Hazardous waste transportation treatment method, device and equipment based on Internet of Things and storage medium

Abstract

The invention discloses a hazardous waste transportation treatment method, device and equipment based on the Internet of Things and a storage medium, and relates to the technical field of hazardous waste transportation treatment. The method is characterized by comprising the following steps: determining an objective function and constraint conditions of a hazardous waste transportation path optimization problem; performing optimization solution on the dangerous waste transportation path optimization problem by using an improved genetic algorithm to obtain an optimal dangerous waste transportation path; wherein the traditional genetic algorithm is improved by improving a fitness function, a selection operator combining a self-adaptive elitism strategy and a roulette selection strategy, a self-adaptive crossover probability and a self-adaptive mutation probability. Experimental results show that the improved genetic algorithm accelerates the convergence speed and improves the performance of the algorithm while ensuring convergence to an optimal solution. The superiority of the method in the economic level can provide reference for construction of a hazardous waste recovery system, and algorithm enabling is achieved for more cities on the basis of construction of an informatization hazardous waste management platform.

Description

Technical Field

[0001] The present invention relates to the technical field of hazardous waste transportation and treatment, and in particular to a hazardous waste transportation and treatment method, device, equipment and storage medium based on the Internet of Things. Background Art

[0002] The disadvantages of paper forms in the process of hazardous waste transfer are gradually becoming apparent: first, the hazardous waste transfer form itself is complex in design and cumbersome to fill out. There are many links in the review and transmission of the transfer form during the transfer, which has resulted in a lot of manpower, material resources and time for regulatory departments, waste-producing units and disposal units. With the current staffing, it is impossible to verify the amount of transfer out and in through the form, and the transfer form actually only serves as a receipt for transportation; second, as a paper form, the transfer form itself has low technical content and is easy to obtain. Some illegal units and individuals, for the purpose of profit, make and sell fake forms and buy and sell real forms, disrupting the management of hazardous waste; third, the actual generation and disposal of waste by waste-producing units and operating units cannot be obtained in a timely and authentic manner. At the same time, the data fraud of hazardous waste management personnel of waste-producing and operating units occasionally occurs, and the scientific and technological management methods are insufficient, resulting in the passive state of hazardous waste environmental supervision.

[0003] In order to avoid the above-mentioned drawbacks and create a good environment for hazardous waste transfer management, the construction of hazardous waste transfer system is necessary and urgent. Now, the concept of Internet of Things (IOT) no longer refers to wireless sensor networks based on RFID technology. Its definition and coverage have overturned the traditional thinking of mankind and integrated basic physical facilities with IT infrastructure. According to the internationally recognized definition of Internet of Things, IOT is a network that connects any object to the Internet through information sensing devices such as radio frequency identification (RFID), infrared sensors, GPS, laser scanners, etc., in accordance with agreed protocols, to exchange information and communicate, so as to realize intelligent identification, positioning, tracking, monitoring and management of objects.

[0004] The scope of hazardous waste management covers all aspects of the entire life cycle of hazardous waste, from participating in production activities to storage, transportation, and finally to disposal. There are many reasons for the risk to the environment. Whether it is due to improper technical disposal or incorrect business management, there is a possibility of hazardous waste leakage, and ultimately cause environmental pollution. In the existing technology, the hazardous waste transportation and treatment methods have the following shortcomings: the path planning is not safe enough. Most methods directly seek the shortest path based on time, distance and cost, without considering risk factors, and lack effective and comprehensive hazardous waste transportation risk assessment methods and means; the real-time performance of path planning is low: when the environment or scene changes or an emergency occurs, it cannot be quickly adjusted dynamically, and it is impossible to provide timely and effective optimal path guidance for hazardous waste transportation vehicles; the basic path data is updated too low, resulting in a lag in the path planning results, and the optimal path cannot be output in time.

[0005] Therefore, how to reasonably plan the transportation route of hazardous waste is an important prerequisite for ensuring the minimum risk in the transportation process of hazardous waste. Summary of the invention

[0006] In view of the above problems, the present invention proposes a hazardous waste transportation and treatment method, device, equipment and storage medium based on the Internet of Things, in an effort to solve or alleviate one or more of the above problems.

[0007] According to one aspect of the present invention, a method for transporting and treating hazardous waste based on the Internet of Things is proposed, the method comprising the following steps:

[0008] S1. Determine the objective function and constraints of the hazardous waste transportation route optimization problem;

[0009] S2. Utilize an improved genetic algorithm to optimize and solve the hazardous waste transportation route optimization problem, and obtain the optimal hazardous waste transportation route.

[0010] In one possible implementation, the objective function of the hazardous waste transportation route optimization problem described in S1 is established as follows:

[0011] Min F=f1+f2+f3

[0012] In the formula, Min means minimization, f1 represents the fixed cost of hazardous waste recycling; f2 represents the hazardous waste transportation cost; f3 represents the hazardous waste time penalty cost;

[0013] The constraints of the hazardous waste transportation route optimization problem are established as follows:

[0014]

[0015] Where m represents the total number of hazardous waste production units; g irepresents the demand for hazardous waste disposal by hazardous waste production unit i; y ik The hazardous waste produced by hazardous waste production unit i is transported by transport vehicle k, y ik ∈[0,1]; Q represents the maximum load of hazardous waste recycling vehicles; n represents the total number of transport vehicles; x ijk represents the transport vehicle k from hazardous waste production unit i to hazardous waste production unit j, x ijk ∈[0,1]; y jk The hazardous waste produced by hazardous waste production unit j is transported by transport vehicle k; x i0k and x 0jk It means that each transport vehicle k needs to return after leaving the transport company and completing the disposal; It means that there is only one hazardous waste production unit connected to the path p of each hazardous waste production unit i or j; t i represents the time of arrival at hazardous waste production unit i; l i It represents the limited time of the right time window specified for hazardous waste production unit i.

[0016] In one possible implementation, the fixed cost f1 of hazardous waste recycling in S1 is expressed as:

[0017]

[0018] The hazardous waste transportation cost f2 is expressed as:

[0019]

[0020] The hazardous waste time penalty cost f3 is expressed as:

[0021]

[0022] Where c1 represents the fixed cost of hazardous waste transportation vehicles; z k indicates that hazardous waste transport vehicle k is used; c2 represents the transportation cost per kilometer of hazardous waste recycling vehicles; d ij represents the distance of the vehicle from hazardous waste production unit i to hazardous waste production unit j; ε1 and ε2 represent the time cost penalty factors; represents the time when the kth vehicle arrives at hazardous waste production unit i; [Et a ,Et b ]=[e i +λ,l i +λ],e i represents the left time window specified by hazardous waste production unit i; λ represents the relaxation of the time window.

[0023] In one possible implementation, the optimizing solution of the hazardous waste transportation path optimization problem by using an improved genetic algorithm in S2 includes:

[0024] S21, initialize and set the population size, initial number of iterations, maximum number of iterations, number of selected individuals, and probability P of retaining elite individuals s , crossover probability P cmax ,P cmin and mutation probability P mmax ,P mmin ;

[0025] S22, real number encoding is performed on the individuals in the population, and an initial population is randomly generated;

[0026] S23, calculating the fitness function value of each individual x; wherein the fitness function value is calculated by a fitness function that adaptively changes dynamically based on the number of iterations;

[0027] S24, selection operation: adopt the dynamic elite retention strategy combined with roulette wheel to select, and replace the last t individuals in the population after crossover mutation with the selected t individuals; let the retained individuals and the offspring individuals participate in the competition together in the next iteration;

[0028] S25, crossover operation: use a single-point crossover method to perform crossover according to the crossover probability calculation formula;

[0029] S26, mutation operation: using the basic bit mutation method to perform mutation according to the mutation probability calculation formula;

[0030] S27, determine whether the stop condition is met, if so, output the optimal solution, otherwise continue to repeat from S23.

[0031] In one possible implementation, the formula of the fitness function based on the adaptive dynamic change of the number of iterations in S23 is:

[0032] F'(x)=e -aF(x)

[0033] Where, F'(x) is the fitness function after exponential transformation, F(x) is the objective function, F(x) = f1+f2+f3; a s is the preset starting value of a, k is the adjustment factor, g is the current number of iterations, G is the maximum number of iterations, F(x) avg is the average value of the population objective function, and ε is a number infinitely close to 0.

[0034] In one possible implementation, the dynamic elite retention strategy combined with roulette wheel selection described in S24 is used to replace the last t individuals in the population after crossover mutation with the selected t individuals, including:

[0035] S241. Determine the number of individuals to be selected as t, and the proportion of elite retained individuals to the population size as P s , the number of elite retained individuals is n, and the size of n is determined according to the following formula:

[0036]

[0037] Where, t≥n; ceil is the floor rounding function, N is the population size;

[0038] S242, calculating the fitness function values ​​of all individuals in the population, and sorting them from large to small according to the values;

[0039] S243. Select the first n individuals as elite individuals and directly copy them to the next generation. The probability formula for each individual to be selected is as follows:

[0040]

[0041] Among them, P i is the probability of the i-th individual being selected;

[0042] S244, calculating the sum of fitness functions of the remaining individuals in the population, and calculating the probability of each individual in the population being selected;

[0043] S245. The remaining individuals are combined into a roulette wheel according to the probability of being selected, and a number is directly randomly generated in [0,1], and the probability size in the roulette wheel is subtracted in sequence. If the probability difference after subtracting a certain individual is negative, the individual is selected to enter the next generation population;

[0044] S246. Repeat S245 tn times.

[0045] In one possible implementation, the crossover probability calculation formula in S25 is:

[0046]

[0047] Where P cmax , P cmin are the maximum and minimum values ​​of the crossover probability respectively; f' is the value of the individual with the larger fitness function value in the two crossover objects; f avg is the average value of the current population;

[0048] The mutation probability calculation formula in S26 is:

[0049]

[0050] Where P mmax , P mmin are the maximum and minimum values ​​of the mutation probability respectively; f is the value of the individual to be mutated.

[0051] According to another aspect of the present invention, a hazardous waste transportation and treatment device based on the Internet of Things is provided, the device comprising:

[0052] a route optimization model building module configured to determine an objective function and constraints for a hazardous waste transportation route optimization problem;

[0053] The optimal path solving module is configured to use an improved genetic algorithm to optimize and solve the hazardous waste transportation path optimization problem to obtain the optimal path for hazardous waste transportation.

[0054] According to another aspect of the present invention, an electronic device is proposed, comprising: a memory; a processor; and a computer program; wherein the computer program is stored in the memory and is configured to be executed by the processor to implement the hazardous waste transportation and processing method as described above.

[0055] According to another aspect of the present invention, a computer-readable storage medium is provided, on which a computer program is stored; the computer program is executed by a processor to implement the hazardous waste transportation and processing method as described above.

[0056] The beneficial technical effects of the present invention are:

[0057] The present invention proposes a method, device, equipment and storage medium for hazardous waste transportation and treatment based on the Internet of Things, that is, on the basis of constructing a hazardous waste recycling management system based on the Internet of Things technology, a recycling vehicle path optimization model based on an improved genetic algorithm is constructed for the path optimization problem of hazardous waste recycling. The traditional genetic algorithm is improved by improving the fitness function, the selection operator combining the adaptive elite retention strategy with the roulette selection strategy, the adaptive crossover probability and the adaptive mutation probability. The traditional genetic algorithm, the hybrid genetic algorithm and the improved genetic algorithm of the present invention are used for comparison respectively. The results show that it is difficult for the traditional genetic algorithm to jump out of the local optimum when it falls into the local optimal solution, resulting in low solution quality. The hybrid genetic algorithm has been greatly improved and can converge to most functions; while the improved genetic algorithm of the present invention accelerates the convergence speed while ensuring convergence to the optimal solution, thereby improving the performance of the algorithm. The superiority of the present invention at the economic level can provide a reference for the construction of hazardous waste recycling systems, and enable more cities to realize algorithm empowerment on the basis of building an information-based hazardous waste management platform. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] The above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood by reading the detailed description below with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, in which:

[0059] Figure 1 The present invention is a flowchart of a method for transporting and treating hazardous waste based on the Internet of Things according to an embodiment of the present invention.

[0060] Figure 2 This is an example diagram of the changes in crossover probability and mutation probability in an embodiment of the present invention.

[0061] Figure 3 This is an example diagram comparing the total cost optimization efficiency of various algorithms in the embodiments of the present invention.

[0062] Figure 4 The figure is a schematic diagram of the structure of a hazardous waste transportation and treatment device based on the Internet of Things according to an embodiment of the present invention.

[0063] Figure 5 FIG. 1 is a schematic diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0064] The principles and spirit of the present invention will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided only to enable those skilled in the art to better understand and implement the present invention, and are not intended to limit the scope of the present invention in any way. On the contrary, these embodiments are provided to make the present disclosure more thorough and complete, and to fully convey the scope of the present disclosure to those skilled in the art.

[0065] Those skilled in the art know that the embodiments of the present invention can be implemented as a system, device, equipment, method or computer program product. Therefore, the present disclosure can be specifically implemented in the following forms, namely: complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software. In this article, it is to be understood that any number of elements in the drawings is for illustration and not limitation, and any naming is only for distinction and does not have any limiting meaning.

[0066] Hazardous wastes in a broad sense refer to wastes with any one or more hazardous properties such as corrosiveness, toxicity, flammability, reactivity, and infectiousness, or substances that do not exclude hazards to the environment and human health. Substances that meet any of the above conditions can be defined as hazardous wastes. The toxic and harmful substances contained in hazardous wastes may pose a potential threat to humans and the environment. If they are not specially controlled, once they become potentially harmful, they may cause poisoning of humans and animals and cause serious pollution accidents. The leakage of hazardous wastes will infiltrate the surface through rainwater and pollute the soil and groundwater, endangering the safety of groundwater and drinking water and seriously threatening human health. The leaked harmful substances will cause a variety of untreatable diseases in the surrounding people; the surrounding cultivated soil will be contaminated and cannot be cultivated. Therefore, the scientific management and treatment and disposal of hazardous wastes are particularly important under the initiative of ecological civilization construction, which can avoid the potential impact of hazardous wastes on society and the environment.

[0067] Hazardous waste recycling is a complex transportation organization process, which includes waste-generating units, transporting units and disposal units. The present invention starts from the perspective of a hazardous waste disposal platform developed based on the Internet of Things system, and optimizes multiple recycling routes under a transportation network with a unique starting and ending point for hazardous waste recycling under given recycling needs in the spirit of economy, safety, efficiency and timeliness. While giving priority to time efficiency and not considering costs, point-to-point dispatching of vehicles to all waste-generating unit nodes can achieve the highest transfer efficiency, which will result in high costs and large carbon emissions. When giving priority to economic costs and reducing dispatching vehicles to achieve point-to-multiple, it will lead to low transfer efficiency and users will lose dependence.

[0068] The optimization problem of hazardous waste recycling routes can be specifically described as follows: multiple waste-producing units report the type, volume and quality of hazardous waste to the platform. After collecting the cumulative processing tasks, the platform dispatches the corresponding fleet to recycle the scattered waste-producing units and finally sends them to the disposal units. Combined with the demand nodes and logistics basis in the transportation network, the recycling vehicle starts from the starting point P, passes through multiple waste-producing nodes M, and then recycles to the disposal point C. The transportation network between points P, M, and C forms N transportation routes that can be used as system options, but there are differences in time cost, transportation cost, and carbon emissions under different routes and trips.

[0069] Although carbon emissions are positively correlated with transportation costs without considering transfer points and multimodal transport, as carbon trading becomes popular in the future, carbon emission taxes will become part of corporate operating costs. Therefore, the present invention takes this emission into consideration but does not use it as an optimization target value for the time being. In addition, hazardous waste exists in different forms of liquid and solid, and transportation vehicles need to be equipped with storage tanks of different sizes to meet the storage of different liquids and achieve solid-liquid mixing. Therefore, there will be differences in the transfer space. The facilities and conditions of the service companies that provide services to the platform will also directly affect the transfer and disposal of hazardous waste. For example, if the transportation company's transfer vehicles are old and have poor energy-saving effects and slow transfer efficiency, the transfer time will be too long and the time window will be missed, resulting in increased costs. Therefore, adding an Internet of Things system to all equipment to make the transportation network information-based is a prerequisite for achieving an efficient recycling system.

[0070] The IoT system is named as the IoT platform for the whole process of hazardous waste supervision and treatment. It can be designed as a three-layer architecture, storage layer, data processing layer, and application layer. According to the application scenario, it can be divided into four layers: user layer, operation tool layer, cloud platform, and sensor device layer. Among them, the user layer is the decision-making subject of the optimization of the hazardous waste recycling path. It is centered on the objective physical world and faces various applications of customers. It provides interfaces between applications on any end of the network. It is mainly divided into three parties, namely, hazardous waste producers, hazardous waste carriers, and hazardous waste disposal parties. Hazardous waste producers are generally enterprises; hazardous waste carriers, after receiving orders from hazardous waste producers, sign contracts and complete the contract. According to the requirements of the customer waste producer, select a reasonable transportation plan and deliver the goods to the disposal unit or transfer station in time within the specified time. Therefore, the carrier is the key to path optimization. The carrier should try its best to expand profits and reduce losses on the premise of satisfying the waste producer; the hazardous waste disposal party is a recycling unit with qualifications for disposing special pollutants and hazardous waste. After receiving the hazardous waste transported by the carrier, it will dispose of it, thereby completing the closed loop of the hazardous waste recycling system. The operation tool layer is responsible for connecting the data collected by the perception layer to access networks such as Ethernet, wireless networks or satellite clusters, and then transporting data over long distances through transmission networks such as mobile communication networks, the Internet or dedicated networks. At the same time, it transmits instructions to the perception layer, thereby completing extensive processing and transmission of the physical world and realizing application and control of objects. The cloud platform is designed to process and analyze the collected data for effective integration and utilization. The sensor device layer mainly uses sensors, QR codes, GPS, radio frequency devices, etc. to collect and conduct preliminary analysis of data on the measured object and its surrounding environment.

[0071] Therefore, the embodiment of the present invention proposes a method for transporting and treating hazardous waste based on the Internet of Things, such as Figure 1 As shown, the method includes:

[0072] S1. Determine the objective function and constraints of the hazardous waste transportation route optimization problem;

[0073] S2. Utilize an improved genetic algorithm to optimize and solve the hazardous waste transportation route optimization problem, and obtain the optimal hazardous waste transportation route.

[0074] The present invention is described in detail below.

[0075] The method starts from S1. In S1, the objective function and constraints of the hazardous waste transportation route optimization problem are determined.

[0076] According to an embodiment of the present invention, the hazardous waste transportation route optimization problem is described as follows: The time window path planning problem is to plan a path from the starting point through each node and then back to the starting point based on the determined location information. The hazardous waste recycling path optimization problem is a static path planning problem. After building an avoidance path matrix based on existing nodes, the hazardous waste recycling path of static demand is planned after meeting the vehicle carrying restrictions, time window restrictions, road restrictions and other restrictions. The optimization plan for hazardous waste path recycling that meets the needs of all waste-producing units is planned, and the recycling cost is minimized.

[0077] It is assumed that the transport vehicles travel at a constant speed and traffic congestion is not considered; the locations of garages, waste-generating units and disposal units are known; the quantities of hazardous wastes entrusted for disposal by different waste-generating units are the same or different; there is no problem of violent reactions between different hazardous wastes that prevent them from being transported at the same time; each customer point can only be recycled and transported by one transport vehicle, and the amount of hazardous waste from the waste-generating units is known; one transport vehicle can serve multiple waste-generating units; the time window constraint set by the waste-generating units is a soft time window, that is, there is a penalty cost for the recycling vehicles to arrive early or late; the transport vehicles used by the carrier are of the same model and meet the relevant requirements for hazardous waste transportation management. The amount of hazardous waste transported does not exceed the rated load and space limit of the recycling vehicle, and the vehicle's endurance is not considered.

[0078] Therefore, a total cost minimization model for the recycling process is constructed, and the recycling cost includes the recycling fixed cost, the recycling vehicle transportation cost and the time penalty cost.

[0079] 1) Fixed cost of hazardous waste recycling: The fixed cost of recycling vehicles comes from recycling vehicles. Fixed costs are incurred when each recycling mission starts, including the repair costs, maintenance costs, insurance costs, and wages of recycling personnel. The hazardous waste recycling company uses n recycling vehicles with the same cargo capacity. When there are m waste units, the fixed cost of vehicles involved in hazardous waste recycling during the recycling process can be reflected as function f1:

[0080]

[0081] Where c1 represents the fixed cost of hazardous waste transportation vehicles; z k indicates that hazardous waste transport vehicle k is used, z k ∈[0,1].

[0082] 2) Hazardous waste recycling transportation cost: refers to the sum of the transportation costs incurred by each recycling vehicle during the transportation process. The transportation cost is positively correlated with the driving distance of the recycling vehicle, and will be affected by changes in multiple factors such as oil prices, cargo load ratio, and maintenance costs. Transportation costs include fixed personnel costs, vehicle operating costs, and energy consumption costs; among them, fixed personnel costs include basic wages, insurance, bonuses and benefits, labor insurance, fees, and comprehensive subsidies; vehicle operating costs include depreciation, maintenance costs, insurance premiums, tire fees, tolls, etc.; energy consumption costs include electricity and fuel costs. Therefore, assuming that the variable cost of hazardous waste recycling vehicles per kilometer is c2, the transportation cost of recycling vehicles can be reflected as function f2:

[0083]

[0084] Where c2 represents the transportation cost per kilometer of hazardous waste recycling vehicles; d ij represents the distance of the vehicle from hazardous waste production unit i to hazardous waste production unit j; x ijk represents the transport vehicle k from hazardous waste production unit i to hazardous waste production unit j, x ijk ∈[0,1].

[0085] 3) Time cost of hazardous waste recycling: In order to optimize the efficiency of hazardous waste recycling and the satisfaction of waste-producing units, a soft time window constraint is set to constrain the delivery vehicles to arrive on time through early and late penalties. The establishment unit stipulates that [e, l] is the operation time, and the penalty function is P(t). The recycling vehicle will be penalized if it arrives between [m, e) and (l, n]. The longer the early or late arrival time, the higher the penalty time cost. However, there will be no penalty for delivery within [e, l].

[0086] If the carrier arrives at the waste generating unit too early, it will affect the work arrangement of the waste generating unit. If it arrives at the waste generating unit too late, the waste generating unit will have a poor evaluation of the recycling efficiency. Therefore, the soft time window is used as a constraint to measure the punctuality of the hazardous waste recycling vehicle's door-to-door waste recycling. When the recycling vehicle arrives at the waste generating unit too early or overdue within the specified time interval, a corresponding penalty will be given. The time penalty cost function can be expressed as f3:

[0087]

[0088] Where ε1 and ε2 represent time cost penalty factors; represents the time when the kth vehicle arrives at hazardous waste production unit i; [Eta ,Et b ]=[e i +λ,l i +λ],e i represents the left time window specified by hazardous waste production unit i; λ represents the relaxation of the time window.

[0089] Therefore, the objective function of the minimum cost model for hazardous waste recycling is expressed as:

[0090] Min F=f1+f2+f3

[0091] In the formula, Min means minimization, f1 represents the fixed cost of hazardous waste recycling; f2 represents the hazardous waste transportation cost; and f3 represents the time penalty cost of hazardous waste.

[0092] The constraints are: the amount of hazardous waste transported cannot exceed the maximum loading weight of the vehicle; each waste-producing unit can only be recycled by one vehicle; each waste-producing unit can only be on one recycling route; all waste-producing units have recycling vehicles responsible for recycling; each recycling vehicle must return to the carrier company after completing disposal from the carrier company; each waste-producing unit's route has only one waste-producing unit connected to it; the time to reach a certain waste-producing unit cannot exceed the time limit of the right time window specified by the waste-producing unit.

[0093] The formula is:

[0094]

[0095] Where m represents the total number of hazardous waste production units; g i represents the demand for hazardous waste disposal by hazardous waste production unit i; y ik The hazardous waste produced by hazardous waste production unit i is transported by transport vehicle k, y ik ∈[0,1]; Q represents the maximum load of hazardous waste recycling vehicles; n represents the total number of transport vehicles; x ijk represents the transport vehicle k from hazardous waste production unit i to hazardous waste production unit j, x ijk ∈[0,1]; y jk The hazardous waste produced by hazardous waste production unit j is transported by transport vehicle k; x i0k and x 0jk It means that each transport vehicle k needs to return after leaving the transport company and completing the disposal; It means that there is only one hazardous waste production unit connected to the path p of each hazardous waste production unit i or j; t i represents the time of arrival at hazardous waste production unit i; l i It represents the limited time of the right time window specified for hazardous waste production unit i.

[0096] Then, S2 is executed. In S2, the hazardous waste transportation path optimization problem is optimized and solved using an improved genetic algorithm to obtain the optimal hazardous waste transportation path.

[0097] According to the embodiment of the present invention, the vehicle path optimization problem for hazardous waste recycling has been described in S1 as a single-objective, soft-time-window, static-demand closed type. For solving the path optimization problem, after referring to the pros and cons of various algorithms and their adaptability to the present invention, the present invention decides to use metaheuristic algorithms as the research basis. Such algorithms have good performance in terms of solution speed and solution scope, and can be used in various extensive path optimization problems with unclear paths, unclear road conditions, multiple nodes, and multiple demands.

[0098] The Genetic Algorithm (GA) was first proposed in 1975. The algorithm draws on Darwin's theory of biological evolution and forms a new type of optimization algorithm based on the biological evolution laws of "genetic inheritance" and "natural selection" in nature. The idea of ​​the genetic algorithm is "survival of the fittest". Since the resources in nature are limited, when the population reaches a certain size, the resources can no longer meet the survival needs of all individuals in the population, forcing the individuals in the population to compete with each other. In the competition, excellent individuals are retained and inferior individuals are eliminated. At the same time, when individuals reproduce offspring, genes may mutate, thus forming a new individual.

[0099] Although genetic algorithms have good global search capabilities, due to the fixed algorithm parameters, it is difficult to converge to the optimal solution when solving many complex problems, resulting in local optimal solutions. To overcome this shortcoming, adaptive genetic algorithms were created. Adaptive genetic algorithms not only have all the characteristics of basic genetic algorithms, but also have strong global and local search capabilities, and are more effective when dealing with complex problems. However, adaptive genetic algorithms rely heavily on the choice of fitness functions, which makes it difficult to determine the fitness function and increases the amount of calculation. When adjusting parameters, it is necessary to calculate the fitness function values ​​of all individuals in the population, which may eventually lead to poor stability of the algorithm, making it difficult for the algorithm to converge or converge prematurely.

[0100] Therefore, the embodiment of the present invention improves the adaptive genetic algorithm to use the improved adaptive genetic algorithm to optimize and solve the above-mentioned hazardous waste transportation path optimization problem. The improvements to the adaptive genetic algorithm include: improvements to the fitness function, improvements to the selection operator, and improvements to the crossover and mutation probabilities.

[0101] 1) Improvement of fitness function

[0102] The fitness function is used to evaluate the adaptability of an individual to the living environment, and the design of the fitness function directly affects the convergence of the algorithm and subsequent genetic operations. By analyzing various transformations of the fitness function, the present invention selects an exponential transformation for the transformation of the fitness function, and the transformation is shown in the following formula:

[0103] f'=e -a*f

[0104] The use of exponential changes to complete the transformation of the fitness function not only ensures that the fitness function is non-negative after the change, but also facilitates the conversion of the maximum and minimum values ​​of the problem. If the problem itself seeks the maximum value, it is only necessary to negate the objective function. At the same time, the a value can be adjusted to control the size of the gap between the fitness functions after the change. If the a value is smaller, the gap between the new fitness function value of the individual with a larger fitness function value before the change and the individual with a smaller fitness function value before the change will be reduced. If the a value is larger, the gap between the new fitness function value will increase. Therefore, the size of the a value determines the mandatory nature of the selection. By controlling the size of the a value in the iterative process to improve the solution efficiency of the algorithm, the present invention proposes a fitness function based on the adaptive dynamic change of the number of iterations.

[0105] In the early stage of algorithm iteration, since the fitness function values ​​between individuals are generally dispersed, the value of a is smaller at this time, so that the fitness function value gap between individuals can be reduced, and the probability of the best individual being selected is reduced to prevent the best individual from controlling the evolutionary direction of the entire population, so as to maintain the diversity between populations. In the later stage of algorithm iteration, since the fitness function values ​​between populations are generally uniform, the value of a is larger at this time, so that the fitness function value gap between individuals in the population can be increased, and the probability of each individual being selected is the same, which leads to low competitiveness between populations. Therefore, the present invention proposes the following fitness function:

[0106] F'(x)=e -aF(x)

[0107] Where, F'(x) is the fitness function after exponential transformation, F(x) is the objective function, F(x) = f1+f2+f3; a s is the preset starting value of a, k is the adjustment factor, a s The values ​​of and k can be set according to the specific problem; g is the current number of iterations, G is the maximum number of iterations, and F(x) avg is the average value of the population objective function. Since a is a positive number, F(x) avg It must be a non-negative number. When the objective function value of an individual in the population is negative, F(x) can be added to an appropriate number to ensure that the values ​​of all individuals in the population are non-negative; ε is a number infinitely close to 0 to prevent F(x) avgWhen the denominator is 0, a program error occurs.

[0108] From the above formula, we can see that when finding the minimum value of the problem, at the beginning of the iteration, due to F(x) avg The value of is relatively large, and the value of a is small. As the number of iterations increases, F(x) avg The value of a is also increasing. By adaptively adjusting the value of a, the algorithm can gradually increase the weight of local search during the iteration process, thereby better balancing global search and local search and accelerating the convergence of the algorithm.

[0109] 2) Improvement of selection operator

[0110] Species with high adaptability to the living environment in nature can have more opportunities to reproduce, otherwise the opportunity will be reduced, and the selection operation performs individual selection by imitating this behavior in nature. If the fitness function value of the current individual is high, the probability of the individual being selected to enter the next generation is large, and if the fitness function value is low, the probability of the individual being selected will also be low. Genetic algorithms have many different selection strategies, but they all have their own advantages and disadvantages. For example, the probability of an individual being selected by the roulette selection strategy is proportional to the fitness function value of the individual, but in the later stage of algorithm iteration, due to the close fitness function values ​​of the individuals, the ability of survival of the fittest is not strong at this time, which will cause the convergence ability of the algorithm to be affected, and may cause excellent individuals to be eliminated during the iteration process. Although the elite retention strategy can avoid the elimination of excellent individuals, when the algorithm falls into a local optimal solution, it will cause the individual to not be easily eliminated and may even control the evolutionary direction of the population, thereby affecting the global search ability of the algorithm. In order to enable the genetic algorithm to solve the problem better, the present invention improves the selection operator by combining the dynamic elite retention strategy with the roulette.

[0111] Since there are few or no excellent individuals in the population in the early stage of algorithm iteration, the number of elite retained individuals can be reduced or not retained directly, and individuals are selected completely in a roulette manner; as the number of iterations increases, excellent individuals will gradually appear in the population, and the number of elite retained individuals can be increased, and the remaining individuals to be retained will continue to be selected in a roulette manner. The specific operations of the improved selection operator are as follows:

[0112] S241. Determine the number of individuals to be selected as t, and the proportion of elite retained individuals to the population size as P s , the number of elite retained individuals is n, and the size of n is determined according to the following formula:

[0113]

[0114] Where t≥n; ceil is the floor function, N is the population size, g is the current iteration number, and G is the number of algorithm iterations.

[0115] S242, calculating the fitness function values ​​of all individuals in the population, and sorting them from large to small according to the values;

[0116] S243. Select the first n individuals as elite individuals and directly copy them to the next generation. The probability formula for each individual to be selected is as follows:

[0117]

[0118] Among them, P i is the probability of the i-th individual being selected; n is the number of elite individuals to be retained.

[0119] S244. Calculate the sum of the fitness functions of the remaining individuals in the population And calculate the probability of each individual in the population being selected:

[0120]

[0121] S245. The remaining individuals are combined into a roulette wheel according to the probability of being selected, and a number is directly randomly generated in [0,1], and the probability size in the roulette wheel is subtracted in sequence. If the probability difference after subtracting a certain individual is negative, the individual is selected to enter the next generation population;

[0122] S246. Repeat S245 tn times.

[0123] In the early stage of algorithm iteration, since the individual fitness function values ​​are generally poor, all individuals are selected by roulette, and the number of elite individuals retained is zero. As the number of iterations increases, the individual fitness function value will gradually increase, and the number of elite individuals retained will also increase accordingly, until the number remains unchanged when the algorithm is halfway through the iteration. By combining the dynamic elite retention strategy with the roulette strategy to improve the selection operator, it is possible to avoid the control of the population evolution direction by the extremely excellent individuals, increase the diversity of the population, and ensure that the excellent individuals are not destroyed, accelerate the convergence speed of the algorithm, and improve the solution efficiency of the algorithm.

[0124] 3) Improvement of crossover and mutation probability

[0125] In genetic algorithms, crossover operators and mutation operators determine the algorithm's search capabilities, and have an important impact on both the algorithm's convergence speed and the algorithm's solution quality. The crossover operator determines the way genes are recombined between individuals and determines the global search capability of the entire algorithm. When the crossover probability is too small, the number of gene exchanges between individuals will decrease, reducing the algorithm's search capability, resulting in unclear individual differences between subclasses, which will lead to the following problems: premature convergence of the algorithm: Due to the lack of individual differences between populations, the probability of generating a better solution is reduced, and the algorithm reaches a convergence state early and cannot find the optimal solution; local optimal solution: When the population diversity is small, the algorithm may stagnate, resulting in the algorithm being unable to jump out of the local optimal solution when it finds the local optimal solution. When the crossover probability is too large, the algorithm's search space will also increase, and the speed of generating new individuals will also increase, but it will also increase the possibility of excellent solutions being destroyed: As the probability of individual crossover increases, excellent individuals are destroyed due to crossover; efficiency slows down: Since the crossover operation wastes a lot of computing time, a large crossover probability will greatly increase the time complexity and running time of the algorithm. The mutation operator also increases the search range of the algorithm. When the mutation probability is too low, the number of mutations decreases, which reduces the diversity of the population, resulting in the possibility of missing out on better individuals during the search process and failing to obtain the optimal solution. A high mutation probability will not only greatly increase the running time of the algorithm, but will also cause the genetic algorithm to become a random search algorithm. Therefore, the setting of the crossover probability and mutation probability should be analyzed based on specific problems, and the parameters of the two should be reasonably set to balance the search efficiency and accuracy.

[0126] The present invention proposes to add an iteration number parameter to improve the crossover probability calculation formula and the mutation probability calculation formula. The specific formula is shown as follows:

[0127]

[0128] Where P cmax , P cmin are the maximum and minimum values ​​of the crossover probability respectively; f' is the value of the individual with the larger fitness function value in the two crossover objects; f avg is the average value of the current population; P mmax , P mmin are the maximum and minimum values ​​of the mutation probability respectively; f is the value of the individual to be mutated; g is the current iteration number, G is the iteration number of the algorithm, at this time, the crossover probability and mutation probability are still controlled within [P cmax ,P cmin ] and [P mmax ,P mmin ]between.

[0129] By referencing the iteration parameters, the algorithm mainly uses crossover operations in the early stage to search the search space faster, while mutation operations are mainly used in the later stage of the algorithm, which not only avoids the destruction of excellent individuals, but also increases the search ability of the algorithm. The group can be adjusted more accurately to avoid premature convergence of the algorithm and improve the solution quality of the algorithm. Without considering the number of iterations, the specific change value of the parameter is as follows Figure 2 As shown in the figure, the individual crossover probability and mutation probability change nonlinearly between the maximum and minimum values ​​with the fitness function value. This improvement can effectively solve the problems of the genetic algorithm mentioned above.

[0130] In summary, the improved genetic algorithm is used to optimize and solve the optimization problem of hazardous waste transportation path. The steps of obtaining the optimal path for hazardous waste transportation using the adaptive genetic algorithm to solve the function optimization problem are as follows:

[0131] S21. Initialize the population size to N, the initial number of iterations to g, the maximum number of iterations to G, the number of selected individuals to n, and the probability of retaining elite individuals to P s , crossover probability P cmax ,P cmin and mutation probability P mmax ,P mmin .

[0132] S22, perform real number encoding on the individuals x in the population and randomly generate an initial population;

[0133] The specific encoding method is: number N waste-generating units in sequence, and when the maximum number of carrier vehicles is K, the chromosome length is recorded as N+K+1, and the chromosome encoding string is: {1, 2, 3, ..., N+K+1}. For example, the encoding string is {0, 1, 12, 8, 5, 0, 2, 3, 7, 0, 10, 13, 6, 9, 0}, which means that there are 3 recycling vehicles in this encoding string that collect hazardous waste from 13 waste-generating units, with a total of 3 recycling routes.

[0134] S23, calculate the fitness function value of each individual: take the objective function as the original fitness function, and calculate the fitness function value of each individual by the fitness function calculation formula based on the adaptive dynamic change of the number of iterations:

[0135] F'(x)=e -aF(x)

[0136] S24, selection operation: adopt the dynamic elite retention strategy combined with roulette wheel to select, and replace the last t individuals in the population after crossover mutation with the selected t individuals; let the retained individuals and the offspring individuals participate in the competition together in the next iteration.

[0137] S25, crossover operation: use single-point crossover to perform crossover, crossover probability P c The calculation is performed according to the crossover probability calculation formula.

[0138] S26, mutation operation: mutation is performed using the basic bit mutation method, with a mutation probability P m The calculation is performed according to the mutation probability calculation formula.

[0139] S27, determine whether the stop condition is met, if so, output the optimal solution, otherwise continue to repeat from S23.

[0140] The technical effect of the present invention is further verified through experiments.

[0141] By using the traditional genetic algorithm, the hybrid genetic algorithm and the improved genetic algorithm of the present invention, the data with the same requirements are imported to perform path optimization. The time window problem is considered in all three experimental groups. The experimental results show that the path optimized by the improved genetic algorithm of the present invention can ensure that there is no early or late arrival. Therefore, in the path planning problem, the use of the improved genetic algorithm can avoid the time window problem while planning the path. Table 1 shows the comparison of the operation results of each algorithm.

[0142] Table 1

[0143] Total distance Total Cost Operation time Traditional genetic algorithm 358.2 1309.24 3.4478 Hybrid Genetic Algorithm 340.9 1274.99 6.6756 Improved genetic algorithm of the present invention 364.4 1121.51 4.4524

[0144] The results show that the improved genetic algorithm of the present invention increases the path by 6.2 kilometers compared with the traditional genetic algorithm, but the total cost is reduced by 187.73 yuan. The reason for the difference is that compared with the original 3 recycling vehicles of the traditional algorithm, the improved genetic algorithm of the present invention only uses 2 recycling vehicles to complete the given task. The operation time is reduced by 2.2 seconds compared with the hybrid genetic algorithm. Figure 3 The analysis of the results shows that the improved genetic algorithm of the present invention can obtain better path planning results. The improved genetic algorithm of the present invention reduces the cost by 14.3% compared with the traditional genetic algorithm and reduces the cost by 12% compared with the hybrid genetic algorithm. Even if the total path of hazardous waste recycling increases by 1.7% under the rule of minimum total cost, it can still be proved that the improved genetic algorithm of the present invention has a strong advantage and has achieved the optimal solution with the lowest cost by reducing the number of vehicles invested and extending the recycling distance.

[0145] Another embodiment of the present invention provides a hazardous waste transportation and treatment device based on the Internet of Things, such as Figure 4 As shown, the system includes:

[0146] A route optimization model building module 410, which is configured to determine the objective function and constraints of the hazardous waste transportation route optimization problem;

[0147] The optimal path solving module 420 is configured to optimize and solve the hazardous waste transportation path optimization problem using an improved genetic algorithm to obtain an optimal hazardous waste transportation path.

[0148] For the undetailed parts of a hazardous waste transportation and treatment device based on the Internet of Things according to an embodiment of the present invention, please refer to the above specific description of the method embodiment.

[0149] The method of the present invention can be executed in an electronic device. The electronic device can be any device with storage and computing capabilities, which can be implemented as a server, a workstation, etc., or as a personal computer such as a desktop computer or a notebook computer, or as a terminal device such as a mobile phone, a tablet computer, a smart wearable device, an Internet of Things device, but is not limited thereto.

[0150] Figure 5 Schematic diagram of an electronic device according to an embodiment of the present invention is shown. Figure 5As shown, the electronic device may include: a processor 510, a memory 520, an input / output interface 530, a communication interface 540 and a bus 550. The processor 510, the memory 520, the input / output interface 530 and the communication interface 540 are connected to each other through the bus 550. The processor 510 can be implemented in a general CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, etc., for executing related programs to implement the technical solutions provided in the embodiments of this specification. The memory 520 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage devices, dynamic storage devices, etc. The memory 520 can store operating systems and other applications. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program codes are stored in the memory 520 and are called and executed by the processor 510. The input / output interface 530 is used to connect the input / output module to implement information input and output. The input / output / module can be configured as a component in an electronic device (not shown in the figure), or it can be externally connected to an electronic device to provide corresponding functions. The input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc. The communication interface 540 is used to connect a communication module (not shown in the figure) to realize communication interaction between this electronic device and other devices. The communication module can realize communication through a wired mode (such as USB, network cable, etc.) or through a wireless mode (such as mobile network, WIFI, Bluetooth, etc.). The bus 550 includes a channel to transmit information between various components of the electronic device (such as a processor 510, a memory 520, an input / output interface 530, and a communication interface 540).

[0151] The embodiment of the present invention also provides a non-transitory readable storage medium, which stores instructions, and the instructions are used to make the electronic device perform a method according to an embodiment of the present invention. The readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. The information can be a computer-readable instruction, a data structure, a module of a program, or other data. Examples of readable storage media include, but are not limited to: phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, tape disk storage, etc.

[0152] It should be noted that, although several units, modules or submodules are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to an embodiment of the present invention, the features and functions of two or more modules described above can be embodied in one module. Conversely, the features and functions of one module described above can be further divided into being embodied by multiple modules.

[0153] In addition, although the operations of the method of the present invention are described in a specific order in the drawings, this does not require or imply that the operations must be performed in this specific order, or that all the operations shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.

[0154] Although the spirit and principle of the present invention have been described with reference to several specific embodiments, it should be understood that the present invention is not limited to the disclosed specific embodiments, and the division of various aspects does not mean that the features in these aspects cannot be combined to benefit, and such division is only for the convenience of expression. The present invention is intended to cover various modifications and equivalent arrangements included in the spirit and scope of the attached claims.

Claims

1. A method for transporting and treating hazardous waste based on the Internet of Things, characterized in that: The following steps are involved: S1. Determine the objective function and constraints of the hazardous waste transportation route optimization problem; S2. Utilize an improved genetic algorithm to optimize and solve the hazardous waste transportation route optimization problem, and obtain the optimal hazardous waste transportation route.

2. According to the method for transporting and treating hazardous waste based on the Internet of Things in claim 1, it is characterized in that: The objective function of the hazardous waste transportation route optimization problem described in S1 is established as follows: Min F=f1+f2+f3 In the formula, Min means minimization, f1 represents the fixed cost of hazardous waste recycling; f2 represents the hazardous waste transportation cost; f3 represents the hazardous waste time penalty cost; The constraints of the hazardous waste transportation route optimization problem are established as follows: Where m represents the total number of hazardous waste production units; g i represents the demand for hazardous waste disposal by hazardous waste production unit i; y ik The hazardous waste produced by hazardous waste production unit i is transported by transport vehicle k, y ik ∈[0, 1]; Q represents the maximum load of hazardous waste recycling vehicles; n represents the total number of transport vehicles; x ijk represents the transport vehicle k from hazardous waste production unit i to hazardous waste production unit j, x ijk ∈[0,1];y jk The hazardous waste produced by hazardous waste production unit j is transported by transport vehicle k; x i0k and x 0jk It means that each transport vehicle k needs to return after leaving the transport company and completing the disposal; It means that there is only one hazardous waste production unit connected to the path p of each hazardous waste production unit i or j; t i represents the time of arrival at hazardous waste production unit i; l i It represents the limited time of the right time window specified for hazardous waste production unit i.

3. The method for transporting and treating hazardous waste based on the Internet of Things according to claim 2 is characterized in that: The fixed cost f1 of hazardous waste recycling described in S1 is expressed as: The hazardous waste transportation cost f2 is expressed as: The hazardous waste time penalty cost f3 is expressed as: Where c1 represents the fixed cost of hazardous waste transportation vehicles; z k indicates that hazardous waste transport vehicle k is used; c2 represents the transportation cost per kilometer of hazardous waste recycling vehicles; d ij represents the distance of the vehicle from hazardous waste production unit i to hazardous waste production unit j; ε1 and ε2 represent the time cost penalty factors; represents the time when the kth vehicle arrives at hazardous waste production unit i; [Et a ,Et b ]=[e i +λ,l i +λ],e i represents the left time window specified by hazardous waste production unit i; λ represents the relaxation of the time window.

4. The method for transporting and treating hazardous waste based on the Internet of Things according to claim 3 is characterized in that: The method of optimizing and solving the hazardous waste transportation path optimization problem by using an improved genetic algorithm in S2 includes: S21, initialize and set the population size, initial number of iterations, maximum number of iterations, number of selected individuals, and probability P of retaining elite individuals s , crossover probability P cmax , P cmin and mutation probability P mmax , P mmin ; S22, real number encoding is performed on the individuals in the population, and an initial population is randomly generated; S23, calculating the fitness function value of each individual x; wherein the fitness function value is calculated by a fitness function that adaptively changes dynamically based on the number of iterations; S24, selection operation: adopt the dynamic elite retention strategy combined with roulette wheel to select, and replace the last t individuals in the population after crossover mutation with the selected t individuals; let the retained individuals and the offspring individuals participate in the competition together in the next iteration; S25, crossover operation: use a single-point crossover method to perform crossover according to the crossover probability calculation formula; S26, mutation operation: using the basic bit mutation method to perform mutation according to the mutation probability calculation formula; S27, determine whether the stop condition is met, if so, output the optimal solution, otherwise continue to repeat from S23.

5. The method for transporting and treating hazardous waste based on the Internet of Things according to claim 4 is characterized in that: The formula of the fitness function based on the adaptive dynamic change of the number of iterations described in S23 is: F′(x)=e -aF(x) Where, F′(x) is the fitness function after exponential transformation, F(x) is the objective function, F(x) = f1+f2+f3; a s is the preset starting value of a, k is the adjustment factor, g is the current number of iterations, G is the maximum number of iterations, F(x) avg is the average value of the population objective function, and ε is a number infinitely close to 0.

6. The method for transporting and treating hazardous waste based on the Internet of Things according to claim 5 is characterized in that: The dynamic elite retention strategy combined with roulette wheel selection described in S24 replaces the last t individuals in the population after crossover mutation with the selected t individuals, including: S241. Determine the number of individuals to be selected as t, and the proportion of elite retained individuals to the population size as P s , the number of elite retained individuals is n, and the size of n is determined according to the following formula: Where, t≥n; ceil is the floor rounding function, N is the population size; S242, calculating the fitness function values ​​of all individuals in the population, and sorting them from large to small according to the values; S243. Select the first n individuals as elite individuals and directly copy them to the next generation. The probability formula for each individual to be selected is as follows: Among them, P i is the probability of the i-th individual being selected; S244, calculating the sum of fitness functions of the remaining individuals in the population, and calculating the probability of each individual in the population being selected; S245, the remaining individuals are combined into a roulette wheel according to the probability of being selected, and a number is directly randomly generated in [0, 1], and the probability size in the roulette wheel is subtracted in sequence. If the probability difference after subtracting a certain individual is negative, the individual is selected to enter the next generation population; S246. Repeat S245 tn times.

7. The method for transporting and treating hazardous waste based on the Internet of Things according to claim 6 is characterized in that: The crossover probability calculation formula in S25 is: Where P cmax , P cmin are the maximum and minimum values ​​of the crossover probability respectively; f′ is the value of the individual with the larger fitness function value in the two crossover objects; f avg is the average value of the current population; The mutation probability calculation formula in S26 is: Where P mmax , P mmin are the maximum and minimum values ​​of the mutation probability respectively; f is the value of the individual to be mutated.

8. A hazardous waste transportation and treatment device based on the Internet of Things, characterized in that: include: a route optimization model building module configured to determine an objective function and constraints for a hazardous waste transportation route optimization problem; The optimal path solving module is configured to use an improved genetic algorithm to optimize and solve the hazardous waste transportation path optimization problem to obtain the optimal path for hazardous waste transportation.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program; wherein the computer program is stored in the memory and configured to be executed by the processor to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The storage medium stores a computer program; the computer program is executed by a processor to implement the method according to any one of claims 1 to 7.

Images