Kitchen waste transfer station optimization site selection method considering double objectives and service platform

Abstract

The invention relates to a kitchen waste transfer station optimization site selection method and service platform considering double objectives, and the method comprises the steps: carrying out the random coding of alternative transfer station candidate points, generating a first site selection configuration code array, and enabling the first site selection configuration code array to comprise a plurality of first codes; based on a preset improved NSGA-II algorithm, performing non-dominated solution sorting and genetic evolution operation on the first code, and generating a mixed site selection configuration code array; performing new population iteration on the mixed site selection configuration coding array by utilizing an elitist retention strategy corresponding to an improved NSGA-II algorithm to generate a second site selection configuration coding array with a plurality of second codes; determining fitness corresponding to the second codes, performing non-dominated solution sorting, genetic evolution operation and new population iteration processing based on an elitism strategy on the second codes in the second site selection configuration code array according to the fitness, generating a target site selection configuration code array, and obtaining target codes from the target site selection configuration code array, and obtaining a site selection result.

Description

Technical Field

[0001] The present application relates to the technical field of waste classification, and in particular to a method and service platform for optimizing the site selection of kitchen waste transfer stations taking dual objectives into consideration. Background Art

[0002] With the implementation of the garbage classification system, more and more scholars have begun to pay attention to the research on garbage transfer stations under the background of garbage classification, but most of the research focuses on the site selection of a single type of garbage transfer station or the configuration of internal processing equipment; at the same time, in related technologies, the reconstruction of garbage classification transfer stations is restricted by land resources, funds and NIMBY effects. The reconstruction and site selection schemes of garbage transfer stations in existing technologies are all based on multi-objective modeling and heuristic solutions for the site selection of various types of urban domestic waste treatment facilities, and no research has been carried out on the site selection problem of food waste transfer stations.

[0003] In the relevant technology, the site selection research of food waste transfer stations faces the following challenges: First, food waste transfer stations are typical NIMBY facilities. Food waste is perishable and smelly. The odor, leachate and noise generated by storage will have an impact on the environment and cause complaints from surrounding residents. If the food waste is too far away from the point where residents generate it, the company's transportation costs will increase. Secondly, land resources are scarce, and it is difficult to find a site for the construction of a waste transfer station. Especially under the garbage classification system, the reconstruction of the urban domestic waste classification collection and transportation system requires the construction / reconstruction of a large number of classified garbage transfer stations. Thirdly, the construction cost of a food waste transfer station is high. In order to minimize the impact on the surrounding environment and improve the operating efficiency of the transfer station, certain intelligent equipment is often invested, such as: intelligent tanks, intelligent deodorization equipment, sewage treatment equipment and various environmental monitoring equipment, etc., but this will increase the investment cost.

[0004] At present, with regard to the reconstruction and site selection scheme of food waste transfer stations in related technologies, there are problems such as high site selection and construction costs, and high collection and transportation costs of the garbage transfer stations after reconstruction, and no effective solution has been proposed yet. Summary of the invention

[0005] The embodiments of the present application provide a method and service platform for optimizing the site selection of a kitchen waste transfer station that considers dual objectives, as well as a device and a storage medium, so as to at least solve the problem of high site selection and construction costs, and high collection and transportation costs of the garbage transfer station after reconstruction in the related art, and no effective solution has yet been proposed.

[0006] In the first aspect, an embodiment of the present application provides a method for optimizing the site selection of a kitchen waste transfer station considering dual objectives, including: randomly encoding candidate transfer station candidate points to generate a first site selection configuration code array, wherein the first site selection configuration code array includes multiple first codes, and the first code is used to characterize a site selection result of configuring the transfer station candidate point as a target transfer station, and the target transfer station is associated with a site selection cost parameter and an environmental negative effect parameter, and the site selection cost parameter is determined based on the garbage removal cost parameter and the garbage transfer cost parameter corresponding to the target transfer station; based on the preset improved NSGA-Ⅱ algorithm, the first code is subjected to non-dominated solution sorting and genetic evolution operations to generate a mixed site selection configuration code array, wherein the genetic evolution operation adopts dynamic crossover probability and dynamic mutation probability; and the elite retention strategy corresponding to the improved NSGA-Ⅱ algorithm is utilized. , performing a new population iteration on the mixed location configuration coding array to generate a second location configuration coding array having multiple second codes, wherein the elite retention strategy introduces a mechanism for completing the second codes through a crossover mutation operation, and the second codes are used to characterize the location selection result of configuring the transfer station candidate point as the target transfer station at present; determining the fitness corresponding to the second code, and performing non-dominated solution sorting, genetic evolution operation and new population iteration processing based on the elite retention strategy on the second codes in the second location configuration coding array according to the fitness, generating a target location configuration coding array, and obtaining a target code from the target location configuration coding array to obtain a location selection result, wherein the location selection result includes the target code, and the fitness is determined according to the location selection cost parameter and the negative environmental effect parameter associated with the target transfer station corresponding to the second code.

[0007] In a second aspect, an embodiment of the present application provides a device for optimizing the site selection of a kitchen waste transfer station considering dual objectives, including: A coding module, used for randomly coding the candidate transfer station points to generate a first site selection configuration coding array, wherein the first site selection configuration coding array includes a plurality of first codes, the first codes are used to represent a site selection result of configuring the transfer station candidate point as a target transfer station, the target transfer station is associated with a site selection cost parameter and an environmental negative effect parameter, and the site selection cost parameter is determined according to a garbage removal cost parameter and a garbage transfer cost parameter corresponding to the target transfer station; An operation module, used for performing non-dominated solution sorting and genetic evolution operation on the first coding based on a preset improved NSGA-Ⅱ algorithm to generate a mixed site configuration coding array, wherein the genetic evolution operation adopts a dynamic crossover probability and a dynamic mutation probability; A generation module, used to use the elite retention strategy corresponding to the improved NSGA-Ⅱ algorithm to perform a new population iteration on the mixed location configuration coding array to generate a second location configuration coding array with multiple second codes, wherein the elite retention strategy introduces a mechanism for completing the second codes through crossover mutation operations, and the second codes are used to represent the current location selection result of configuring the transfer station candidate point as the target transfer station; A processing module is used to determine the fitness corresponding to the second code, and according to the fitness, perform non-dominated solution sorting, genetic evolution operation and new population iterative processing based on the elite retention strategy on the second code in the second site selection configuration code array to generate a target site selection configuration code array, and obtain the target code from the target site selection configuration code array to obtain a site selection result, wherein the site selection result includes the target code, and the fitness is determined based on the site selection cost parameter and the negative environmental effect parameter associated with the target transfer station corresponding to the second code.

[0008] In a third aspect, an embodiment of the present application provides a service platform, including 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 steps of the method for optimizing the site selection of a kitchen waste transfer station considering dual objectives as in the first aspect are implemented.

[0009] In a fourth aspect, an embodiment of the present application provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method for optimizing the site selection of a kitchen waste transfer station considering dual objectives as described in the first aspect above.

[0010] Compared with the related art, the method and service platform for optimizing the site selection of kitchen waste transfer stations considering dual objectives, as well as the device and storage medium provided in the embodiment of the present application, randomly encode the candidate transfer station candidate points to generate a first site selection configuration code array, the first site selection configuration code array including multiple first codes; based on the preset improved NSGA-Ⅱ algorithm, the first codes are sorted by non-dominated solutions and genetic evolution operations to generate a mixed site selection configuration code array; the elite retention strategy corresponding to the improved NSGA-Ⅱ algorithm is used to iterate the mixed site selection configuration code array with a new population to generate a second site selection configuration code array with multiple second codes; the fitness corresponding to the second code is determined, and according to the fitness, the second codes in the second site selection configuration code array are sorted by non-dominated solutions, genetic evolution operations and new population iterative processing based on the elite retention strategy to generate a target site selection configuration code array, And obtain the target code from the target site configuration code array to obtain the site selection result including the target code; by introducing a fast non-dominated sorting algorithm, adopting an elite retention strategy of a mechanism to complete the second code through crossover mutation operations, and adopting congestion and congestion comparison operators, the computational complexity of the algorithm is reduced, the target code is quickly solved, and the basic framework based on the NSGA-Ⅱ algorithm is adopted to set the crossover and mutation probabilities that were originally fixed values ​​to dynamically change values ​​that decrease according to the logsig function as the number of iterations increases, so as to increase the convergence of the population during the iteration process, so that the population searches in the direction of the global optimal solution, so that the configuration cost corresponding to the selected target transfer station and the total negative environmental effect are minimized, and the reconstruction site selection plan of the kitchen waste transfer station is solved. There are problems of high site selection cost and construction cost, and high collection and transportation cost of the garbage transfer station after reconstruction.

[0011] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings: Figure 1 It is a hardware structure block diagram of a terminal of the method for optimizing the site selection of a kitchen waste transfer station considering dual objectives in an embodiment of the present application; Figure 2 is a flow chart of a method for optimizing the site selection of a kitchen waste transfer station considering dual objectives according to an embodiment of the present application; Figure 3 A flow chart of the improved NASG-Ⅱ algorithm used in the preferred embodiment of the present application; Figure 4It is a structural block diagram of a device for optimizing the site selection of a kitchen waste transfer station taking dual objectives into consideration according to an embodiment of the present application. DETAILED DESCRIPTION

[0013] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application. In addition, it can also be understood that although the efforts made in this development process may be complex and lengthy, for ordinary technicians in the field related to the contents disclosed in the present application, some changes such as design, manufacturing or production based on the technical contents disclosed in the present application are only conventional technical means, and should not be understood as insufficient contents disclosed in the present application.

[0014] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those of ordinary skill in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0015] Unless otherwise defined, the technical terms or scientific terms involved in this application should be understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the" and the like involved in this application do not indicate a quantitative limitation and may represent the singular or plural. The terms "including", "comprising", "having" and any of their variations involved in this application are intended to cover non-exclusive inclusions; for example, a process, method, system, product or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include unlisted steps or units, or may also include other steps or units inherent to these processes, methods, products or devices. The "multiple links" involved in this application refer to links greater than or equal to two. "And / or" describes the association relationship of associated objects, indicating that there may be three relationships, for example, "A and / or B" may represent: A exists alone, A and B exist at the same time, and B exists alone. The terms "first", "second", "third" and the like involved in this application are only used to distinguish similar objects and do not represent a specific ordering of objects.

[0016] The method embodiment provided in this embodiment can be executed in a terminal, a computer or a similar computing device. Taking running on a terminal as an example, Figure 1 1 is a hardware structure block diagram of a terminal of a method for optimizing the site selection of a kitchen waste transfer station considering dual objectives according to an embodiment of the present application. Figure 1 As shown, the terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data. Optionally, the terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is for illustration only and does not limit the structure of the above terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0017] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the method for optimizing the site selection of a food waste transfer station considering dual objectives in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0018] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0019] This embodiment provides a method for optimizing the location of a kitchen waste transfer station taking into account dual objectives and running on the above terminal. Figure 2is a flowchart of a method for optimizing the site selection of a kitchen waste transfer station considering dual objectives according to an embodiment of the present application. Figure 2 As shown, the process includes the following steps: Step S201, randomly encode the candidate transfer station candidate points to generate a first site selection configuration code array, wherein the first site selection configuration code array includes multiple first codes, and the first code is used to represent a site selection result of configuring the transfer station candidate point as a target transfer station, and the target transfer station is associated with a site selection cost parameter and an environmental negative effect parameter, and the site selection cost parameter is determined based on the garbage removal cost parameter and the garbage transfer cost parameter corresponding to the target transfer station.

[0020] In this embodiment, before implementing the site selection method of the embodiment of the present application, target information of multiple candidate transfer stations to be improved into target transfer stations has been obtained, and the corresponding target information includes the location information (latitude and longitude) of the candidate transfer station, the site size of the candidate transfer station, the number of tanks equipped at the candidate transfer station, the capacity of each tank and the surrounding associated garbage collection points; after determining the target information of the candidate transfer station, the site selection planning of the transfer station will be carried out according to the two set objective functions: minimizing the site selection cost of the transfer station and minimizing the total negative environmental effect, that is, configuring multiple candidate transfer station points as the target transfer station to be rebuilt, and then calculating the two objective functions. Then, the optimal site selection scheme of the target transfer station that meets the budget is selected; in this embodiment, the site selection cost parameters include but are not limited to: the collection and transportation cost of garbage collection and transportation (clearance and transfer), the station construction cost, and the operating cost of the target transfer station; the environmental negative effect parameters include but are not limited to the adverse effects of odor, noise, and air pollutants generated by the target transfer station on the permanent residents around the target transfer station; in this embodiment, the candidate points of the transfer station are initialized, that is, random coding is performed, and at least one of the multiple candidate points of the transfer station is randomly configured as the target transfer station. Then, the improved non-dominated sorting genetic algorithm with elite strategy is used. Sorting Genetic Algorithm II, NSGA-II for short) is used to solve until a site selection result that meets the requirements is obtained, that is, a solution that can minimize the values ​​of the two objective functions and convert the transfer station candidate point into a target transfer station is obtained; in this embodiment, a first code corresponds to a genetic coding individual, and a site selection result corresponding to a first code includes configuring at least one transfer station candidate point as a target transfer station, that is, a first code is not a coding result of converting a transfer station candidate point into a target transfer station, but a coding result of converting one or more of a plurality of transfer station candidate points into a target transfer station; at the same time, the first site selection configuration coding array corresponds to a population; in this embodiment, during initialization, the individual of the initialization population size is set to N, and the parent population P corresponding to the first site selection configuration coding array is randomly generated t, set the evolutionary generation t=0, and set various parameters such as the maximum evolutionary generation, population size, and mutation probability.

[0021] It should be noted that, in the present embodiment, there are multiple candidate transfer stations, and the garbage from the garbage collection points can only be transported to a target transfer station nearby (a selected candidate transfer station), and a target transfer station can accept garbage from multiple garbage collection points, and the garbage collection points and transfer stations have a "many-to-one" relationship; while the garbage from a target transfer station can be transported to multiple garbage disposal points, and a garbage disposal point can accept garbage from multiple target transfer stations, and the target transfer station and the garbage disposal point have a "many-to-many" relationship; it can be understood that kitchen waste recycling includes three important links: front-end collection, mid-end collection and transportation, and terminal disposal; the site selection method implemented in the embodiment of the present application is aimed at the mid-end collection and transportation link of kitchen waste, that is, the collection and transportation process from the front-end garbage collection point to the terminal garbage disposal point, and the collection and transportation link is divided into two parts: transportation and transfer. There are three sub-links: the collection and transportation sub-link is responsible for transporting the garbage from the garbage collection points to the target transfer station that has been selected and renovated; the transfer sub-link is responsible for transporting the garbage from the target transfer station to the garbage treatment point; there are many types of garbage collection points for kitchen waste and they are widely distributed, mainly including restaurants in commercial areas, snack bars in food streets, hotel restaurants, canteens, garbage sorting booths (points) in various communities, farmers' markets, etc. The garbage from the garbage collection points can only be transported to the target transfer station by small collection and transportation vehicles (such as platform vehicles, tricycles, and closed pickup trucks) due to the narrow roads. The main purpose of setting up the target transfer station is to reduce the cost of garbage collection and transportation. It is located in the urban area near the garbage collection points and is responsible for the centralized temporary storage of garbage from the surrounding garbage collection points. When the garbage at the target transfer station reaches a certain amount, it will be transported to the final garbage treatment point by large transfer vehicles (such as large tank trucks).

[0022] Step S202, based on the preset improved NSGA-Ⅱ algorithm, non-dominated solution sorting and genetic evolution operation are performed on the first code to generate a mixed site configuration code array, wherein the genetic evolution operation adopts dynamic crossover probability and dynamic mutation probability.

[0023] In this embodiment, after generating a first location configuration coding array including a plurality of first codes, non-dominated solution sorting and genetic evolution operations are sequentially performed on the plurality of first codes; in this embodiment, the non-dominated solution sorting is first performed on the parent population corresponding to the first location configuration coding array, that is, the parent population P is sorted by fast non-dominated sorting. t Each individual in (corresponding to a first code) is graded and the crowding distance is calculated; then, the offspring population Q is generated t , that is, using genetic algorithm to t Each individual in performs genetic operations to produce a descendant population Q t , and then the parent population Pt and the offspring population Q t Merge to obtain the new population R corresponding to the mixed site configuration encoding array t .

[0024] In this embodiment, based on the basic framework of the NSGA-Ⅱ algorithm, the crossover and mutation probabilities, which were originally fixed values, are set to dynamically change values ​​that decrease according to the logsig function as the number of iterations increases, so as to increase the convergence of the population and enable the population to search in the direction of the global optimal solution.

[0025] Step S203, using the elite retention strategy corresponding to the improved NSGA-Ⅱ algorithm, a new population iteration is performed on the mixed location configuration coding array to generate a second location configuration coding array with multiple second codes, wherein the elite retention strategy introduces a mechanism for completing the second code through a crossover mutation operation, and the second code is used to characterize the current location selection result of configuring the transfer station candidate point as the target transfer station.

[0026] In this embodiment, based on the elite retention strategy corresponding to the improved NSGA-Ⅱ algorithm, the next generation population is generated; that is, the new population R is sorted by fast non-dominated sorting. t Each individual (corresponding to a corresponding code) in is graded and the crowding distance is calculated, and the individuals whose crowding distance is the target value (for example, zero) are probabilistically deleted to reduce duplication and increase the diversity of the population; at the same time, if the corresponding codes are insufficient after deletion (the number of individuals is not enough), crossover mutation is performed again based on the corresponding second code to maintain the population size, thereby achieving the new generation of parent population P corresponding to the second location configuration coding array through the elite retention strategy. t+1 In this embodiment, in order to prevent the problem of insufficient number of second codes to be solved, a crossover mutation is introduced into the inner loop to complete the second codes so as to quickly solve the optimal solution.

[0027] Step S204, determine the fitness corresponding to the second code, and according to the fitness, perform non-dominated solution sorting, genetic evolution operation and new population iterative processing based on the elite retention strategy on the second code in the second site selection configuration code array to generate a target site selection configuration code array, and obtain the target code from the target site selection configuration code array to obtain a site selection result, wherein the site selection result includes the target code, and the fitness is determined based on the site selection cost parameters and environmental negative effect parameters associated with the target transfer station corresponding to the second code.

[0028] In this embodiment, after implementing a non-dominated solution sorting, genetic evolution operation and population iteration based on the elite retention strategy for the first code based on the improved NSGA-Ⅱ algorithm, the fitness corresponding to each second code is calculated, that is, the location cost and environmental negative effect parameters associated with the location result corresponding to the second code are calculated, and by judging whether the corresponding location cost and environmental negative effect parameter are the smallest, it is decided to continue to perform non-dominated solution sorting, genetic evolution operation and population iteration based on the elite retention strategy for the currently generated code based on the improved NSGA-Ⅱ algorithm, until the target location configuration code array is generated, and the location result including the target code is obtained.

[0029] Through the above steps S201 to S204, the candidate transfer station candidate points are randomly encoded to generate a first location configuration coding array, which includes multiple first codes; based on the preset improved NSGA-Ⅱ algorithm, the first codes are sorted by non-dominated solutions and genetic evolution operations to generate a mixed location configuration coding array; the elite retention strategy corresponding to the improved NSGA-Ⅱ algorithm is used to iterate the mixed location configuration coding array with a new population to generate a second location configuration coding array with multiple second codes; the fitness corresponding to the second code is determined, and according to the fitness, the second codes in the second location configuration coding array are sorted by non-dominated solutions, genetic evolution operations, and new population iteration processing based on the elite retention strategy are performed to generate a target location configuration coding array, and the target location configuration coding array is obtained from the target location configuration coding array. The target code is encoded and the site selection result including the target code is obtained; by introducing a fast non-dominated sorting algorithm, adopting an elite retention strategy of a mechanism to complete the second code through crossover and mutation operations, and adopting crowding and crowding comparison operators, the computational complexity of the algorithm is reduced, the target code is quickly solved, and the basic framework based on the NSGA-Ⅱ algorithm is adopted to set the crossover and mutation probabilities, which were originally fixed values, to dynamically change values ​​that decrease according to the logsig function as the number of iterations increases, so as to increase the convergence of the population during the iteration process, so that the population searches in the direction of the global optimal solution, so that the configuration cost corresponding to the selected target transfer station and the total negative environmental effect are minimized, and the reconstruction site selection plan of the kitchen waste transfer station is solved. There are problems such as high site selection cost and construction cost, and high collection and transportation cost of the garbage transfer station after reconstruction.

[0030] It should be noted that the embodiment of the present application considers the site selection and optimal configuration method of the kitchen waste transfer station under dual objectives, in order to achieve the dual objectives of minimizing the site selection cost and the negative environmental effect, improve the traditional multi-objective genetic algorithm, increase the number and quality of optimal solutions, and improve the solution speed. The site selection method of the embodiment of the present application is implemented through the following aspects: First, according to the characteristics of kitchen waste collection and transportation, a mixed integer programming model is established to characterize the site selection and optimal configuration problems of the transfer station, and the goal is to minimize the site selection cost (including construction cost, operation cost, transportation cost and transshipment cost) and environmental negative utility of the transfer station; secondly, in view of the fact that the traditional heuristic algorithm for solving multiple objectives is difficult to converge during the solution process and is prone to fall into local optimality, an improved non-dominated sorting genetic algorithm (NSGA-Ⅱ) with an elite strategy is adopted, that is, the crossover and mutation probabilities that were originally fixed values ​​are set to dynamically decreasing values ​​with the number of iterations, thereby increasing the diversity of the population, so that the population searches in the direction of the global optimal solution, and verifies the effectiveness of the improved algorithm.

[0031] In some of the embodiments, based on the preset improved NSGA-Ⅱ algorithm, the first code is subjected to non-dominated solution sorting and genetic evolution operations to generate a mixed location configuration code array, which is achieved by the following steps: Step 21, using a non-dominated sorting algorithm, non-dominated sorting is performed on all first codes, and congestion calculation is performed on all first codes that have completed the non-dominated sorting, to obtain coding parameters corresponding to each first code, wherein the coding parameters include non-dominated sorting parameters and congestion.

[0032] In this embodiment, a non-dominated sorting algorithm corresponding to the improved NSGA-Ⅱ algorithm is used to stratify all first codes into non-dominated layers until all first codes are stratified, thereby obtaining a non-dominated sorting parameter corresponding to each first code, and the non-dominated sorting parameter represents which non-dominated layer the corresponding first code is assigned to; then, the corresponding congestion degree is calculated for the first codes assigned to each non-dominated layer, so that the coding parameters corresponding to each first code are obtained, and a screening parameter is provided for the subsequent selection of the optimal code (corresponding to the first non-dominated code) based on the congestion degree comparison operator.

[0033] It can be understood that the non-dominated solution sorting and congestion calculation involved in the embodiments of the present application are knowable to those skilled in the art, and the corresponding sorting and calculation are known technologies, that is, the non-dominated solution sorting and congestion calculation of the present application do not constitute an unclear limitation on the present application.

[0034] Step 22: Filter out first non-dominated codes from all first codes according to the non-dominated sorting parameter and the congestion degree.

[0035] In this embodiment, after the fast non-dominated sorting and congestion calculation are completed, all first codes have two attribute parameters, namely, the non-dominated sorting parameter and the congestion, wherein the non-dominated order (level, i.e., the level) determined by the non-dominated sorting parameter is defined. According to these two attributes, a congestion comparison operator can be defined, and based on the congestion comparison operator, the corresponding first non-dominated code can be screened out. Specifically, the e-th first code is set to be compared with the g-th first code. If the non-dominated sorting of the e-th first code is better than the non-dominated sorting of the g-th first code, or the e-th first code and the g-th first code have the same non-dominated sorting and the congestion of the e-th first code is greater than the congestion of the g-th first code, then the e-th first code is used as the first non-dominated code. In this way, all first non-dominated codes are screened out from all first codes.

[0036] Step 23, using a preset genetic algorithm, performing a genetic evolution operation on all first codes to generate a preset number of first sub-codes, the genetic evolution operation includes one of the following: tournament selection, crossover, mutation, the crossover probability corresponding to the crossover adopts a dynamic crossover probability generated by a preset gradient decreasing logsig function, and the mutation probability corresponding to the mutation adopts a dynamic mutation probability generated by a preset gradient decreasing logsig function.

[0037] In this embodiment, a genetic algorithm is used to perform genetic operations including selection, crossover and mutation on all first codes to generate a offspring population including multiple first sub-codes; in this embodiment, the probabilities of mutation and crossover are set to dynamically decrease with the number of iterations, thereby increasing the diversity of the population and allowing the population to search in the direction of the global optimal solution.

[0038] Step 24: merge all first non-dominated codes and all first sub-codes to generate a hybrid location configuration code array.

[0039] Through the above steps 21 to 24, the non-dominated solution sorting and genetic evolution operations are performed on the first code based on the improved NSGA-Ⅱ algorithm to generate a mixed location configuration coding array; and by adopting the crowding degree and crowding degree comparison operator, the computational complexity of the algorithm is reduced, so that the individuals (corresponding codes) in the optimal frontier can be evenly expanded to the entire Pareto domain, ensuring the diversity of the population.

[0040] In some of the embodiments, the elite retention strategy corresponding to the improved NSGA-Ⅱ algorithm is used to perform new population iteration on the mixed location configuration encoding array to generate a second location configuration encoding array with multiple second encodings, which is achieved by the following steps: Step 31, using a non-dominated sorting algorithm, non-dominated sorting is performed on the intended codes corresponding to the hybrid location configuration coding array, and congestion calculation is performed on all the intended codes that have completed the non-dominated sorting to obtain the coding parameters corresponding to each intended code.

[0041] In this embodiment, the non-dominated sorting algorithm corresponding to the improved NSGA-Ⅱ algorithm is used to stratify all the intention codes corresponding to the hybrid location configuration coding array into non-dominated layers until all the intention codes are stratified, thereby obtaining the non-dominated sorting parameter corresponding to each intention code, which represents which non-dominated layer the corresponding intention code is assigned to; then the corresponding congestion degree of the intention code assigned to each non-dominated layer is calculated, so as to obtain the coding parameter corresponding to each intention code; in this embodiment, the population R corresponding to the hybrid location configuration coding array is sorted by fast non-dominated sorting. t All individuals in (corresponding to intention codes) are graded and the crowding distance (corresponding to crowding degree) is calculated to obtain the coding parameters corresponding to all intention codes including non-dominated sorting parameters and crowding degree.

[0042] Step 32, according to the non-dominated sorting parameters of the coding parameters corresponding to the intended coding, the first candidate coding is screened out from all the intended codings, and among all the intended codings except the first candidate coding, the intended coding corresponding to the intended coding with the target congestion degree is deleted to obtain the second candidate coding.

[0043] In this embodiment, after the coding parameters of all intended codes are determined, the intended codes are first screened according to the non-dominated sorting parameters, and then the intended codes whose congestion is equal to the target congestion (for example, the congestion is 0) are probabilistically deleted from the remaining intended codes, thereby obtaining the second candidate code.

[0044] In this embodiment, fast non-dominated sorting is used for screening and probabilistic deletion, thereby reducing the duplication of intention codes and increasing the diversity of the population corresponding to the second location configuration code array.

[0045] Step 33, determine whether the sum of the code numbers of the first alternative code and the second alternative code is less than the preset code number threshold, and when it is determined that the sum of the code numbers of the first alternative code and the second alternative code is not less than the preset code number threshold, determine that the second code corresponding to the second address configuration code array includes all the first alternative codes and all the second alternative codes.

[0046] Step 34, when it is determined that the sum of the code numbers of the first alternative code and the second alternative code is less than the preset code number threshold, a genetic algorithm is used to cross and mutate the first alternative code and the second alternative code according to the corresponding dynamic probability to generate a third alternative code with a code number equal to the preset code number threshold, and all third alternative codes are used as the second code corresponding to the second location configuration code array.

[0047] In this embodiment, after probabilistically deleting the intention code of the target congestion, if the number of screened intention codes exceeds the set number, all the screened intention codes are used as the second code corresponding to the second location configuration code array; if the number of screened intention codes is insufficient, the screened intention codes are subjected to inner loop cross-mutation to generate a third alternative code whose number of codes meets the set number, and the second code corresponding to the second location configuration code data is obtained.

[0048] By using the non-dominated sorting algorithm in the above steps, the intention codes corresponding to the mixed location configuration coding array are non-dominatedly sorted, and the congestion degree of all the intention codes that have completed the non-dominated sorting is calculated to obtain the coding parameters corresponding to each intention code; according to the non-dominated sorting parameters of the coding parameters corresponding to the intention codes, the first alternative code is screened out from all the intention codes, and in all the intention codes except the first alternative code, the intention code corresponding to the intention code is deleted The congestion degree is the target congestion degree, and the second alternative code is obtained; it is determined whether the sum of the code numbers of the first alternative code and the second alternative code is less than the preset code number threshold, and when the code numbers of the first alternative code and the second alternative code are determined, When the sum of the code numbers is not less than the preset code number threshold, it is determined that the second code corresponding to the second location configuration code array includes all the first candidate codes and all the second candidate codes; and when it is determined that the sum of the code numbers of the first candidate code and the second candidate code is less than the preset code number threshold, a genetic algorithm is used to cross and mutate the first candidate code and the second candidate code according to the corresponding dynamic probability to generate a third candidate code with a code number of the preset code number threshold, and all the third candidate codes are used as the second code corresponding to the second location configuration code array, so as to achieve the generation of a second location configuration code array with multiple second codes through an elite retention strategy, that is, to generate the next generation population.

[0049] In some embodiments, determining the fitness corresponding to the second encoding is achieved by the following steps: Step 41, determining the target transfer station corresponding to the second code, and based on the location information of the target transfer station, determining the garbage collection point and garbage treatment point associated with each target transfer station.

[0050] In this embodiment, the second code does not only refer to the second code generated by processing the initialized first code based on the improved NSGA-Ⅱ algorithm, but can also be the relevant code generated by performing non-dominated solution sorting, genetic evolution operation and new population iterative processing based on the elite retention strategy on the second code in the second location configuration code array; it can be understood that by calculating the fitness of the corresponding code, it is determined whether to continue to perform non-dominated solution sorting, genetic evolution operation and new population iterative processing based on the elite retention strategy on the currently obtained corresponding code. When the fitness of the current corresponding code meets expectations, the corresponding code is used as the target code.

[0051] Step 42, after determining the total garbage transportation cost corresponding to each target transfer station based on the transportation cost corresponding to each target transfer station and all the garbage collection points associated with it, determine the total garbage transfer cost corresponding to each target transfer station based on the transfer cost between the target transfer station and all the garbage treatment points associated with it, and calculate the site selection cost parameters of each target transfer station based on the construction cost, operation cost, total garbage transportation cost and total garbage transfer cost corresponding to each target transfer station.

[0052] In this embodiment, since the garbage at the garbage collection point is limited to being transported to the target transfer station closest to the garbage collection point, and the garbage treatment point to which the garbage of the target transfer station is transferred also needs to meet certain constraints, therefore, after the transfer station candidate point is pre-configured as the target transfer station, the garbage collection point to which the garbage is transported is also simultaneously confirmed, so that the corresponding transportation cost can be determined, and the garbage treatment point to which the garbage of the target transfer station is transferred can also be determined, that is, the transfer cost corresponding to the corresponding target transfer station can be determined, and in conjunction with the determined construction cost and operation cost of the target transfer station, the site selection cost parameters of the transfer station candidate point configured as the target transfer station can be determined, that is, an objective function corresponding to the corresponding target transfer station, i.e., the total transfer station site selection cost, can be determined.

[0053] Step 43, determine the number of residents around the garbage collection point associated with each target transfer station, the amount of garbage transported from the garbage collection point to the corresponding target transfer station, the arc length distance between the garbage collection point and the target transfer station on the same transportation trajectory circle, the first negative effect impact degree corresponding to the garbage capacity, and the second negative effect impact degree corresponding to the distance, and calculate the environmental negative effect parameters of each target transfer station based on the number of residents, garbage amount, arc length distance, first negative effect impact degree and second negative effect impact degree.

[0054] Step 44, taking the location cost parameter and the negative environmental effect parameter corresponding to each target transfer station as the sub-fitness corresponding to the corresponding target transfer station, and summing the sub-fitnesses of all target transfer stations corresponding to the second code to obtain the fitness corresponding to each second code.

[0055] Through the above steps 41 to 44, the corresponding fitness is calculated according to the two objective functions of the target transfer station, providing data parameters for guiding the corresponding coding whether to continue non-dominated solution sorting, genetic evolution operation and new population iteration based on the elite retention strategy.

[0056] In some embodiments, calculating the site selection cost parameter and the negative environmental effect parameter comprises the following steps: Step 51, calculate the location cost parameter C according to the following formula: .

[0057] Step 52, calculate the negative environmental effect parameter U according to the following formula: .

[0058] In this embodiment, when calculating the site selection cost parameter C and the negative environmental effect parameter U, the corresponding constraints include: (1) The garbage at each garbage collection point can only be unloaded at one target transfer station. The constraint is as follows: .

[0059] (2) The garbage from each target transfer station must be transported to at least one garbage disposal point for treatment. The constraint is as follows: .

[0060] (3) The garbage from the garbage collection point will only be transported to the open target transfer station. The constraint is as follows: .

[0061] (4) Only when the target transfer station is open can the garbage be transported to the garbage disposal point. The constraint is as follows: .

[0062] (5) The removal distance (the distance between the garbage collection point and the target transfer station) is constrained as follows: ; .

[0063] (6) Transfer distance (the distance between the target transfer station and the garbage disposal point), the constraint formula is as follows: ; .

[0064] (7) The actual construction capacity of the target transfer station is greater than or equal to the minimum construction capacity of the transfer station candidate point, and less than or equal to the maximum construction capacity of the transfer station candidate point. The constraint formula is as follows: .

[0065] (8) The construction capacity of the target transfer station is greater than or equal to the total amount of garbage transported from the garbage collection point to the target transfer station. The constraint formula is as follows: .

[0066] (9) The processing capacity of the garbage disposal point is greater than or equal to the total garbage generated by the garbage collection point. The constraint formula is as follows: .

[0067] (10) The material balance relationship of the amount of garbage entering and leaving the target transfer station is as follows: .

[0068] (11) Garbage from the garbage collection point is preferentially transported to the nearest target transfer station for unloading. The constraint is as follows: .

[0069] (12) Garbage from the garbage collection point is preferentially transported to the nearest target transfer station for unloading. The constraint is as follows: .

[0070] (13) The garbage at the target transfer station is preferentially transferred to the nearest garbage disposal point for unloading. The constraint is as follows: .

[0071] (14) The processing capacity of the waste treatment point is greater than the total amount transported from the target transfer station to the waste treatment plant. The constraint is as follows: .

[0072] (15) The amount of garbage generated at the garbage collection point is equal to the amount transported to the garbage disposal point. The constraint is as follows: .

[0073] (16) The tank loading rate of the target transfer station must be greater than or equal to , the constraints are as follows: .

[0074] Wherein, i represents the i-th garbage collection point, I represents the set of garbage collection points, i∈I={1, 2, ..., m}, m represents the number of garbage collection points, and m is a positive integer; j represents the j-th transfer station candidate point, j∈J; h represents the h-th transfer station candidate point, h∈J; J represents the set of transfer station candidate points, J={1, 2, ..., n}, n represents the number of transfer station candidate points, and n is a positive integer; k represents the k-th garbage disposal point, k∈K; r represents the r-th garbage disposal point, r∈K; K represents the set of garbage disposal points, K={1, 2, ..., p}, p represents the number of garbage disposal points, and p is a positive integer; C represents the location cost parameter; C max represents the maximum value of the site selection cost parameter; C1 represents the construction cost of the target transfer station; C2 represents the operating cost of the target transfer station; C3 represents the total garbage collection and transportation cost corresponding to a target transfer station; C4 represents the total garbage transfer cost corresponding to a target transfer station; c1 represents the unit construction cost corresponding to the jth transfer station candidate point after being configured as the target transfer station; c2 represents the unit operating cost corresponding to each target transfer station; c3 represents the unit transportation cost of the collection vehicle transporting garbage from the garbage collection point to the target transfer station; c4 represents the unit transportation cost of the transfer vehicle transporting garbage from the target transfer station to the garbage treatment point; T represents the planned service life of the target transfer station; ;Q j represents the actual construction capacity corresponding to the jth target transfer station, Q j =h j ×Q o ;h j represents the number of tanks stored under the actual construction capacity of the jth target transfer station; Q o Indicates the capacity of a single tank at a candidate transfer station or a target transfer station; ; ; p ij represents the amount of garbage transported from the i-th garbage collection point to the j-th transfer station candidate point every day; d ij represents the arc length distance between the i-th garbage collection point and the j-th transfer station candidate point on the same transportation trajectory circle; d ih represents the arc length distance between the i-th garbage collection point and the h-th transfer station candidate point on the same transportation trajectory circle; D jk represents the arc length distance between the jth transfer station candidate point and the kth garbage disposal point on the same transportation trajectory circle; D jr represents the arc length distance between the jth transfer station candidate point and the rth garbage disposal point on the same conveying trajectory circle; long i Indicates the longitude coordinate of the center point of the i-th garbage collection point; lat i Indicates the latitude coordinate of the center point of the i-th garbage collection point; longi Indicates the longitude coordinate of the center point of the j-th transfer station candidate point; lat j Indicates the latitude coordinate of the center point of the j-th transfer station candidate point; long h Indicates the longitude coordinate of the center point of the h-th transfer station candidate point; lat h Indicates the latitude coordinate of the center point of the h-th transfer station candidate point; long k Indicates the longitude coordinate of the center point of the kth garbage disposal point; lat k Indicates the latitude coordinate of the center point of the kth garbage disposal point; ∆long ij represents the longitude difference between the i-th garbage collection point and the j-th transfer station candidate point; ∆lat ij Indicates the latitude difference between the i-th garbage collection point and the j-th transfer station candidate point; ∆long ih represents the longitude difference between the i-th garbage collection point and the h-th transfer station candidate point; ∆lat ih Indicates the latitude difference between the i-th garbage collection point and the h-th transfer station candidate point; ∆long jk Indicates the longitude difference between the jth transfer station candidate point and the kth garbage disposal point; ∆lat ih Indicates the latitude difference between the jth transfer station candidate point and the kth garbage disposal point; ∆long jr Indicates the longitude difference between the jth transfer station candidate point and the rth garbage disposal point; ∆lat ih represents the latitude difference between the jth transfer station candidate point and the rth garbage disposal point; ; ; U represents the environmental negative benefit parameter; H i represents the number of residents around the garbage collection point; a represents the first negative effect influence degree corresponding to the garbage capacity of the transfer station candidate point or the target transfer station; p jk represents the amount of garbage transported from the jth target transfer station to the kth garbage disposal point every day; b represents the second negative effect influence degree corresponding to the distance between the garbage collection point and the target transfer station or the transfer station candidate point; ∀ represents an arbitrary symbol, ∀i∈I represents that there is any i belonging to I, ∀j∈J represents that there is any j belonging to J, and ∀k∈K represents that there is any k belonging to K; Represents the maximum construction capacity of the jth transfer station candidate point.

[0075] In some of the embodiments, obtaining the target code from the target location configuration code array is achieved by the following steps: Step 61, determining the fitness corresponding to all third codes of each target location configuration code, wherein the third code represents the second code corresponding to the target location configuration code.

[0076] Step 62: Select the third code with the smallest fitness among all the third codes to obtain the target code.

[0077] By determining the fitness corresponding to all third codes of each target site selection configuration code in the above steps, the third code represents the second code corresponding to the target site selection configuration code; among all the third codes, the third code with the smallest fitness is selected to obtain the target code, thereby achieving the site selection result of determining the optimal solution.

[0078] Figure 3 This is a flow chart of the improved NASG-Ⅱ algorithm used in the preferred embodiment of this application, refer to Figure 3 , the process includes the following steps: Step S301, initialization, randomly generating the parent population P t , set the evolutionary generation t=0, then execute step S302.

[0079] In this embodiment, an integer encoding method is selected, the individuals of the initialized population size are set to N, and various parameters such as the maximum evolutionary generation, population size, mutation probability (change rule-function value), etc. are set.

[0080] Step S302, sort the non-dominated solutions of the parent population, and then execute step S303.

[0081] In this embodiment, fast non-dominated sorting is used to sort P t Each individual in is classified and the crowding distance is calculated.

[0082] Step S303: Select, crossover, and mutate to generate a descendant population Q with N individuals. t , then execute step S304.

[0083] In this embodiment, P t Use genetic algorithms (selection, crossover, mutation) to generate offspring population Q t .

[0084] Step S304: Merge P t and Q t Get the new population R t , then execute step S305.

[0085] Step S305: t The individuals are classified into non-dominated solutions and the congestion degree is calculated, and then step S306 is executed.

[0086] Step S306, probabilistically delete R t Among the individuals, the individuals with crowding degree equal to 0, then execute step S307.

[0087] Step S307, determine whether the number of individuals in the population Rt after deleting the individual is ≥ N? If yes, execute step S308, if not, execute step S309.

[0088] Step S308, using the elite retention strategy to select N individuals as the new parent population, then executing step S310.

[0089] Step S309, selection, crossover, and mutation to supplement the insufficient number of individuals, then execute step S308.

[0090] Step S310, generating a new generation of parent population P t+1 , then execute step S311.

[0091] Step S311, update the crossover and mutation probabilities, and then execute step S312.

[0092] Step S312: Is the number of iterations G ≥ the maximum number? If yes, terminate the iteration; if no, after G+1, execute step S302.

[0093] This embodiment also provides a device for optimizing the site selection of a kitchen waste transfer station considering dual objectives, which is used to implement the above-mentioned embodiments and preferred implementation modes, and will not be repeated hereafter. As used below, the terms "module", "unit", "subunit", etc. may be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0094] Figure 4 is a structural block diagram of a device for optimizing the site selection of a kitchen waste transfer station considering dual objectives according to an embodiment of the present application, such as Figure 4 As shown, the device includes an encoding module 41, an operation module 42, a generation module 43 and a processing module 44, wherein: The coding module 41 is used to randomly code the candidate transfer station points to generate a first site selection configuration coding array, wherein the first site selection configuration coding array includes a plurality of first codes, and the first code is used to represent a site selection result of configuring the transfer station candidate point as a target transfer station, and the target transfer station is associated with a site selection cost parameter and an environmental negative effect parameter, and the site selection cost parameter is determined according to a garbage removal cost parameter and a garbage transfer cost parameter corresponding to the target transfer station; The operation module 42 is coupled to the encoding module 41 and is used to perform non-dominated solution sorting and genetic evolution operations on the first encoding based on a preset improved NSGA-Ⅱ algorithm to generate a mixed site configuration encoding array, wherein the genetic evolution operation adopts a dynamic crossover probability and a dynamic mutation probability; The generation module 43 is coupled to the operation module 42 and is used to perform a new population iteration on the mixed location configuration coding array using the elite retention strategy corresponding to the improved NSGA-Ⅱ algorithm to generate a second location configuration coding array with multiple second codes, wherein the elite retention strategy introduces a mechanism for completing the second code through a crossover mutation operation, and the second code is used to represent the location selection result of configuring the transfer station candidate point as the target transfer station at present; The processing module 44 is coupled to the generation module 43, and is used to determine the fitness corresponding to the second code. According to the fitness, the second code in the second site selection configuration code array is sorted by non-dominated solutions, genetic evolution operations and new population iterative processing based on the elite retention strategy to generate a target site selection configuration code array, and obtain the target code from the target site selection configuration code array to obtain a site selection result, wherein the site selection result includes the target code, and the fitness is determined according to the site selection cost parameters and environmental negative effect parameters associated with the target transfer station corresponding to the second code.

[0095] Through the dual-objective kitchen waste transfer station optimization site selection device of the embodiment of the present application, the candidate transfer station candidate points are randomly encoded to generate a first site selection configuration code array, and the first site selection configuration code array includes multiple first codes; based on the preset improved NSGA-Ⅱ algorithm, the first codes are sorted by non-dominated solutions and genetic evolution operations to generate a mixed site selection configuration code array; using the elite retention strategy corresponding to the improved NSGA-Ⅱ algorithm, the mixed site selection configuration code array is iterated with a new population to generate a second site selection configuration code array with multiple second codes; the fitness corresponding to the second code is determined, and according to the fitness, the second codes in the second site selection configuration code array are sorted by non-dominated solutions, genetic evolution operations and new population iterative processing based on the elite retention strategy are performed to generate a target site selection configuration code array, and from the target site selection configuration code The target code is obtained from the array to obtain the site selection result including the target code; by introducing a fast non-dominated sorting algorithm, adopting an elite retention strategy of a mechanism to complete the second code through crossover and mutation operations, and adopting crowding and crowding comparison operators, the computational complexity of the algorithm is reduced, the target code is quickly solved, and the basic framework based on the NSGA-Ⅱ algorithm is adopted to set the crossover and mutation probabilities, which were originally fixed values, to dynamically change values ​​that decrease according to the logsig function as the number of iterations increases, so as to increase the convergence of the population during the iteration process, so that the population searches in the direction of the global optimal solution, so that the configuration cost corresponding to the selected target transfer station and the total negative environmental effect are minimized, and the reconstruction site selection plan of the kitchen waste transfer station is solved. There are problems such as high site selection cost and construction cost, and high collection and transportation cost of the garbage transfer station after reconstruction.

[0096] In some embodiments, the operation module 42 further includes: The first calculation unit is used to perform non-dominated sorting on all first codes by using a non-dominated sorting algorithm, and perform congestion calculation on all first codes that have completed the non-dominated sorting to obtain coding parameters corresponding to each first code, wherein the coding parameters include non-dominated sorting parameters and congestion.

[0097] The screening unit is coupled to the first calculation unit and is used to screen out the first non-dominated codes from all the first codes according to the non-dominated sorting parameter and the congestion degree.

[0098] The operation unit is coupled to the screening unit and is used to use a preset genetic algorithm to perform a genetic evolution operation on all the first codes to generate a preset number of first sub-codes, wherein the genetic evolution operation includes one of the following: tournament selection, crossover, and mutation, wherein the crossover probability corresponding to the crossover adopts a dynamic crossover probability generated by a preset gradient decreasing logsig function, and the mutation probability corresponding to the mutation adopts a dynamic mutation probability generated by a preset gradient decreasing logsig function.

[0099] The generating unit is coupled to the operating unit and is used for merging all the first non-dominated codes and all the first sub-codes to generate a mixed location configuration code array.

[0100] In some embodiments, the generating module 43 further comprises: The second calculation unit is used to use a non-dominated sorting algorithm to perform non-dominated sorting on the intention codes corresponding to the mixed location configuration coding array, and to calculate the congestion of all the intention codes that have completed the non-dominated sorting to obtain the coding parameters corresponding to each intention code.

[0101] The processing unit is coupled to the second computing unit and is used to screen out a first candidate code from all the intended codes according to the non-dominated sorting parameters of the coding parameters corresponding to the intended code, and delete the intended code whose congestion degree corresponding to the intended code is the target congestion degree from all the intended codes except the first candidate code, so as to obtain a second candidate code.

[0102] The judgment unit is coupled to the processing unit and is used to judge whether the sum of the code numbers of the first alternative code and the second alternative code is less than a preset code number threshold, and when it is judged that the sum of the code numbers of the first alternative code and the second alternative code is not less than the preset code number threshold, determine that the second code corresponding to the second location configuration code array includes all the first alternative codes and all the second alternative codes, and when it is judged that the sum of the code numbers of the first alternative code and the second alternative code is less than the preset code number threshold, use a genetic algorithm to cross and mutate the first alternative code and the second alternative code according to the corresponding dynamic probability to generate a third alternative code with a code number of the preset code number threshold, and use all the third alternative codes as the second code corresponding to the second location configuration code array.

[0103] In some embodiments, the processing module 44 is also used to determine the target transfer station corresponding to the second code, and determine the garbage collection point and garbage treatment point associated with each target transfer station based on the location information of the target transfer station; after determining the total garbage transportation cost corresponding to each target transfer station based on the transportation cost corresponding to each target transfer station and all the garbage collection points associated with it, determine the total garbage transfer cost corresponding to each target transfer station based on the transfer cost of the target transfer station and all the garbage treatment points associated with it, and calculate the site selection cost parameters of each target transfer station based on the construction cost, operation cost, total garbage transportation cost and total garbage transfer cost corresponding to each target transfer station; determine each The number of residents around the garbage collection point associated with each target transfer station, the amount of garbage transported from the garbage collection point to the corresponding target transfer station, the arc length distance between the garbage collection point and the target transfer station on the same transportation trajectory circle, the first negative effect influence degree corresponding to the garbage capacity, and the second negative effect influence degree corresponding to the distance; and the environmental negative effect parameters of each target transfer station are calculated based on the number of residents, the amount of garbage, the arc length distance, the first negative effect influence degree and the second negative effect influence degree; the site selection cost parameter and the environmental negative effect parameter corresponding to each target transfer station are used as the sub-fitness corresponding to the corresponding target transfer station, and the sub-fitness of all target transfer stations corresponding to the second code are summed to obtain the fitness corresponding to each second code.

[0104] In some embodiments, the processing module 44 is further configured to calculate the site selection cost parameter C according to the following formula: ; And the negative environmental effect parameter U is calculated according to the following formula: .

[0105] When calculating the site selection cost parameter C and the negative environmental effect parameter U, the corresponding constraints include: ; Wherein, i represents the i-th garbage collection point, I represents the set of garbage collection points, i∈I={1, 2, ..., m}, m represents the number of garbage collection points, and m is a positive integer; j represents the j-th transfer station candidate point, j∈J; h represents the h-th transfer station candidate point, h∈J; J represents the set of transfer station candidate points, J={1, 2, ..., n}, n represents the number of transfer station candidate points, and n is a positive integer; k represents the k-th garbage disposal point, k∈K; r represents the r-th garbage disposal point, r∈K; K represents the set of garbage disposal points, K={1, 2, ..., p}, p represents the number of garbage disposal points, and p is a positive integer; C represents the location cost parameter; C max represents the maximum value of the site selection cost parameter; C1 represents the construction cost of the target transfer station; C2 represents the operating cost of the target transfer station; C3 represents the total garbage collection and transportation cost corresponding to a target transfer station; C4 represents the total garbage transfer cost corresponding to a target transfer station; c1 represents the unit construction cost corresponding to the jth transfer station candidate point after being configured as the target transfer station; c2 represents the unit operating cost corresponding to each target transfer station; c3 represents the unit transportation cost of the collection vehicle transporting garbage from the garbage collection point to the target transfer station; c4 represents the unit transportation cost of the transfer vehicle transporting garbage from the target transfer station to the garbage treatment point; T represents the planned service life of the target transfer station; ;Q j represents the actual construction capacity corresponding to the jth target transfer station, Q j =h j ×Q o ;h j represents the number of tanks stored under the actual construction capacity of the jth target transfer station; Q o Indicates the capacity of a single tank at a candidate transfer station or a target transfer station; ; ; p ij represents the amount of garbage transported from the i-th garbage collection point to the j-th transfer station candidate point every day; d ij represents the arc length distance between the i-th garbage collection point and the j-th transfer station candidate point on the same transportation trajectory circle; d ih represents the arc length distance between the i-th garbage collection point and the h-th transfer station candidate point on the same transportation trajectory circle; D jk represents the arc length distance between the jth transfer station candidate point and the kth garbage disposal point on the same transportation trajectory circle; D jr represents the arc length distance between the jth transfer station candidate point and the rth garbage disposal point on the same conveying trajectory circle; long i Indicates the longitude coordinate of the center point of the i-th garbage collection point; lat i Indicates the latitude coordinate of the center point of the i-th garbage collection point; long iIndicates the longitude coordinate of the center point of the j-th transfer station candidate point; lat j Indicates the latitude coordinate of the center point of the j-th transfer station candidate point; long h Indicates the longitude coordinate of the center point of the h-th transfer station candidate point; lat h Indicates the latitude coordinate of the center point of the h-th transfer station candidate point; long k Indicates the longitude coordinate of the center point of the kth garbage disposal point; lat k Indicates the latitude coordinate of the center point of the kth garbage disposal point; ∆long ij represents the longitude difference between the i-th garbage collection point and the j-th transfer station candidate point; ∆lat ij Indicates the latitude difference between the i-th garbage collection point and the j-th transfer station candidate point; ∆long ih represents the longitude difference between the i-th garbage collection point and the h-th transfer station candidate point; ∆lat ih Indicates the latitude difference between the i-th garbage collection point and the h-th transfer station candidate point; ∆long jk Indicates the longitude difference between the jth transfer station candidate point and the kth garbage disposal point; ∆lat ih Indicates the latitude difference between the jth transfer station candidate point and the kth garbage disposal point; ∆long jr Indicates the longitude difference between the jth transfer station candidate point and the rth garbage disposal point; ∆lat ih represents the latitude difference between the jth transfer station candidate point and the rth garbage disposal point; ; ; U represents the environmental negative benefit parameter; H i represents the number of residents around the garbage collection point; a represents the first negative effect influence degree corresponding to the garbage capacity of the transfer station candidate point or the target transfer station; p jk represents the amount of garbage transported from the jth target transfer station to the kth garbage disposal point every day; b represents the second negative effect influence degree corresponding to the distance between the garbage collection point and the target transfer station or the transfer station candidate point; ∀ represents an arbitrary symbol, ∀i∈I represents that there is any i belonging to I, ∀j∈J represents that there is any j belonging to J, and ∀k∈K represents that there is any k belonging to K; represents the maximum construction capacity of the jth transfer station candidate point; γ represents the transfer coefficient of each transfer station candidate point or target transfer station; S k represents the maximum amount of garbage processed by the kth garbage processing point every day; s jk represents the amount of garbage transported to the kth garbage disposal point after the jth transfer station candidate point is configured as the target transfer station; q i represents the daily garbage output of the i-th garbage collection point; q ijIt represents the amount of garbage that the i-th garbage collection point transports to the j-th target transfer station every day.

[0106] In some of the embodiments, the processing module 44 is also used to determine the fitness corresponding to all third codes of each target site selection configuration code, wherein the third code represents the second code corresponding to the target site selection configuration code; among all the third codes, the third code with the smallest fitness is selected to obtain the target code.

[0107] This embodiment further provides a service platform, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0108] Optionally, the service platform may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0109] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program: S1, randomly encode the candidate transfer station candidate points to generate a first site selection configuration code array, the first site selection configuration code array includes multiple first codes, the first code is used to represent a site selection result of configuring the transfer station candidate point as a target transfer station, the target transfer station is associated with a site selection cost parameter and a negative environmental effect parameter, and the site selection cost parameter is determined based on the garbage removal cost parameter and the garbage transfer cost parameter corresponding to the target transfer station.

[0110] S2, based on the preset improved NSGA-Ⅱ algorithm, performs non-dominated solution sorting and genetic evolution operations on the first code to generate a mixed site configuration coding array. The genetic evolution operation uses dynamic crossover probability and dynamic mutation probability.

[0111] S3, using the elite retention strategy corresponding to the improved NSGA-Ⅱ algorithm, a new population iteration is performed on the mixed location configuration coding array to generate a second location configuration coding array with multiple second codes. The elite retention strategy introduces a mechanism to complete the second code through crossover mutation operations. The second code is used to characterize the current location selection result of configuring the transfer station candidate point as the target transfer station.

[0112] S4, determining the fitness corresponding to the second code, and according to the fitness, performing non-dominated solution sorting, genetic evolution operation and new population iterative processing based on the elite retention strategy on the second code in the second site selection configuration code array to generate a target site selection configuration code array, and obtaining the target code from the target site selection configuration code array to obtain a site selection result, which includes the target code. The fitness is determined based on the site selection cost parameters and environmental negative effect parameters associated with the target transfer station corresponding to the second code.

[0113] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be described in detail here.

[0114] In addition, in combination with the method for optimizing the site selection of a kitchen waste transfer station considering dual objectives in the above embodiments, the present application embodiment can provide a storage medium for implementation. The storage medium stores a computer program; when the computer program is executed by a processor, any one of the methods for optimizing the site selection of a kitchen waste transfer station considering dual objectives in the above embodiments is implemented.

[0115] Those skilled in the art should understand that the technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0116] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A method for optimizing the site selection of a kitchen waste transfer station considering dual objectives, characterized in that: include: Randomly encode the candidate transfer station candidate points to generate a first site selection configuration code array, wherein the first site selection configuration code array includes a plurality of first codes, and the first codes are used to represent a site selection result of configuring the transfer station candidate point as a target transfer station, and the target transfer station is associated with a site selection cost parameter and an environmental negative effect parameter, and the site selection cost parameter is determined according to a garbage removal cost parameter and a garbage transfer cost parameter corresponding to the target transfer station; Based on the preset improved NSGA-Ⅱ algorithm, the first coding is subjected to non-dominated solution sorting and genetic evolution operation to generate a mixed location configuration coding array, wherein the genetic evolution operation adopts dynamic crossover probability and dynamic mutation probability; Using the elite retention strategy corresponding to the improved NSGA-Ⅱ algorithm, a new population iteration is performed on the mixed location configuration coding array to generate a second location configuration coding array with multiple second codes, wherein the elite retention strategy introduces a mechanism for completing the second code through a crossover mutation operation, and the second code is used to represent the current location selection result of configuring the transfer station candidate point as the target transfer station; Determine the fitness corresponding to the second code, and according to the fitness, perform non-dominated solution sorting, genetic evolution operation and new population iterative processing based on the elite retention strategy on the second code in the second site selection configuration code array to generate a target site selection configuration code array, and obtain the target code from the target site selection configuration code array to obtain a site selection result, wherein the site selection result includes the target code, and the fitness is determined based on the site selection cost parameters and environmental negative effect parameters associated with the target transfer station corresponding to the second code.

2. The method according to claim 1, characterized in that Based on the preset improved NSGA-Ⅱ algorithm, the first coding is subjected to non-dominated solution sorting and genetic evolution operations to generate a hybrid site configuration coding array, including: Using a non-dominated sorting algorithm, non-dominated sorting is performed on all the first codes, and congestion calculation is performed on all the first codes that have completed the non-dominated sorting, so as to obtain a coding parameter corresponding to each of the first codes, wherein the coding parameter includes a non-dominated sorting parameter and a congestion degree; Filtering out first non-dominated codes from all the first codes according to the non-dominated sorting parameter and the congestion degree; Using a preset genetic algorithm, a genetic evolution operation is performed on all the first codes to generate a preset number of first sub-codes, wherein the genetic evolution operation includes one of the following: tournament selection, crossover, and mutation, wherein the crossover probability corresponding to the crossover adopts a dynamic crossover probability generated by a preset logsig function with a decreasing gradient, and the mutation probability corresponding to the mutation adopts a dynamic mutation probability generated by a preset logsig function with a decreasing gradient; All of the first non-dominated codes and all of the first sub-codes are combined to generate a mixed location configuration code array.

3. The method according to claim 2, characterized in that Using the elite retention strategy corresponding to the improved NSGA-Ⅱ algorithm, a new population iteration is performed on the hybrid location configuration coding array to generate a second location configuration coding array with multiple second codes, including: Using a non-dominated sorting algorithm, non-dominated sorting is performed on the intended codes corresponding to the hybrid location configuration coding array, and congestion calculation is performed on all the intended codes that have completed the non-dominated sorting to obtain coding parameters corresponding to each intended code; According to the non-dominated sorting parameter of the coding parameter corresponding to the intention code, a first candidate code is screened out from all the intention codes, and from all the intention codes except the first candidate code, the intention code corresponding to the intention code and having the target congestion degree is deleted to obtain a second candidate code; Determine whether the sum of the number of codes of the first alternative code and the second alternative code is less than a preset code number threshold, and when it is determined that the sum of the number of codes of the first alternative code and the second alternative code is not less than the preset code number threshold, determine that the second code corresponding to the second address configuration coding array includes all the first alternative codes and all the second alternative codes.

4. The method according to claim 3, characterized in that When it is determined that the sum of the code numbers of the first alternative code and the second alternative code is less than a preset code number threshold, the method further includes: using the genetic algorithm to cross and mutate the first alternative code and the second alternative code according to the corresponding dynamic probability to generate a third alternative code with a code number that is the preset code number threshold, and using all the third alternative codes as the second code corresponding to the second location configuration code array.

5. The method according to claim 1, characterized in that Determining the fitness corresponding to the second encoding includes: Determine the target transfer station corresponding to the second code, and determine the garbage collection point and garbage disposal point associated with each of the target transfer stations based on the location information of the target transfer stations; After determining the total garbage transportation cost corresponding to each target transfer station according to the transportation cost corresponding to each target transfer station and all the garbage collection points associated therewith, determining the total garbage transfer cost corresponding to each target transfer station according to the transfer cost between the target transfer station and all the garbage treatment points associated therewith, and calculating the site selection cost parameter of each target transfer station based on the construction cost, operation cost, total garbage transportation cost and total garbage transfer cost corresponding to each target transfer station; Determine the number of residents around the garbage collection point associated with each of the target transfer stations, the amount of garbage transported from the garbage collection point to the corresponding target transfer station, the arc length distance between the garbage collection point and the target transfer station on the same transport trajectory circle, the first negative effect influence degree corresponding to the garbage capacity, and the second negative effect influence degree corresponding to the distance, and calculate the environmental negative effect parameters of each of the target transfer stations based on the number of residents, the amount of garbage, the arc length distance, the first negative effect influence degree, and the second negative effect influence degree; The site selection cost parameter and the negative environmental effect parameter corresponding to each of the target transfer stations are used as the sub-fitness corresponding to the corresponding target transfer station, and the sub-fitnesses of all the target transfer stations corresponding to the second code are summed to obtain the fitness corresponding to each of the second codes.

6. The method according to claim 5, characterized in that The site selection cost parameter C is calculated according to the following formula: ； The negative environmental effect parameter U is calculated according to the following formula: ； When calculating the site selection cost parameter C and the negative environmental effect parameter U, the corresponding constraints include: ； Wherein, i represents the i-th garbage collection point, I represents the set of garbage collection points, i∈I={1, 2, ..., m}, m represents the number of garbage collection points, and m is a positive integer; j represents the j-th transfer station candidate point, j∈J; h represents the h-th transfer station candidate point, h∈J; J represents the set of transfer station candidate points, J={1, 2, ..., n}, n represents the number of transfer station candidate points, and n is a positive integer; k represents the k-th garbage disposal point, k∈K; r represents the r-th garbage disposal point, r∈K; K represents the set of garbage disposal points, K={1, 2, ..., p}, p represents the number of garbage disposal points, and p is a positive integer; C represents the location cost parameter; C max represents the maximum value of the site selection cost parameter; C1 represents the construction cost of the target transfer station; C2 represents the operating cost of the target transfer station; C3 represents the total garbage collection and transportation cost corresponding to a target transfer station; C4 represents the total garbage transfer cost corresponding to a target transfer station; c1 represents the unit construction cost corresponding to the jth transfer station candidate point after being configured as the target transfer station; c2 represents the unit operating cost corresponding to each target transfer station; c3 represents the unit transportation cost of the collection vehicle transporting garbage from the garbage collection point to the target transfer station; c4 represents the unit transportation cost of the transfer vehicle transporting garbage from the target transfer station to the garbage treatment point; T represents the planned service life of the target transfer station; ;Q j represents the actual construction capacity corresponding to the jth target transfer station, Q j =h j ×Q o ;h j represents the number of tanks stored under the actual construction capacity of the jth target transfer station; Q o Indicates the capacity of a single tank at a candidate transfer station or a target transfer station; ； ; p ij represents the amount of garbage transported from the i-th garbage collection point to the j-th transfer station candidate point every day; d ij represents the arc length distance between the i-th garbage collection point and the j-th transfer station candidate point on the same transportation trajectory circle; d ih represents the arc length distance between the i-th garbage collection point and the h-th transfer station candidate point on the same transportation trajectory circle; D jk represents the arc length distance between the jth transfer station candidate point and the kth garbage disposal point on the same transportation trajectory circle; D jr represents the arc length distance between the jth transfer station candidate point and the rth garbage disposal point on the same conveying trajectory circle; long i Indicates the longitude coordinate of the center point of the i-th garbage collection point; lat i Indicates the latitude coordinate of the center point of the i-th garbage collection point; long i Indicates the longitude coordinate of the center point of the j-th transfer station candidate point; lat j Indicates the latitude coordinate of the center point of the j-th transfer station candidate point; long h Indicates the longitude coordinate of the center point of the h-th transfer station candidate point; lat h Indicates the latitude coordinate of the center point of the h-th transfer station candidate point; long k Indicates the longitude coordinate of the center point of the kth garbage disposal point; lat k Indicates the latitude coordinate of the center point of the kth garbage disposal point; ∆long ij represents the longitude difference between the i-th garbage collection point and the j-th transfer station candidate point; ∆lat ij Indicates the latitude difference between the i-th garbage collection point and the j-th transfer station candidate point; ∆long ih represents the longitude difference between the i-th garbage collection point and the h-th transfer station candidate point; ∆lat ih Indicates the latitude difference between the i-th garbage collection point and the h-th transfer station candidate point; ∆long jk Indicates the longitude difference between the jth transfer station candidate point and the kth garbage disposal point; ∆lat ih Indicates the latitude difference between the jth transfer station candidate point and the kth garbage disposal point; ∆long jr Indicates the longitude difference between the jth transfer station candidate point and the rth garbage disposal point; ∆lat ih represents the latitude difference between the jth transfer station candidate point and the rth garbage disposal point; ； ; U represents the environmental negative benefit parameter; H i represents the number of residents around the garbage collection point; a represents the first negative effect influence degree corresponding to the garbage capacity of the transfer station candidate point or the target transfer station; p jk represents the amount of garbage transported from the jth target transfer station to the kth garbage disposal point every day; b represents the second negative effect influence degree corresponding to the distance between the garbage collection point and the target transfer station or the transfer station candidate point; ∀ represents an arbitrary symbol, ∀i∈I represents that there is any i belonging to I, ∀j∈J represents that there is any j belonging to J, and ∀k∈K represents that there is any k belonging to K; represents the maximum construction capacity of the jth transfer station candidate point; γ represents the transfer coefficient of each transfer station candidate point or target transfer station; S k represents the maximum amount of garbage processed by the kth garbage processing point every day; s jk represents the amount of garbage transported to the kth garbage disposal point after the jth transfer station candidate point is configured as the target transfer station; q i represents the daily garbage output of the i-th garbage collection point; q ij It represents the amount of garbage that the i-th garbage collection point transports to the j-th target transfer station every day.

7. The method according to claim 5, characterized in that Obtaining a target code from the target location configuration code array includes: Determine the fitness corresponding to all third codes of each target location configuration code, wherein the third code represents the second code corresponding to the target location configuration code; Among all the third codes, the third code with the smallest fitness is selected to obtain the target code.

8. A dual-objective kitchen waste transfer station optimization site selection device, characterized in that: include: A coding module, used for randomly coding the candidate transfer station points to generate a first site selection configuration coding array, wherein the first site selection configuration coding array includes a plurality of first codes, the first codes are used to represent a site selection result of configuring the transfer station candidate point as a target transfer station, the target transfer station is associated with a site selection cost parameter and an environmental negative effect parameter, and the site selection cost parameter is determined according to a garbage removal cost parameter and a garbage transfer cost parameter corresponding to the target transfer station; An operation module, used for performing non-dominated solution sorting and genetic evolution operation on the first coding based on a preset improved NSGA-Ⅱ algorithm to generate a mixed site configuration coding array, wherein the genetic evolution operation adopts a dynamic crossover probability and a dynamic mutation probability; A generation module, used to use the elite retention strategy corresponding to the improved NSGA-Ⅱ algorithm to perform a new population iteration on the mixed location configuration coding array to generate a second location configuration coding array with multiple second codes, wherein the elite retention strategy introduces a mechanism for completing the second codes through crossover mutation operations, and the second codes are used to represent the current location selection result of configuring the transfer station candidate point as the target transfer station; A processing module is used to determine the fitness corresponding to the second code, and according to the fitness, perform non-dominated solution sorting, genetic evolution operation and new population iterative processing based on the elite retention strategy on the second code in the second site selection configuration code array to generate a target site selection configuration code array, and obtain the target code from the target site selection configuration code array to obtain a site selection result, wherein the site selection result includes the target code, and the fitness is determined based on the site selection cost parameter and the negative environmental effect parameter associated with the target transfer station corresponding to the second code.

9. A service platform, comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps of the method for optimizing the site selection of a kitchen waste transfer station considering dual objectives as described in any one of claims 1 to 7.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for optimizing the site selection of a kitchen waste transfer station considering dual objectives as described in any one of claims 1 to 7 is implemented.

Images