Solid waste resource utilization management method based on digital city

Abstract

The present invention discloses a solid waste resource utilization management method based on a digital city, including: collecting data by deploying Internet of Things sensors in the solid waste treatment link, establishing a data set, and constructing a digital twin model in a virtual environment; performing capacity prediction and risk assessment on the treatment equipment in the model, and dynamically predicting the amount of solid waste generated in combination with historical data; taking resource utilization efficiency and treatment cost as optimization goals, constructing a dual-objective optimization function, solving it through a genetic algorithm, generating an optimal resource treatment strategy, and updating the digital twin model by calculating the output error; the present invention significantly improves the resource utilization efficiency and treatment economy of solid waste, and through the combination of digital twins and genetic algorithms, realizes the precise scheduling of equipment capacity, optimizes the treatment process, reduces equipment load fluctuation and operating costs, and provides an intelligent solution for solid waste management in smart cities.

Description

Technical Field

[0001] The present invention relates to the technical field of solid waste resource optimization management under digital twin, and in particular to a solid waste resource utilization management method based on digital city. Background Art

[0002] In recent years, with the rise of information technology and intelligent management methods, cutting-edge technologies such as the Internet of Things (IoT), digital twins, and artificial intelligence (AI) have gradually been introduced into the field of solid waste management, bringing disruptive changes to the traditional model. For example, by collecting data in real time through IoT sensors, the amount of solid waste generated and the operating status of the treatment process can be dynamically monitored. The physical system can be virtualized and modeled using digital twin technology to achieve digital simulation and optimization of the solid waste treatment process. However, although the integrated application of these technologies has improved management efficiency to a certain extent, the existing technology system still has significant limitations in terms of the balanced optimization of solid waste resource efficiency and treatment costs, and it is difficult to meet the complex needs of future smart city construction.

[0003] The main deficiencies of existing solid waste management technologies are concentrated in the following aspects: First, the improvement of solid waste resource efficiency is limited by the lack of status monitoring and capacity assessment of treatment equipment. Current technologies mostly use static monitoring or numerical statistical methods, lacking accurate prediction models for equipment health status and treatment capacity, resulting in the inability to fully utilize equipment potential when formulating resource strategies, and may even aggravate system instability due to prediction bias. Second, although multi-objective optimization technology has been initially applied to resource allocation problems, most optimization models rely on fixed parameters and conditional assumptions, lack dynamic adjustment mechanisms, and cannot adapt to real-time changes in solid waste generation and treatment conditions. This static optimization method not only reduces the flexibility of resource allocation, but may also significantly reduce system efficiency due to fluctuations in external conditions. Third, the feedback mechanism of the solid waste management system is generally lagging and lacks real-time closed-loop optimization capabilities. Existing methods are usually based on single-stage optimization and adjustment, and fail to effectively realize dynamic feedback of real-time data and iterative updates of strategies. As a result, it is difficult to achieve the optimal state of improving resource efficiency and controlling treatment costs at the same time, making the overall operation effect of the system still far from the goal of efficient and sustainable development of smart cities.

[0004] Through the above analysis, further exploring solid waste resource management technology with dynamic prediction and real-time optimization as the core has become an important research direction of current digital cities. Summary of the invention

[0005] Some simplifications or omissions may be made in this section and the abstract and title of the present application to avoid obscuring the purpose of this section, the abstract and the title of the invention, and such simplifications or omissions shall not be used to limit the scope of the present invention.

[0006] In view of the above existing problems, the present invention is proposed. Therefore, the present invention provides a solid waste resource utilization management method based on digital city to solve the problems raised in the background technology.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions: a solid waste resource utilization management method based on a digital city, comprising:

[0008] Deploy IoT sensors in each link of solid waste treatment, collect basic parameters of solid waste through the IoT sensors, and establish a solid waste data set;

[0009] Using the solid waste data set and various links of solid waste treatment, a digital twin model of solid waste treatment is created in a virtual environment, the capacity of the treatment equipment in the digital twin model is predicted, and based on the capacity prediction results of the treatment equipment, the future amount of solid waste generated is dynamically predicted;

[0010] Construct a resource optimization treatment strategy for solid waste, taking the resource efficiency and treatment cost of solid waste generation as the optimization target, and specify the constraints of the optimization target;

[0011] By using a genetic algorithm to solve the resource optimization treatment strategy of the solid waste, the optimal resource treatment strategy is obtained, and the output error of the digital twin model is calculated according to the optimal resource treatment strategy to update the digital twin model, thereby realizing the optimal resource utilization management method of solid waste in a digital city.

[0012] As a preferred solution of the solid waste resource utilization management method based on digital city described in the present invention, wherein: IoT sensors are deployed in each link of solid waste treatment, basic parameters of solid waste are collected by the IoT sensors, and a solid waste data set is established, including:

[0013] IoT sensors are deployed in the collection, transportation, classification and treatment of solid waste to collect the basic parameters of solid waste in each treatment link and establish a solid waste data set.

[0014] As a preferred solution of the solid waste resource utilization management method based on digital city described in the present invention, it also includes:

[0015] The basic parameters of solid waste collected by the IoT sensor are sorted, duplicate basic parameters are deleted, and the missing values ​​in the basic parameters are filled with the average value after deleting the duplicate basic parameters.

[0016] As a preferred solution of the solid waste resource utilization management method based on digital city described in the present invention, wherein: using the solid waste data set and each link of solid waste treatment, a digital twin model of solid waste treatment is created in a virtual environment, including:

[0017] The solid waste data set collected during the collection, transportation, classification and treatment of solid waste is used to obtain a solid waste treatment system in a physical environment. Through the solid waste treatment system in the physical environment, the solid waste collection points, transportation routes and treatment equipment in the solid waste treatment system are identified and a unique and corresponding ID is assigned;

[0018] Create a digital twin model of solid waste treatment based on the ID identification of solid waste collection points, transportation routes and treatment equipment.

[0019] As a preferred solution of the solid waste resource utilization management method based on digital city described in the present invention, the capacity prediction of the processing equipment in the digital twin model includes:

[0020] Extract the collection frequency and processing frequency of the processing equipment and the flow change trend on the transportation route from the digital twin model, determine the processing capacity of the processing equipment under healthy conditions, establish the functional relationship expression between the operating parameters of the processing equipment and the processing capacity, and output the processing capacity prediction results of the processing equipment;

[0021] By considering the change of processing capacity to the efficiency of processing equipment, a risk assessment is performed on the processing capacity prediction result to generate a credible interval of the processing capacity prediction result.

[0022] As a preferred solution of the solid waste resource utilization management method based on digital city described in the present invention, the amount of solid waste generated is dynamically predicted based on the capacity prediction results of the processing equipment, including:

[0023] Based on the credible interval of the processing capacity prediction result and the historical solid waste generation, a mapping relationship between the solid waste generation and the processing equipment capacity is constructed to obtain the current solid waste generation.

[0024] As a preferred solution of the solid waste resource utilization management method based on digital city described in the present invention, a resource optimization treatment strategy for solid waste is constructed, with the resource efficiency and treatment cost of the amount of solid waste generated as the optimization target, and the constraint conditions of the optimization target are specified, including:

[0025] The resource efficiency of solid waste generation is defined as the ratio of solid waste generation to total input, and the cost of solid waste treatment is defined as the sum of the operating cost of the treatment equipment, transportation cost and energy consumption cost;

[0026] A dual-objective optimization function is obtained through the resource utilization efficiency of the solid waste generation and the cost of treating the solid waste;

[0027] The equipment processing capacity constraints, transportation time constraints, classification resource ratio constraints, environmental emission constraints and energy consumption constraints of the dual-objective optimization function are established.

[0028] As a preferred solution of the solid waste resource utilization management method based on digital city described in the present invention, wherein: the optimal resource processing strategy is obtained by solving the resource optimization processing strategy of the solid waste using a genetic algorithm, including:

[0029] The resource optimization treatment strategy of solid waste is represented as individuals in the population and encoded in the form of a matrix;

[0030] Based on the processing capacity prediction result of the processing equipment and its credible interval, P initial individuals are randomly generated to form a population, and each individual in the population is evaluated by the dual-objective optimization function;

[0031] The roulette method based on fitness ratio is used to randomly select an individual from the current population for the next generation of reproduction, and the confidence interval of the processing capacity prediction result is introduced into the crossover operation of the genetic algorithm to obtain the fitness of the selected individual;

[0032] Apply mutation operation to the individuals with the lowest fitness in the population;

[0033] Repeat the above operations until the number of individuals in the population reaches the maximum value or the fitness of the population does not change, then stop the iteration and select the individual with the highest fitness from the population as the current optimal resource optimization processing strategy.

[0034] As a preferred solution of the solid waste resource utilization management method based on digital city described in the present invention, wherein: each individual in the population is evaluated by the dual-objective optimization function, including:

[0035] The weights of the resource utilization efficiency of the amount of solid waste generated and the cost of treating the solid waste are set in the dual-objective optimization function, and the weight of the resource utilization efficiency of the amount of solid waste generated is greater than the weight of the cost of treating the solid waste as the initial weight ratio;

[0036] If the resource utilization efficiency of the amount of solid waste generated is maximized, the weight of adjusting the resource utilization efficiency of the amount of solid waste generated will gradually become smaller than the weight of the cost of treating the solid waste;

[0037] The weight value of the dual-objective optimization function is adjusted by evaluating the change in the current population resource efficiency and the processing cost.

[0038] As a preferred solution of the solid waste resource utilization management method based on digital city described in the present invention, wherein: calculating the output error of the digital twin model according to the optimal resource processing strategy to update the digital twin model includes:

[0039] Compare the prediction results of the digital twin model with the output results of the optimal strategy, calculate the output error, and update the functional relationship expression between the operating parameters of the processing equipment and the processing capacity in the digital twin model as well as the dual-objective optimization function.

[0040] Compared with the prior art, the invention has the following beneficial effects:

[0041] 1. The present invention takes the collection points, transportation routes and processing equipment in the solid waste treatment process as the core, and uses unique ID identification to build a precise correspondence between virtual and physical systems, so that the digital twin model can not only simulate the operation of the equipment, but also dynamically adjust and predict the processing capacity, significantly improving the management system's ability to adapt to external variables;

[0042] 2. In the digital twin environment, by collecting dynamic data of frequency, processing frequency and flow trend, the health status and capacity changes of the processing equipment can be judged in real time. Compared with the traditional method that relies on historical statistical data, the solution of the present invention uses a dynamic prediction method to improve the prediction accuracy, and combines the credible interval for risk assessment, providing a scientific basis for resource utilization strategy;

[0043] 3. By constructing a dynamic mapping relationship between waste generation and equipment processing capacity, the future waste generation is predicted, which effectively solves the problem of slow response of traditional systems to changes in the external environment, and realizes the rapid perception of dynamic changes in future waste generation and dynamic matching of processing capacity;

[0044] 4. By introducing the adaptive crossover and mutation strategy of the processing capacity credible interval and the fitness evaluation mechanism, the genetic algorithm's ability to solve complex goals is enhanced. Compared with the traditional static optimization method, this scheme can quickly iterate a better processing strategy and significantly improve the system's computing efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0046] Figure 1 This is an overall flow chart of a solid waste resource utilization management method based on a digital city according to an embodiment of the present invention;

[0047] Figure 2 A genetic algorithm flow chart of a solid waste resource utilization management method based on a digital city according to an embodiment of the present invention;

[0048] Figure 3 A diagram showing dynamic changes in the processing capacity of each device in a solid waste resource utilization management method based on a digital city according to an embodiment of the present invention;

[0049] Figure 4 An optimized waste treatment volume diagram of a solid waste resource utilization management method based on a digital city according to an embodiment of the present invention;

[0050] Figure 5 This is a genetic algorithm convergence curve diagram (cost) of the solid waste resource utilization management method based on a digital city according to an embodiment of the present invention. DETAILED DESCRIPTION

[0051] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0052] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0053] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0054] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0055] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0056] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0057] Example 1: Reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and provides a solid waste resource utilization management method based on a digital city, comprising:

[0058] S1. Deploy IoT sensors in all links of solid waste treatment, collect basic parameters of solid waste through IoT sensors, and establish a solid waste data set;

[0059] Specifically, the various links of solid waste treatment refer to collection (collection of solid waste in households, industries, commercial places, etc.); transportation (transportation from the collection source to the treatment facility, not considering the issue of transfer stations here), classification (sorting according to the characteristics of the material, such as organic matter, metals, plastics, paper, etc.) and treatment (equipment treatment for the classification and treatment process of the sorted materials, such as incineration to generate heat energy for power generation or heating);

[0060] Furthermore, IoT sensors are deployed in the collection, transportation, classification and treatment of solid waste to collect basic parameters of solid waste in each treatment link and establish a solid waste data set;

[0061] Furthermore, the basic parameters of the solid waste collected by the IoT sensor are sorted, duplicate basic parameters are deleted, and the missing values ​​in the basic parameters are filled with the average values ​​after deleting the duplicate basic parameters;

[0062] Specifically, select ascending (default) or descending order for the sort order of basic parameters;

[0063] Specifically, the average value filling method is to calculate the column corresponding to the missing value. For example, if the quantity of solid waste in a certain data is missing, then only the average value of the "quantity" column of the field is calculated, and the average value is used to fill the position of the missing value. It should be noted that the average value filling method is only applicable to numerical data. If text or date data is encountered, the context inference rule needs to be used for filling.

[0064] Specifically, the basic parameters include the ID, timestamp, geographic location, type, quantity, and treatment status of the solid waste;

[0065] Specifically, the solid waste data set is expressed as follows:

[0066]

[0067] Among them, d 1 It is represented as a data point, i.e., the data point represented by the solid waste collected by the IoT sensor, each of which contains the above basic parameters as the attributes of the data point; n represents the number of data points;

[0068] Furthermore, the solid waste data set is stored in the form of a two-dimensional data table locally and backed up in the cloud through a wireless network;

[0069] It should be noted that the solid waste data set is sent to the local site to facilitate local personnel to call it, because the call of cloud backup usually requires higher-level permissions. At the same time, sending it to the cloud backup is to prevent local data loss and to facilitate tracing when the values ​​or models are abnormal in the future;

[0070] S2. Using the solid waste data set and various links of solid waste treatment, create a digital twin model of solid waste treatment in a virtual environment, predict the capacity of the treatment equipment in the digital twin model, and dynamically predict the future solid waste generation based on the capacity prediction results of the treatment equipment;

[0071] Furthermore, the solid waste treatment system in the physical environment is obtained from the solid waste data set collected during the collection, transportation, classification and treatment of solid waste. Through the solid waste treatment system in the physical environment, the solid waste collection points, transportation routes and treatment equipment in the solid waste treatment system are identified and assigned unique and corresponding ID identifications;

[0072] It should be noted that assigning a unique ID to each component of the actual solid waste system can avoid data confusion or incorrect association, ensure that each virtual node in the created digital twin model corresponds one-to-one with the actual solid waste treatment system, and establish a dynamic interaction process between the two;

[0073] Furthermore, a digital twin model of solid waste treatment is created through the ID identification of solid waste collection points, transportation routes and treatment equipment;

[0074] Specifically, the digital twin model consists of three layers, namely the physical layer: the collection points, transportation routes and equipment of the actual solid waste treatment system; the data layer: real-time collection and storage of operating data and historical data of the actual solid waste system; the model layer: the state equation and output equation of the digital twin model;

[0075] Specifically, assuming that the state variable is x(t), the control input is u(t), the output is y(t), and the disturbance is w(t), the state equation of the digital twin model is:

[0076] x(t+1)=A x(t+1)+Bu(t)+w(t)

[0077] Among them, x(t) represents the state of the model at time t, including , , ; Expressed as the solid waste stock at the i-th collection point at time t (tons), is the transport volume (tons) from collection point i to treatment facility j at time t, is the processing capacity of processing equipment j at time t (tons / hour); u(t) represents the control input vector of the model, including , ; is the transportation decision variable (whether to transport solid waste from i to j at time t, with a value of 0 or 1, 0 represents false and 1 represents true); represents the environmental disturbance vector, such as random events such as transportation delay and equipment failure at time t; A and B are model matrices, representing the mapping relationship between state variables and control inputs;

[0078] Specifically, the output equation of the digital twin model is:

[0079] y(t)=Cx(t)

[0080] Among them, y(t) is the output value of the model at time t, including , , ; For real-time transportation efficiency, is the load rate of processing device j at time t, is the resource utilization rate of the model at time t; C is the observation matrix, which is used to map the state variables to output indicators;

[0081] It should be noted that at this time, the digital twin model of solid waste treatment and the actual solid waste treatment system are interconnected, that is, if there are time delays, equipment failures or transportation anomalies in the collection points, transportation routes and treatment equipment in the actual solid waste treatment system, real feedback can be obtained from the digital twin model;

[0082] Furthermore, the collection frequency and processing frequency of the processing equipment and the flow change trend on the transportation route are extracted from the digital twin model to determine the processing capacity of the processing equipment under healthy conditions, establish a functional relationship expression between the operating parameters of the processing equipment and the processing capacity, and output the processing capacity prediction result of the processing equipment;

[0083] Specifically, the collection frequency of the processing equipment is the average collection frequency of the collection point i, and the processing frequency is the average processing frequency of the processing equipment j; the flow change trend on the transportation line is the flow change rate from i to j;

[0084] Furthermore, based on the above equipment collection frequency, processing frequency and flow change trend definition on the transportation line, the health status of the processing equipment can be obtained as follows:

[0085] When the equipment collection frequency is equal to the processing frequency, it indicates that the equipment can stably process the input solid waste volume, indicating that the equipment is operating normally and in a healthy state;

[0086] When the equipment processing frequency is lower than the collection frequency, it means that the equipment cannot fully process the input of solid waste, resulting in equipment performance degradation or blockage; or, when the equipment processing frequency is higher than the collection frequency, it means that the input of solid waste is insufficient and the equipment is in an operating state that cannot reach full load; the health status of such equipment is judged to be sub-healthy;

[0087] When the equipment processing frequency exceeds the maximum processing capacity of the equipment (e.g., the supply of solid waste at the upstream transportation or collection point surges, causing the equipment to process solid waste under overload), and the flow change trend of the transportation line fluctuates violently (e.g., the input of solid waste surges or decreases rapidly in a short period of time), it means that the equipment has entered a high-load operation state, and there is a risk of equipment failure, and the health state is judged to be an unhealthy state (fault state);

[0088] Specifically, for the processing capacity of the equipment under a certain health condition, the functional relationship expression between the operating parameters of the processing equipment and the processing capacity is established as follows:

[0089]

[0090] in, is the actual processing capacity of processing equipment j at time t (tons / hour), is the maximum processing capacity of processing equipment j (tons / hour), It is represented as the health status index of device j at time t, with a value range of [0,1], where 0 represents a fault state, 1 represents a healthy state, and the rest represent a sub-healthy state; is the operating load rate of equipment j at time t, ; represents the fluctuation rate of the transportation flow from collection point i to equipment j at time t , Expressed as the standard deviation of the transport flow from collection point i to equipment j, It is expressed as the mean value of the transport flow from collection point i to equipment j; is the coefficient of influence of load on equipment processing efficiency; is the coefficient of weakening of equipment processing capacity due to flow fluctuation;

[0091] Specifically, the formula is explained as follows:

[0092] When the equipment health index is at the highest (i.e. 1), the equipment's processing capacity is closer to the maximum value. If the equipment health status decreases, the processing capacity will be reduced proportionally. The higher the operating load rate, the closer the equipment's current operating load is to its maximum processing capacity. At this time, the load has a significant weakening effect on the equipment efficiency. That is, when the operating load rate is close to 1, the weakening factor approaches 0. The higher the transport flow fluctuation rate, the greater the fluctuation of the equipment input supply, and the higher the possibility of impact on the equipment operation, which will lead to a decrease in the equipment's processing capacity.

[0093] For example, assuming that the maximum processing capacity of a device is Tons / hour, health status index , operating load factor , transportation flow volatility , , ; Then the actual processing capacity of the device is:

[0094]

[0095]

[0096] It should be explained that, since the previously mentioned treatment and collection frequencies do not take into account the efficiency changes of the equipment, this factor should be included in the risk assessment;

[0097] Specifically, the defined equipment efficiency changes are:

[0098]

[0099] in, is the efficiency of equipment j at time t, It is expressed as the resource consumed by the device at time t (e.g., energy consumption, in kWh);

[0100] Furthermore, considering the change of the efficiency of the processing equipment due to the equipment processing capacity, the risk assessment of the equipment processing capacity prediction result is performed to generate a credible interval of the equipment processing capacity prediction result;

[0101] Specifically, the confidence interval of the equipment processing capacity prediction results It is expressed as:

[0102]

[0103] Among them, K represents the confidence level, which is selected according to the needs, for example, the confidence level of 90% is K=1.645; Expressed as At the minimum value of the credible interval, Expressed as The maximum value of the credible interval;

[0104] It should be noted that by considering the equipment efficiency variation and confidence level, the reliability of equipment efficiency can be effectively evaluated, thereby achieving the accuracy of the prediction results of equipment processing capacity;

[0105] Furthermore, based on the credible interval of the treatment capacity prediction results and the historical solid waste generation, a mapping relationship between solid waste generation and treatment equipment capacity is constructed to obtain the current solid waste generation;

[0106] Specifically, a mapping relationship between the amount of solid waste generated and the capacity of the treatment equipment is constructed. as follows:

[0107]

[0108] in, is the historical solid waste generation;

[0109] Furthermore, To match the equipment processing capacity with the amount of solid waste generated, The equipment has excess processing capacity. Insufficient equipment processing capacity;

[0110] Specifically, the current amount of solid waste generated can be obtained through a fast approximation method. , the mathematical expression is as follows:

[0111]

[0112] It should be noted that the current solid waste generation obtained is used as the resource optimization treatment strategy for solid waste;

[0113] S3. Construct a resource optimization treatment strategy for solid waste, taking the resource efficiency and treatment cost of solid waste generation as the optimization target, and specify the constraints of the optimization target;

[0114] Furthermore, the resource efficiency of solid waste generation is defined as the ratio of solid waste generation to total input, and the cost of solid waste treatment is defined as the sum of the operating cost of the treatment equipment, transportation cost, and energy consumption cost;

[0115] Furthermore, the resource efficiency of solid waste generation can be improved by and solid waste disposal costs , and obtain the bi-objective optimization function;

[0116] Specifically, the dual objective optimization function It is expressed as:

[0117]

[0118] in, , , , They represent the operating cost, transportation cost and energy consumption cost of the processing equipment respectively; , is the amount of solid waste converted into resources at time t, is the total amount of solid waste input at time t; and The weights corresponding to resource recovery efficiency and solid waste treatment costs;

[0119] Furthermore, the equipment processing capacity constraint, transportation time constraint, classification resource ratio constraint, environmental emission constraint and energy consumption constraint of the dual-objective optimization function are established;

[0120] Specifically, the equipment processing capacity constraint needs to ensure that the total solid waste processing volume does not exceed the maximum processing capacity of the equipment, which can be expressed as:

[0121]

[0122]

[0123] Where N is the total number of devices;

[0124] Specifically, the transportation time constraint needs to ensure that the transportation time is within the scheduled time T max Inside, it is expressed as:

[0125]

[0126] in, It is expressed as the transportation time from collection point i to processing equipment j. Since the transportation time is related to the transportation flow It can be further expressed as:

[0127]

[0128] in, is the average transport speed at time t;

[0129] Specifically, the classification resource utilization ratio constraint needs to ensure that the resource utilization ratio of each type of solid waste meets the requirements, which can be expressed as:

[0130]

[0131] in, is the resource recovery amount of the kth type of solid waste at time t, is the total input of the kth type of solid waste at time t, The minimum resource recovery ratio of the kth type of solid waste;

[0132] Specifically, environmental emission constraints require limiting the amount of emissions from the treatment process. Not exceeding the maximum emission allowable value E max , expressed as:

[0133]

[0134] in, is the emission of equipment j at time t, which may also include emission factors;

[0135] It should be noted that maximum emission allowable values ​​can be defined according to local regulations and regional policies;

[0136] Specifically, the energy consumption constraint needs to ensure that the total energy consumption of the equipment processing process Stay within your energy budget , expressed as:

[0137]

[0138] in, is the energy consumption of device j at time t, , is the energy consumption factor per unit processing volume;

[0139] S4. By using genetic algorithm to solve the resource optimization treatment strategy of solid waste, the optimal resource treatment strategy is obtained, and the output error of the digital twin model is calculated according to the optimal resource treatment strategy to update the digital twin model, thereby realizing the optimal resource utilization management method of solid waste in the digital city;

[0140] It should be explained that the genetic algorithm (GA) is a global optimization algorithm based on natural selection and genetic mechanism. In the solid waste treatment problem of the present invention, since multiple variables (such as resource efficiency, treatment cost, transportation time, etc.) are involved, other optimization methods may be subject to complex constraints, so it is necessary to use genetic algorithms to quickly find a global solution.

[0141] Specifically, refer to Figure 2 , the genetic algorithm steps are as follows:

[0142] S401. Represent the resource optimization treatment strategy of solid waste as individuals in the population and encode them in matrix form. , It represents the treatment capacity of the k-th type of waste allocated to the j-th treatment equipment;

[0143] Specifically, a matrix is ​​a population, and each element in the matrix corresponds to an individual;

[0144] S402, based on the processing capacity prediction result of the processing equipment and its credible interval, randomly generate P initial individuals to form a population, and evaluate each individual in the population through a dual-objective optimization function;

[0145] Specifically, the evaluation method is as follows:

[0146] The weights of the resource efficiency of the amount of solid waste generated and the cost of treating solid waste are set in the dual-objective optimization function, and the weight of the resource efficiency of the amount of solid waste generated is greater than the weight of the cost of treating solid waste as the initial weight ratio, that is, the resource efficiency is the first optimization direction;

[0147] If the resource utilization efficiency of the amount of solid waste generated is maximized, the weight of adjusting the resource utilization efficiency of the amount of solid waste generated will gradually become smaller than the weight of the cost of treating the solid waste;

[0148] It should be noted that when the resource utilization efficiency is maximized, the weight of resource utilization efficiency is reduced and the optimization focus is placed on the cost of solid waste treatment;

[0149] By evaluating the changes in the current population resource efficiency and treatment cost, the weight value of the dual-objective optimization function is adjusted;

[0150] Specifically, the change in the current population resource efficiency and processing cost refers to the size of the change generated in the process of adjusting the weight;

[0151] S403, using a roulette wheel method based on fitness ratio, randomly selecting an individual from the current population for the next generation of reproduction, and introducing a credible interval of the processing capacity prediction result into the crossover operation of the genetic algorithm to perform a crossover operation to obtain the fitness of the selected individual;

[0152] Specifically, the crossover operation is as follows:

[0153] Randomly select two parents and , then the probability of parent selection for:

[0154]

[0155] in, Represented as an individual The fitness value of is the total number of individuals;

[0156] Randomly select the index of waste category k and equipment j as the intersection point and and Some genes (i.e., processing ) to exchange and obtain new individuals Processing capacity:

[0157]

[0158] If the new individual If the processing volume exceeds the credible interval of the predicted result of the equipment processing capacity, the crossover operation is repeated, otherwise the new individual The amount of treatment is used as the fitness of the selected individual;

[0159] S404, applying mutation operation to the individual with the lowest fitness in the population;

[0160] Specifically, the individual with the lowest fitness is selected to select waste category k and treatment equipment j for mutation operation;

[0161] Specifically, the mutation operation is as follows:

[0162] Select the individual with the lowest fitness, randomly generate a mutation value, and check whether the mutation value exceeds the credible interval of the device processing capacity prediction result. If it exceeds, select an individual from the population again;

[0163] S405, repeating S402 to S404 until the number of individuals in the population reaches a maximum value or the fitness of the population does not change, then stopping the iteration, and selecting the individual with the highest fitness from the population as the current optimal resource optimization processing strategy;

[0164] Furthermore, the prediction results of the digital twin model are compared with the output results of the optimal strategy, the output error is calculated, and the functional relationship expression between the operating parameters of the processing equipment and the processing capacity and the dual-objective optimization function in the digital twin model are updated;

[0165] Specifically, if the value of the output error is greater than any output result, no update is performed; otherwise, the functional relationship expression between the operating parameters of the processing equipment and the processing capacity and the dual-objective optimization function in the digital twin model are updated;

[0166] It should be noted that updating the model when the error is smaller than any output result can avoid the model being frequently adjusted due to large errors, thereby maintaining the stability of the system.

[0167] Example 2: Reference Figures 3 to 5 , which is the second embodiment of the present invention, and which provides a solid waste resource utilization management method based on a digital city, including: in order to verify the performance of the scheme of the present invention in terms of key indicators such as resource utilization efficiency, processing cost, energy consumption and equipment utilization rate, and to conduct comparative experiments with traditional solid waste treatment methods;

[0168] Experimental scenario:

[0169] Location: A centralized solid waste treatment center in a certain city, with an average daily solid waste generation of 150 tons, including three main types of waste:

[0170] Domestic waste (Class A): 70 tons / day;

[0171] Construction waste (Class B): 50 tons / day;

[0172] Industrial waste (Class C): 30 tons / day;

[0173] Among them, the average humidity of the waste was 50%, 15%, and 30%, and the average bulk density was 0.7, 1.2, and 0.9 tons / cubic meter, respectively;

[0174] Experimental environment:

[0175] Solid waste treatment equipment (6 in total), each device is equipped with an operation monitoring module to monitor the treatment volume, energy consumption and health status in real time. The equipment models and parameters are shown in Table 1;

[0176] Table 1

[0177]

[0178] Deploy IoT sensors (model: IoT-MX220): weight sensor: range 0-50 tons, accuracy ±0.05 tons; humidity sensor: range 0%-100%, accuracy ±1%; volume sensor: range 0-10 cubic meters, accuracy ±0.1 cubic meters; data transmission module (LoRa W6100), maximum transmission delay 3 seconds; all sensor data collected are uploaded to the cloud computing platform via the 4G network;

[0179] Use MATLAB and Python to write data processing and optimization algorithms: data cleaning and preprocessing: deduplication, filling missing values, formatting; use the DEAP library to implement genetic algorithms, with an initial population size of 50, a crossover rate of 0.8, and a mutation rate of 0.2;

[0180] Sensors collect weight, humidity and volume data of all types of waste during collection, transportation and processing, with 200 pieces of data collected daily. Based on sensor data and historical operation records, a digital twin model of the equipment operation status is established, with the optimization objectives of the model: maximizing resource efficiency and minimizing processing costs. The constraints of the model are as follows: the actual processing volume of each device shall not exceed the predicted capacity range; the minimum resource utilization ratio of each type of waste: 80% for domestic waste, 50% for construction waste, and 60% for industrial waste; the total energy consumption shall not exceed 3000kWh; the initial population is generated through a genetic algorithm: 50 processing strategies are randomly generated (based on time steps); a fitness function is created: a dual-objective optimization value combining resource efficiency and processing cost; the optimal resource optimization strategy is output after 200 iterations;

[0181] First, through Figure 3It can be seen that from time step 30 to time step 40, the processing capacity of device 2 increased from nearly 30 tons / hour to nearly 70 tons / hour, an increase of about 134%; device 5 showed a gradual upward trend throughout the process, from the initial time step of about 35 tons / hour to nearly 75 tons / hour at time step 50, an increase of about 114%; in addition, device 4 showed a downward trend, from nearly 35 tons / hour at time step 5 to nearly 15 tons / hour at time step 40, a decrease of about 57%; through dynamic prediction and real-time scheduling, the processing capacity of device 2 and device 5 is significantly improved, and the time period of inefficient operation is reduced; in addition, the decline in the processing capacity of device 4 may be related to the deterioration of its health status, and the present invention can discover this problem in advance and maintain or replace the equipment, thereby ensuring the overall efficiency of the actual solid waste treatment system; secondly, through Figure 4 It can be seen that after optimization, the total solid waste treatment capacity tends to be stable after about 30 time steps, gradually increasing from about 140 tons to nearly 220 tons at about 50 time steps, with less fluctuation, and the average value of the overall waste treatment capacity increased by about 15%. Figure 3 and Figure 4 The effectiveness of the present invention for resource efficiency is comprehensively explained; finally, reference Figure 5 After the 20th iteration, the cost dropped rapidly to about 6520 yuan, and then the rate of decline slowed down significantly. After the number of iterations reached 100, the curve tended to be stable, and the change range was less than about 0.1%, which further verified the effectiveness of the scheme of the present invention for processing cost optimization;

[0182] In summary, the present invention can improve the balance between resource utilization efficiency and treatment economy, and provide a more intelligent and refined solution for solid waste management in future smart cities.

[0183] It should be understood by those skilled in the art that the embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. The schemes in the embodiments of the present application may be implemented in various computer languages, for example, object-oriented programming language Java and literal scripting language JavaScript, etc.

[0184] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0185] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0186] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0187] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0188] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A solid waste resource utilization management method based on a digital city, characterized in that: include: Deploy IoT sensors in each link of solid waste treatment, collect parameters of solid waste through the IoT sensors, and establish a solid waste data set; Using the solid waste data set and various links of solid waste treatment, a digital twin model of solid waste treatment is created in a virtual environment, the capacity of the treatment equipment in the digital twin model is predicted, and based on the capacity prediction results of the treatment equipment, the future amount of solid waste generated is dynamically predicted; The capability prediction of the processing equipment in the digital twin model includes: Extract the collection frequency and processing frequency of the processing equipment and the flow change trend on the transportation route from the digital twin model, determine the processing capacity of the processing equipment under healthy conditions, establish the functional relationship expression between the operating parameters of the processing equipment and the processing capacity, and output the processing capacity prediction results of the processing equipment; By considering the change of the processing capacity to the efficiency of the processing equipment, a risk assessment is performed on the processing capacity prediction result to generate a credible interval of the processing capacity prediction result; The method of dynamically predicting the future amount of solid waste generated based on the capacity prediction results of the processing equipment includes: Based on the credible interval of the processing capacity prediction result and the historical solid waste generation, a mapping relationship between the solid waste generation and the processing equipment capacity is constructed to obtain the current solid waste generation; Construct a resource optimization treatment strategy for solid waste, taking the resource efficiency and treatment cost of solid waste generation as the optimization target, and specify the constraints of the optimization target; The resource optimization treatment strategy for solid waste is constructed with the resource efficiency and treatment cost of solid waste generation as the optimization target, and the constraints of the optimization target are stipulated, including: The resource efficiency of solid waste generation is defined as the ratio of solid waste generation to total input, and the cost of solid waste treatment is defined as the sum of the operating cost of the treatment equipment, transportation cost and energy consumption cost; The resource efficiency of the solid waste generated is and solid waste disposal costs , and obtain the bi-objective optimization function; The bi-objective optimization function It is expressed as: in, , , , They represent the operating cost, transportation cost and energy consumption cost of the processing equipment respectively; , is the amount of solid waste converted into resources at time t, is the total amount of solid waste input at time t; and The weights corresponding to resource recovery efficiency and solid waste treatment costs; Establishing equipment processing capacity constraints, transportation time constraints, classified resource utilization ratio constraints, environmental emission constraints, and energy consumption constraints of the dual-objective optimization function; The equipment processing capacity constraint means that the total solid waste processing volume does not exceed the maximum processing capacity of the equipment, which is expressed as: Where N is the total number of devices; is the actual processing capacity of processing device j at time t; is the maximum processing capacity of processing device j; It is represented as the health status index of device j at time t; The transportation time constraint means that the transportation time is within the scheduled time. Inside, it is expressed as: in, It is expressed as the transportation time from collection point i to processing equipment j, and the transportation time is related to the transportation flow Related, further expressed as: in, is the average transport speed at time t; The classification resource utilization ratio constraint means that the resource utilization ratio of each type of solid waste meets the requirements, which is expressed as: in, is the resource recovery amount of the kth type of solid waste at time t, is the total input of the kth type of solid waste at time t, The minimum resource recovery ratio of the kth type of solid waste; The environmental emission constraints refer to limiting the emission of the treatment process. Do not exceed the maximum emission allowable value , expressed as: in, is the emission of equipment j at time t; The energy consumption constraint refers to the total energy consumption of the equipment processing process. Stay within your energy budget , expressed as: in, is the energy consumption of device j at time t, , is the energy consumption factor per unit processing volume; By using a genetic algorithm to solve the resource optimization treatment strategy of the solid waste, the optimal resource treatment strategy is obtained, and the output error of the digital twin model is calculated according to the optimal resource treatment strategy to update the digital twin model, thereby realizing the optimal resource utilization management method of solid waste in a digital city.

2. The solid waste resource utilization management method based on digital city according to claim 1 is characterized in that: IoT sensors are deployed in each link of solid waste treatment, and parameters of solid waste are collected through the IoT sensors to establish a solid waste data set, including: IoT sensors are deployed in the collection, transportation, classification and treatment of solid waste to collect the parameters of solid waste in each treatment link and establish a solid waste data set.

3. The solid waste resource utilization management method based on digital city as claimed in claim 2 is characterized in that: Also includes: The parameters of solid waste collected by the IoT sensor are sorted, duplicate parameters are deleted, and the missing values ​​in the parameters are filled with the average value after deleting the duplicate parameters.

4. The solid waste resource utilization management method based on digital city as claimed in claim 2 is characterized in that: Using the solid waste data set and various links of solid waste treatment, a digital twin model of solid waste treatment is created in a virtual environment, including: The solid waste data set collected during the collection, transportation, classification and treatment of solid waste is used to obtain a solid waste treatment system in a physical environment. Through the solid waste treatment system in the physical environment, the solid waste collection points, transportation routes and treatment equipment in the solid waste treatment system are identified and a unique and corresponding ID is assigned; Create a digital twin model of solid waste treatment based on the ID identification of solid waste collection points, transportation routes and treatment equipment.

5. The solid waste resource utilization management method based on digital city as claimed in claim 1 is characterized in that: By using a genetic algorithm to solve the resource optimization treatment strategy of the solid waste, an optimal resource treatment strategy is obtained, including: The resource optimization treatment strategy of solid waste is represented as individuals in the population and encoded in the form of a matrix; Based on the processing capacity prediction result of the processing equipment and its credible interval, P initial individuals are randomly generated to form a population, and each individual in the population is evaluated by the dual-objective optimization function; The roulette method based on fitness ratio is used to randomly select an individual from the current population for the next generation of reproduction, and the confidence interval of the processing capacity prediction result is introduced into the crossover operation of the genetic algorithm to obtain the fitness of the selected individual; Apply mutation operation to the individuals with the lowest fitness in the population; Repeat the above operations until the number of individuals in the population reaches the maximum value or the fitness of the population does not change, then stop the iteration and select the individual with the highest fitness from the population as the current optimal resource optimization processing strategy.

6. The solid waste resource utilization management method based on digital city according to claim 5 is characterized in that: Each individual in the population is evaluated by the dual-objective optimization function, including: The weights of the resource utilization efficiency of the amount of solid waste generated and the cost of treating the solid waste are set in the dual-objective optimization function, and the weight of the resource utilization efficiency of the amount of solid waste generated is greater than the weight of the cost of treating the solid waste as the initial weight ratio; If the resource utilization efficiency of the amount of solid waste generated is maximized, the weight of adjusting the resource utilization efficiency of the amount of solid waste generated will gradually become smaller than the weight of the cost of treating the solid waste; The weight value of the dual-objective optimization function is adjusted by evaluating the change in the current population resource efficiency and the processing cost.

7. The solid waste resource utilization management method based on digital city as claimed in claim 5, characterized in that: The output error of the digital twin model is calculated according to the optimal resource processing strategy to update the digital twin model, including: comparing the prediction result of the digital twin model with the output result of the optimal strategy, calculating the output error, and updating the functional relationship expression between the processing equipment operating parameters and the processing capacity in the digital twin model and the dual-objective optimization function.

Images