adjust the variables of the new solution with a third probability through Tent mapping, including: Construct an adaptive bandwidth function based on the iteration number, population diversity, and convergence state; Dynamically adjust the bandwidth parameter of harmony search based on the adaptive bandwidth function, and determine the adjustment range based on the bandwidth parameter; Determine whether to make an adjustment according to the second probability. If so, within the adjustment range, use Tent mapping to generate a random number and add the random number to the variable.

4. The multi-bucket-wheel collaborative operation scheduling method based on the swarm intelligence algorithm according to claim 1, wherein Performing global search based on an artificial bee colony algorithm incorporating harmony search includes: Divide the solution space into multiple grid regions, and statistically calculate the improvement score of each region based on the distribution of the historical optimal solutions; Construct a fitness function based on the total operation time, energy consumption weighted sum, and device load variance; In the onlooker bee stage, calculate the similarity between each solution and the historical optimal solution, and at the same time calculate the fitness value of the solution according to the fitness function; Obtain the improvement score of the region where the solution is located, calculate the weighted sum of the fitness and similarity values of the solution according to the improvement score, and the onlooker bees select and update the solution according to the weighted sum.

5. The multi-bucket wheel collaborative operation scheduling method based on swarm intelligence algorithm according to claim 4, wherein Performing global search based on an artificial bee colony algorithm incorporating harmony search includes: Statistically calculate the search step size distribution corresponding to the solutions successfully updated in the current generation; Establish a kernel density estimation model according to the search step size distribution; Adjust the search step size parameter of the onlooker bees in the next iteration according to the kernel density estimation model.

6. The multi-bucket wheel collaborative operation scheduling method based on swarm intelligence algorithm according to claim 1, wherein, Use mixed-integer programming to perform local search in the neighborhood of each feasible solution to obtain the global optimal solution, including: Divide the integer variables and continuous variables in each solution; Determine the values of the integer variables by the branch and bound method; After fixing the integer variables, use the interior point method to optimize the continuous variables to obtain the global optimal solution.

7. A multi-bucket wheel machine collaborative operation scheduling system based on a swarm intelligence algorithm, characterized in that, Including: The first module is used to obtain device information, stockpiling information, and environmental information; The second module is used to input the device information, stockpiling information, and environmental information into the first model to generate constraint conditions; The third module is used for global search based on the artificial bee colony algorithm introducing harmony search, where in each iteration, the solutions are screened according to the constraint conditions to obtain a set of feasible solutions; The fourth module is used for local search in the neighborhood of each feasible solution by using mixed integer programming to obtain the global optimal solution; The fifth module is used for generating the working parameters of the device according to the global optimal solution for job scheduling.

8. The multi-bucket wheel machine collaborative operation scheduling system based on the swarm intelligence algorithm according to claim 7, characterized in that, The third module includes: The first unit is used for randomly generating an initial population, performing search based on the initial population to obtain feasible solutions and storing them in the harmony memory library; The second unit is used for in each iteration, for each variable in each feasible solution, determining with a first probability whether to select a corresponding variable from the harmony memory library to replace it to obtain a replacement new solution; if not, randomly select in the value range of the variable to generate a random new solution; The third unit is used for adjusting each variable of the replacement new solution with a second probability through the Tent mapping. If the adjusted new solution is better than the worst solution in the harmony memory library, the worst solution is replaced.

9. The multi-bucket-wheel collaborative operation scheduling system based on the swarm intelligence algorithm according to claim 8, wherein The third unit includes: The first sub-unit is used for constructing an adaptive bandwidth function based on the number of iterations, population diversity, and convergence status; The second sub-unit is used for dynamically adjusting the bandwidth parameter of the harmony search based on the adaptive bandwidth function, and determining the adjustment range based on the bandwidth parameter; The third sub-unit is used for determining whether to make an adjustment according to the second probability. If so, within the adjustment range, generate a random number by using the Tent mapping and add the random number to the variable.

10. The multi-bucket wheel collaborative operation scheduling system based on the swarm intelligence algorithm according to claim 7, wherein The third module includes: The fourth unit is used for dividing the solution space into multiple grid regions and statistically calculating the improvement scores of each region based on the distribution of the historical optimal solutions; The fifth unit is used for constructing a fitness function based on the total job time, energy consumption weighted sum, and device load variance; The sixth unit is used for in the observer bee stage, calculating the similarity between each solution and the historical optimal solution, and at the same time calculating the fitness value of the solution according to the fitness function; The seventh unit is used for obtaining the improvement score of the region where the solution is located, calculating the weighted sum of the fitness and similarity values of the solution according to the improvement score, and the observer bee selects and updates the solution according to the weighted sum.

Images