Urban solid waste circulation metabolism network construction method based on multi-source data driving

Abstract

The invention discloses an urban solid waste circulation metabolism network construction method based on multi-source data driving, relates to the technical field of solid waste metabolism construction, and solves the technical problem that most of existing solid waste circulation metabolism networks are in static planning and cannot optimize transportation paths in real time. The method comprises the following steps: S1, carrying out multi-source data acquisition on a target area of urban solid waste circulation; s2, cleaning and repairing the multi-source data obtained in the step S1 to form a plurality of high-quality data sets, and performing data fusion on the plurality of high-quality data sets to obtain a fused data set; s3, constructing an urban solid waste circulation metabolism network optimization model, and performing optimization solution based on a preset solver to obtain an optimal metabolism network; s4, on the basis of the optimal metabolic network obtained through optimization solving in the step S3, an urban solid waste circulation vehicle path optimization model is constructed, the urban solid waste circulation vehicle driving path is optimized and solved, and the optimal path is obtained.The method has the advantages that the transfer path can be dynamically optimized, and the transfer efficiency is improved.

Description

Technical Field

[0001] This invention belongs to the field of solid waste metabolism construction technology, specifically involving a method for constructing an urban solid waste recycling metabolism network based on multi-source data. Background Technology

[0002] Solid waste refers to solid and semi-solid substances generated during production, daily life, and other activities that have lost their original utilization value or have been discarded or abandoned, as well as gaseous substances placed in containers. It must be included in solid waste management according to law, encompassing domestic solid waste, general industrial solid waste, and hazardous solid waste. Improper handling of solid waste can lead to multiple forms of pollution. The continuous increase in solid waste production and frequent illegal disposal incidents pose a serious threat to public health and the ecological environment. The points at which solid waste poses environmental risks can exist at any stage of its metabolic chain, such as generation, storage, transportation, and end-of-life disposal. Therefore, strengthening the traceability of the entire solid waste metabolism process and improving the ability to respond to environmental risks are key tasks in the refined management of solid waste.

[0003] Existing research indicates that current management models are insufficient to support refined management of solid waste throughout its entire lifecycle, exhibiting the following problems: First, data is fragmented across multiple sources. Solid waste data is scattered across sensors, business systems, and online text. Business systems refer to various dedicated information management systems used by governments and enterprises in the daily operation of solid waste management. Online text refers to unstructured text information obtained publicly from the internet. These data are important supplements to official business system data, providing more real-time and dynamic information closer to public perception. These systems are typically structured databases recording official, process-oriented business data, but the quality of this data varies, making it difficult to form a unified data foundation. Second, traditional metabolic networks focus only on the numerical value of waste generation, concentrating on depicting solid waste flow between different nodes. The aim is to reveal spatial transfer patterns or industrial interconnection characteristics, ignoring the upstream and downstream linkage process of solid waste from generation, collection, utilization to final disposal in the comprehensive management of urban solid waste. Furthermore, vehicle transportation routes, metabolic routes, and metabolic methods are mostly statically planned, meaning the entire recycling network is based on static rules and cannot be optimized in real time. Therefore, it is necessary to provide an urban solid waste recycling metabolic network that can achieve multi-source data integration and dynamic prediction optimization. Summary of the Invention

[0004] This invention discloses a method for constructing an urban solid waste recycling and metabolism network based on multi-source data, which aims to solve the technical problem that existing solid waste recycling and metabolism networks are mostly statically planned and cannot optimize transportation paths in real time.

[0005] To solve the aforementioned technical problems, the present invention adopts the following technical solution:

[0006] A method for constructing an urban solid waste recycling and metabolism network based on multi-source data includes the following steps:

[0007] Step S1: Collect multi-source data for the target area of ​​urban solid waste recycling. The multi-source data collection includes real-time data collection from multiple nodes of urban solid waste recycling through sensors, collection of business data from business systems, and acquisition of network data through web crawlers. The multiple nodes of urban solid waste recycling include urban solid waste generation nodes, transfer nodes, and processing nodes.

[0008] Step S2: Clean and repair the multi-source data obtained in step S1 to form multiple high-quality datasets, and fuse the multiple high-quality datasets to obtain a fused dataset;

[0009] Step S3: Construct an optimization model for the urban solid waste recycling and metabolism network. Based on the fusion dataset and preset solver in step S2, optimize the urban solid waste recycling and metabolism network optimization model to obtain the optimal metabolism network. The optimal metabolism network includes the solid waste transfer situation of each enterprise in the target area, including the proportion of solid waste that is self-processed and transferred to the treatment point for treatment.

[0010] Step S4: Based on the optimal metabolic network obtained from step S3, construct an urban solid waste recycling vehicle path optimization model, optimize the driving path of urban solid waste recycling vehicles, and obtain the optimal path.

[0011] Further, in step S1, the real-time data acquisition of multi-node urban solid waste recycling includes:

[0012] The weight of solid waste at each point of urban solid waste generation is monitored using sensors.

[0013] The system monitors the weight of solid waste collected by vehicles using sensors, tracks the location of these vehicles using locators, and monitors the total weight of vehicles entering and leaving urban solid waste treatment facilities by installing weighbridges at the entrances and exits of these facilities.

[0014] Further, step S2 includes:

[0015] Step S2.1: Identify the multi-source data in step S1, distinguish between numerical data and spatiotemporal data, and output the identification results;

[0016] The numerical data includes the weight and output of solid waste. The numerical data can come from the weight of solid waste monitored by sensors or the weight of the vehicle monitored by a weighbridge. The spatiotemporal data includes location and time. The spatiotemporal data comes from a locator, which can output time information and location information. It should be noted here that weight refers to a single measurement value, such as the reading of the smart solid waste bin at a certain moment being a fixed value, while output refers to the total amount of solid waste generated by the generation node within a certain period of time.

[0017] Step S2.2: Based on the recognition results output in step S2.1, construct cleaning rules, and clean and repair the multi-source data in step S1 based on the cleaning rules to obtain multiple high-quality datasets;

[0018] In step S2.2, cleaning and repair refers to cleaning and removing invalid values ​​from the multi-source data detected in step S1, interpolating and repairing missing values, and unifying the format (weight bits, time, etc.).

[0019] Step S2.3: Merge the multiple high-quality datasets obtained in step S2.2 to obtain a merged dataset;

[0020] In step S2.3, the Python pandas library is used to implement hierarchical association of multiple high-quality datasets by using the merge function based on key fields. For example, the association generates node and transit node data. Then, the concat function is used to horizontally concatenate the features of multiple nodes to form a fused dataset with a wide list structure. In this embodiment, the key fields are time, vehicle number, etc.

[0021] Step S2.4: Perform spatiotemporal alignment on the fused dataset.

[0022] In step S2.4, the spatiotemporal alignment of the fused dataset is achieved through temporal granularity unification and spatial coordinate standardization. For temporal granularity unification, the core methods are aggregation and interpolation, with the target granularity being hourly. Hourly aggregation is implemented using the `resample` function of Python pandas. For high-frequency data, such as weight data collected by sensors, updates are typically performed every minute. For this frequently updated data, mean aggregation is used, averaging multiple data points within an hour. For low-frequency data, such as data collected from business systems, collection is typically performed daily. For this low-frequency updated data, linear interpolation is used, splitting the data by hour. For example, if a region produces 10 tons of solid waste per day, the interpolation is 1 ton per hour. Furthermore, temporal granularity unification also includes time format standardization, which has been preliminarily explained in the aforementioned format standardization rules. This involves standardizing the timestamps of the data to a unified format, thereby ensuring that the time fields of the open datasets can be directly correlated.

[0023] For spatial coordinate system standardization, this includes coordinate system unification and spatial grid partitioning. For coordinate system unification, in this embodiment, latitude and longitude are converted into a unified coordinate system, such as the WGS84 coordinate system, using the pyproj library. This coordinate system is compatible with mainstream map platforms such as Amap and Google Maps. For spatial grid partitioning, the target area is divided into fixed-length square grids, and each grid is assigned a unique grid ID. In this embodiment, a GeoDataFrame is created using GeoPandas, and the sjoin function is used to spatially connect node data with the grid, automatically assigning grid IDs.

[0024] Furthermore, in step S2.2, the cleaning rules include invalid value handling rules, missing value handling rules, format standardization rules, and logical consistency rules.

[0025] The invalid value handling rules include: marking and removing values ​​with negative weights or location information that exceeds the target area.

[0026] The missing value handling rules include: linear interpolation to fill consecutive missing parts of time series data;

[0027] The format standardization rules include: unifying the weight place and date format;

[0028] The logical consistency rules include: the start time of solid waste collection and transportation vehicles in the same city is earlier than the end time of collection and transportation; and the weight of solid waste at the start of collection and transportation of solid waste by solid waste collection and transportation vehicles in the same city is equal to the total weight of the vehicle monitored by the weighbridge minus the vehicle weight.

[0029] Furthermore, the urban solid waste recycling metabolic network optimization model mentioned in step S3 includes:

[0030] Network optimization decision variables include the amount of solid waste handled by firm i. ,and And the amount of solid waste transferred from enterprise i to treatment point j ,and ;in, Let J be the total amount of solid waste generated by enterprise i, where i = 1, 2, ..., I, j = 1, 2, ..., J;

[0031] The network optimization objective function aims to minimize the total cost and takes carbon emissions into account. The formula is as follows:

[0032]

[0033] In the formula, The cost of solid waste handled by the company itself is expressed in yuan / ton. The carbon emissions per unit of solid waste that the enterprise handles itself; The unit cost of solid waste transportation from enterprise i to treatment point j is expressed in yuan / ton. The cost per unit of waste treated by enterprise i at treatment point j, expressed in yuan / ton. The carbon emissions at treatment point j. This is the carbon price conversion factor, which is used to convert... and The unit is converted to yuan / ton.

[0034] Furthermore, the network optimization constraints, as defined in the formulas, include:

[0035] The solid waste balance constraint means that the sum of the amount of solid waste treated by the enterprise itself and the amount of solid waste transferred to the treatment point should equal the total amount of solid waste generated by the enterprise. The formula is as follows:

[0036]

[0037] Processing capacity constraint: The processing volume of a processing point cannot exceed its maximum processing capacity, as shown in the following formula:

[0038]

[0039] In the formula, This represents the maximum processing capacity of the j-th processing point;

[0040] Nonnegativity constraint: ;

[0041] Preferably, the preset solver is optimization software, such as CPLEX or Gurobi, to obtain the optimal solution. and Value, through optimal and The optimized solid waste metabolic network can be obtained by calculating the value.

[0042] It should be noted that solid waste metabolism includes three types: complete metabolism, incomplete metabolism, and no metabolism. No metabolism refers to a situation where the waste-generating source has no matching downstream receiving enterprise, and the generated solid waste is temporarily stored within the enterprise. Incomplete metabolism refers to a situation where the waste-generating source has a related downstream receiving enterprise, but the solid waste is not completely disposed of; some may be utilized by the waste-generating enterprise itself or stored on-site. Complete metabolism refers to a situation where the waste-generating source has a related downstream receiving enterprise, and all solid waste is transported away for treatment. After adopting this technical solution, the different solid waste metabolism pathways are quantified:

[0043] The solid waste categories generated by each source are summarized to form the solid waste metabolic balance equation for each source, as follows:

[0044]

[0045] In the formula, N is the number of types of solid waste generated by source i. To determine the amount of type j solid waste generated from source i, To generate the amount of type j solid waste that source i can process itself, To generate the amount of type j solid waste stored within the enterprise from source i, This refers to the amount of type j solid waste transferred outward from source i;

[0046] The non-metabolizable formula is as follows:

[0047]

[0048] In the formula, The solid waste production in the jth metabolic pathway of month r is expressed in tons. The amount processed by the enterprise itself in the jth metabolic pathway without metabolic pathway in month r is in tons; This refers to the solid waste storage volume in the jth non-metabolic pathway of month r, expressed in tons.

[0049] The formula for incomplete metabolism is as follows:

[0050]

[0051] In the formula, The amount of solid waste generated in the nth incomplete metabolic pathway in month r, in tons; The amount of waste disposed of by the enterprise itself within the nth incomplete metabolic pathway in month r, in tons; The amount of solid waste transported and disposed of in the nth incomplete metabolic pathway in month r is expressed in tons, including the amount treated and disposed of. This represents the solid waste storage volume in the nth incomplete metabolic pathway of month r, expressed in tons.

[0052] The complete metabolic formula is as follows:

[0053]

[0054] In the formula, The solid waste generated in the mth complete disposal pathway of month r is expressed in tons. The amount of solid waste transported and disposed of in the mth complete disposal route in month r is expressed in tons.

[0055] Metabolic pathway maps were created using ArcGIS, and the quantitative relationships between the various metabolic pathways are as follows:

[0056]

[0057]

[0058] In the formula, For all metabolic pathways in month r; The jth item of month r has no metabolism; The kth pathway in month r has a downstream metabolic pathway; This is the nth incomplete metabolic pathway in month r. This is the mth complete metabolic pathway in month r.

[0059] Furthermore, the urban solid waste recycling vehicle route optimization model described in step S4 includes: route optimization decision variables, wherein the route optimization decision variables include allocation variables. and driving path variables ;

[0060] in This indicates that the k-th vehicle is responsible for the i-th processing point, where k = 1, 2, ..., K, and K is the total number of vehicles; Let (a, b) represent the road segment chosen by the k-th vehicle, where a and b are road network nodes.

[0061] The multi-objective function for route optimization, designed based on transshipment cost and carbon emissions, is as follows:

[0062]

[0063] In the formula, and These represent the maximum and minimum values ​​of the ideal transportation cost, respectively. and These represent the maximum and minimum values ​​of carbon emissions under ideal conditions, respectively. , The value can be dynamically adjusted based on different companies, such as companies that prioritize cost. The value can be greater than Enterprises or industrial parks that prioritize environmental protection can improve... The weights, and .

[0064] The constraints for vehicle routing optimization include: the load capacity of vehicle k ≤ the maximum load capacity; the receiving capacity of the processing point ≤ the remaining capacity of the processing point.

[0065] Furthermore, step S4 also includes

[0066] Receive the optimal metabolic network obtained in step S3, including the amount of solid waste transferred from enterprise i to treatment point j. And the processing capacity constraints of the processing points, the processing capacity constraints of the processing points are those in step S3. Therefore, it can be based on and The remaining processing capacity of the processing point can then be calculated, which is... This ensures that routes that would transport excessive amounts of solid waste to a processing plant that is already nearing full capacity are not planned.

[0067] The vehicle route optimization results are output by solving the problem using optimization software such as CPLEX and Gurobi. The output results include the driving route of each vehicle, the amount of solid waste loaded and unloaded by each vehicle at each node, the cost and carbon emissions, and thus the optimal vehicle transportation route. In addition, the solution in step S3 is the same as here.

[0068] Furthermore, transportation costs Carbon emissions E are calculated using the following formulas:

[0069]

[0070]

[0071] In the formula, Indicates fuel cost, Indicates labor costs, Indicates depreciation cost. Indicates the carbon emission coefficient of fuel. The length of road segment (a, b) is in km. For fuel consumption function, The emissions from the treatment process, of which gasoline... Pick diesel Pick , The length of road segment (a, b) is in km. This is the fuel consumption function.

[0072] Furthermore, fuel costs Labor costs and depreciation costs Calculated using the following formulas respectively:

[0073]

[0074]

[0075]

[0076] In the formula, This indicates the unit price of fuel, expressed in yuan / L; This indicates the hourly wage for workers, expressed in yuan / h. This represents the speed at which vehicle k travels from a to b, expressed in km / h. The loading and unloading time at the i-th processing point is expressed in hours. This refers to the depreciation of a vehicle's mileage, expressed in yuan / km.

[0077] Furthermore, the solution results described in step S4 include: the driving path of each vehicle, the amount of solid waste loaded and unloaded by each vehicle at each node, the cost, and the carbon emissions.

[0078] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0079] 1. The method for constructing an urban solid waste recycling and metabolism network based on multi-source data provided by this invention effectively solves the problems of heterogeneity, noise, and missing values ​​in multi-source data through invalid value handling rules, missing value handling rules, format standardization rules, and logical consistency rules, providing a more accurate data foundation for subsequent steps;

[0080] 2. The method for constructing an urban solid waste recycling and metabolism network based on multi-source data provided by this invention achieves globally optimal resource allocation and improves solid waste recycling efficiency by constructing an urban solid waste recycling network;

[0081] 3. The method for constructing an urban solid waste recycling and metabolism network based on multi-source data provided by this invention constructs a path optimization model based on a multivariate objective function, thereby achieving path optimization for collection and transportation vehicles between nodes, improving transfer efficiency and reducing operating costs. Attached Figure Description

[0082] The present invention will be described by way of example and with reference to the accompanying drawings, wherein:

[0083] Figure 1 This is a flowchart of the present invention;

[0084] Figure 2 This invention does not include a metabolic pathway diagram;

[0085] Figure 3 This is an incomplete metabolic pathway diagram of the present invention;

[0086] Figure 4 This is a complete metabolic pathway diagram of the present invention;

[0087] Figure 5 This is a distribution map of enterprises and processing nodes in the target area of ​​the solid waste recycling project of this invention;

[0088] Figure 6 This is a metabolic cycle network diagram of the target area for solid waste recycling before optimization in this invention;

[0089] Figure 7 This is a metabolic cycle network diagram of the target area for solid waste recycling after optimization according to the present invention;

[0090] Figure 8 This is a metabolic cycle network diagram of the solid waste recycling target area after path optimization according to the present invention. Detailed Implementation

[0091] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the embodiments and accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. The components of the embodiments of this application described and marked in the accompanying drawings can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0092] In the description of the embodiments of this application, it should be noted that the terms "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship conventionally placed when the invention is used. They are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application. In addition, the terms "first," "second," and "third," etc., are only used to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0093] Example 1

[0094] A method for constructing an urban solid waste recycling and metabolism network based on multi-source data, such as Figure 1 As shown, the process includes the following steps: Step S1: Multi-source data collection is performed on the target area of ​​urban solid waste recycling. The multi-source data collection includes real-time data collection of multiple nodes of urban solid waste recycling through sensors, collection of business data through access to the business system, and acquisition of network data through web crawlers. The multiple nodes of urban solid waste recycling include urban solid waste generation nodes, transfer nodes, and processing nodes.

[0095] The real-time data acquisition of multiple nodes in the urban solid waste recycling system includes monitoring the weight of solid waste at the urban solid waste generation nodes through sensors, monitoring the weight of solid waste collected by vehicles through sensors, monitoring the location of solid waste collected by vehicles through locators, and monitoring the weight of vehicles entering and leaving the processing nodes by installing weighbridges at the entrances and exits of the urban solid waste treatment facilities.

[0096] In this embodiment, accessing the business system to collect business data refers to obtaining network data through internal enterprise data interfaces, including solid waste policies and solid waste production in the target area; network data refers to obtaining solid waste treatment costs and traffic information of different enterprises in the target area using web crawlers; in addition, the target area of ​​urban recycling is described, in which there are several solid waste generating enterprises and several solid waste treatment points.

[0097] Step S2: Clean and repair the multi-source data obtained in step S1 to form multiple high-quality datasets, and fuse the multiple high-quality datasets to obtain a fused dataset;

[0098] Step S2 specifically includes:

[0099] Step S2.1: Identify the multi-source data in Step S1, distinguish between numerical data and spatiotemporal data, and output the identification results. The numerical data may come from the solid waste weight monitored by the sensor or the vehicle weight monitored by the weighbridge. The spatiotemporal data includes location and time and comes from the locator.

[0100] In this embodiment, weight refers to a single measurement value, such as the reading of the smart solid waste bin at a certain moment being a fixed value, while output refers to the total amount of solid waste generated by the generation node within a certain period of time.

[0101] Step S2.2: Based on the recognition results output in step S2.1, construct cleaning rules, and clean and repair the multi-source data in step S1 based on the cleaning rules to obtain multiple high-quality datasets;

[0102] In step S2.2, the cleaning rules include invalid value handling rules, missing value handling rules, format standardization rules, and logical consistency rules.

[0103] The invalid value handling rules include: marking and removing values ​​with negative weights or location information exceeding the target area. For example, if the weight detected by the smart solid waste bin is ≤0kg, or the weight of the vehicle detected by the weighbridge at the processing node is ≤0kg, or the weight exceeds the reasonable range of the node (e.g., the maximum detection range of the smart solid waste bin is 500kg, but the detected value is 1000kg), it can be understood that values ​​exceeding the target area are invalid and need to be removed. In addition, invalid values ​​based on time, i.e., future timestamps, also need to be marked and removed. The smart waste bin can detect the weight and overflow level of solid waste through sensors. It can be applied to enterprises and parks to detect the solid waste production of enterprises or parks. In this embodiment, the location information exceeding the target area refers to the vehicle location information detected by the locator. If the vehicle drives out of the target area, it may indicate vehicle positioning drift, locator damage, etc. This data can be removed to improve data accuracy.

[0104] The missing value handling rules include: linear interpolation to fill consecutive missing portions of time series data. For example, at a transfer node, if vehicle load data is missing for one consecutive hour, linear interpolation is used to fill the missing portions, as shown in the following formula:

[0105]

[0106] In the formula, , For the previous valid point, , For the later valid point, , Indicates missing points, where the missing point is defined by the time or location of the missing information. The axis is determined by the values ​​to be filled (weight and position). axis;

[0107] The format standardization rules include: unifying the weight place value and date format, where the weight place value is kg and the time format is: year-month-day-specific time;

[0108] The logical consistency rules include: the start time of solid waste collection and transportation vehicles in the same city is earlier than the end time of collection and transportation; the weight of solid waste at the start of collection and transportation of solid waste by solid waste collection and transportation vehicles in the same city is equal to the total weight of the vehicle monitored by the weighbridge minus the vehicle weight.

[0109] In this embodiment, cleaning rules are constructed to provide an accurate and consistent data foundation for subsequent steps.

[0110] Step S2.3: Merge the multiple high-quality datasets obtained in step S2.2 to obtain a merged dataset;

[0111] In step S2.3, the Python pandas library is used to implement hierarchical association of multiple high-quality datasets by using the merge function based on key fields. For example, the association generates node and transit node data. Then, the concat function is used to horizontally concatenate the features of multiple nodes to form a fused dataset with a wide list structure. In this embodiment, the key fields are time, vehicle number, node information, etc.

[0112] Step S2.4: Perform spatiotemporal alignment on the fused dataset;

[0113] In step S2.4, the spatiotemporal alignment of the fused dataset is achieved through temporal granularity unification and spatial coordinate standardization. For temporal granularity unification, the core methods are aggregation and interpolation. In this embodiment, the target granularity is unified at the hour level. Hourly aggregation is implemented using the `resample` function of Python pandas. For high-frequency data, such as weight data collected by sensors, updates are typically performed every minute. For this frequently updated data, mean aggregation is used to average multiple data points within an hour. For low-frequency data, such as data collected from business systems, collection is typically performed daily. For this low-frequency updated data, linear interpolation is used to split the data by hour. For example, if a region produces 10 tons of solid waste per day, the interpolation is 1 ton per hour. Furthermore, temporal granularity unification also includes time format standardization, which has been preliminarily explained in the aforementioned format standardization rules. This involves standardizing the timestamps of the data to a unified format, thereby ensuring that the time fields of the open datasets can be directly correlated.

[0114] For spatial coordinate system standardization, this includes coordinate system unification and spatial grid partitioning. For coordinate system unification, in this embodiment, latitude and longitude are converted into a unified coordinate system, such as the WGS84 coordinate system, using the pyproj library. This coordinate system is compatible with mainstream map platforms such as Amap and Google Maps. For spatial grid partitioning, the target area is divided into fixed-length square grids, and each grid is assigned a unique grid ID. In this embodiment, a GeoDataFrame is created using GeoPandas, and the sjoin function is used to spatially connect node data with the grid, automatically assigning grid IDs.

[0115] Step S3: Construct an optimization model for the urban solid waste recycling and metabolism network. Based on the fusion dataset and preset solver in step S2, optimize the urban solid waste recycling and metabolism network optimization model to obtain the optimal metabolism network. The optimal metabolism network includes the solid waste transfer situation of each enterprise in the target area, including the proportion of solid waste that is self-processed and transferred to the treatment point for treatment.

[0116] Step S3 includes the following steps:

[0117] The urban solid waste recycling metabolism network optimization model mentioned in step S3 includes:

[0118] Network optimization decision variables include the amount of solid waste handled by firm i. ,and And the amount of solid waste transferred from enterprise i to treatment point j ,and ;in, Let J be the total amount of solid waste generated by enterprise i, where i = 1, 2, ..., I, j = 1, 2, ..., J;

[0119] The network optimization objective function aims to minimize the total cost and takes carbon emissions into account. The formula is as follows:

[0120]

[0121] In the formula, The cost of solid waste handled by the company itself is expressed in yuan / ton. The carbon emissions per unit of solid waste that the enterprise handles itself; The unit cost of solid waste transportation from enterprise i to treatment point j is expressed in yuan / ton. The cost per unit of waste treated by enterprise i at treatment point j, expressed in yuan / ton. The carbon emissions at treatment point j. This is the carbon price conversion factor, which is used to convert... and The unit is converted to yuan / ton.

[0122] Network optimization constraints, including the following formulas:

[0123] The solid waste balance constraint means that the sum of the amount of solid waste treated by the enterprise itself and the amount of solid waste transferred to the treatment point should equal the total amount of solid waste generated by the enterprise. The formula is as follows:

[0124]

[0125] Processing capacity constraint: The processing volume of a processing point cannot exceed its maximum processing capacity, as shown in the following formula:

[0126]

[0127] In the formula, This represents the maximum processing capacity of the j-th processing point;

[0128] Nonnegativity constraint: .

[0129] In this embodiment, the preset solver is optimization software, such as CPLEX or Gurobi, to obtain the optimal solution. and Value, through optimal and The optimized solid waste metabolic network can be obtained by calculating the value.

[0130] Step S4: Based on the optimal metabolic network obtained from step S3, construct an urban solid waste recycling vehicle path optimization model, optimize the driving path of urban solid waste recycling vehicles, and obtain the optimal path.

[0131] The urban solid waste recycling vehicle route optimization model described in step S4 includes: route optimization decision variables, which include allocation variables. and driving path variables ;

[0132] in This indicates that the k-th vehicle is responsible for the i-th processing point, where k = 1, 2, ..., K, and K is the total number of vehicles; Let (a, b) represent the road segment chosen by the k-th vehicle, where a and b are road network nodes.

[0133] The multi-objective function for route optimization, designed based on transshipment cost and carbon emissions, is as follows:

[0134]

[0135] In the formula, and These represent the maximum and minimum values ​​of the ideal transportation cost, respectively. and These represent the maximum and minimum values ​​of carbon emissions under ideal conditions, respectively. , The value can be dynamically adjusted based on different companies, such as companies that prioritize cost. The value can be greater than Enterprises or industrial parks that prioritize environmental protection can improve... The weights, and .

[0136] The constraints for vehicle routing optimization include: the load capacity of vehicle k ≤ the maximum load capacity; the receiving capacity of the processing point ≤ the remaining capacity of the processing point.

[0137] In this embodiment, the transportation cost Carbon emissions E are calculated using the following formulas:

[0138]

[0139]

[0140] In the formula Indicates fuel cost, Indicates labor costs, Indicates depreciation cost. Indicates the carbon emission coefficient of fuel. The length of road segment (a, b) is in km. For fuel consumption function, This refers to emissions during vehicle transport. For example, the carbon dioxide emissions from processing one ton of HW18 solid waste are 800 kg, of which gasoline... Pick diesel Pick , The length of road segment (a, b) is in km. This is the fuel consumption function.

[0141] fuel costs Labor costs and depreciation costs Calculated using the following formulas respectively:

[0142]

[0143]

[0144]

[0145] In the formula, This indicates the unit price of fuel, expressed in yuan / L; This indicates the hourly wage for workers, expressed in yuan / h. This indicates the transfer speed, in km / h. The loading and unloading time at the i-th processing point is expressed in hours. Depreciation per unit mileage for vehicles, expressed in yuan / km.

[0146] The output of step S4 includes: the driving route of each vehicle, the amount of solid waste loaded and unloaded by each vehicle at each node, the cost and carbon emissions, and is consistent with the solution in step S3. The above results are output by using optimization software such as CPLEX and Gurobi, namely the driving route of each vehicle, the amount of solid waste loaded and unloaded by each vehicle at each node, the cost and carbon emissions, and thus the optimal vehicle transportation route is obtained.

[0147] Example 2

[0148] The difference between this embodiment and Embodiment 1 is that the target area in this embodiment is a park, such as... Figures 2-4As shown, this park includes 8 companies with no metabolic waste, 7 companies with incomplete metabolic waste, and 5 companies with complete metabolic waste. Companies with no metabolic waste have no matching downstream receiving companies, and the solid waste generated is temporarily stored inside the company. Companies with incomplete metabolic waste have related downstream receiving companies, but the solid waste is not completely disposed of, and the waste-generating companies may use it themselves or store it on-site. Companies with complete metabolic waste have related downstream receiving companies, and all the solid waste is transported away for disposal.

[0149] In this embodiment, multi-source data related to solid waste in the park are collected according to step S1.

[0150] In this embodiment,

[0151] Quantification of different metabolic pathways:

[0152] The non-metabolizable formula is as follows:

[0153]

[0154] In the formula, The solid waste production in the jth metabolic pathway of month r is expressed in tons. The amount processed by the enterprise itself in the jth metabolic pathway of month r is in tons; The solid waste storage volume in the jth metabolic pathway of month r is expressed in tons.

[0155] The formula for incomplete metabolism is as follows:

[0156]

[0157] In the formula, The amount of solid waste generated in the nth incomplete metabolic pathway in month r, in tons; The amount of waste disposed of by the enterprise itself within the nth incomplete metabolic pathway in the month or year is expressed in tons. The amount of solid waste transported and disposed of in the nth incomplete metabolic pathway of month r is expressed in tons, including the amount treated and disposed of. This represents the solid waste storage volume in the nth incomplete metabolic pathway of month r, expressed in tons.

[0158] The complete metabolic formula is as follows:

[0159]

[0160] In the formula, The solid waste generated in the mth complete disposal pathway of month r is expressed in tons. The amount of solid waste transported and disposed of in the mth complete disposal route in month r is expressed in tons.

[0161] Metabolic pathway maps were created using ArcGIS, and the quantitative relationships between the various metabolic pathways are as follows:

[0162]

[0163]

[0164] In the formula, For all metabolic pathways in month r; The jth item of month r has no metabolism; The kth pathway in month r has a downstream metabolic pathway; This is the nth incomplete metabolic pathway in month r. This is the mth complete metabolic pathway in month r.

[0165] In this embodiment, the focus is on the metabolic network at the park scale, and path visualization is achieved through ArcGIS, providing an indicator system for evaluating the metabolic efficiency of solid waste in the park.

[0166] In this embodiment, the core problem of non-metabolism enterprises is the lack of downstream processing nodes. By using the urban solid waste recycling and metabolism network and vehicle route optimization model, suitable downstream processing resources are matched for non-metabolism enterprises to achieve the transformation from non-metabolism to incomplete or complete metabolism. For incomplete and complete metabolism, the overall cost is further reduced and carbon emissions are minimized through the optimization of the metabolism network and route optimization.

[0167] This embodiment takes a certain park as an example, such as Figures 5-8 As shown, the distribution of the number of enterprises with complete metabolism, incomplete metabolism, and no metabolism, as well as the number of enterprise types and paths before and after optimization, are statistically analyzed.

[0168] Depend on Figure 5 It can be seen that within the target area, there are 3 companies with complete metabolism, 5 companies with incomplete metabolism, and 2 companies with no metabolism. Figure 6 , Figure 7 It can be seen that after optimization through the urban solid waste recycling and metabolism network, the number of enterprises without metabolism decreased by 1 after one month, while the number of enterprises with incomplete metabolism and complete metabolism decreased by 1 and increased by 2, respectively. Among them, 2 enterprises transformed from incomplete metabolism enterprises to complete metabolism enterprises, and 1 enterprise transformed from a non-metabolizing enterprise to an incomplete metabolism enterprise. Figure 7 , Figure 8 It can be seen that the transfer route is optimized through the solid waste recycling vehicle route optimization model.

[0169] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for constructing an urban solid waste recycling and metabolism network based on multi-source data, characterized in that, Includes the following steps: Step S1: Conduct multi-source data collection on the target area of ​​urban solid waste recycling. This multi-source data collection includes real-time data acquisition from multiple nodes in the urban solid waste recycling system via sensors, acquisition of business data from the business system, and acquisition of network data via web crawlers. The multiple nodes in the urban solid waste recycling system include urban solid waste generation nodes, transfer nodes, and processing nodes. Step S2: Clean and repair the multi-source data obtained in step S1 to form multiple high-quality datasets, and fuse the multiple high-quality datasets to obtain a fused dataset; Step S3: Construct an optimization model for the urban solid waste recycling and metabolism network. Based on the fusion dataset and preset solver in step S2, optimize the urban solid waste recycling and metabolism network optimization model to obtain the optimal metabolism network. The optimal metabolism network includes the solid waste transfer situation of each enterprise in the target area, including the proportion of solid waste that is self-processed and transferred to the treatment point for treatment. Step S4: Based on the optimal metabolic network obtained from step S3, construct an urban solid waste recycling vehicle path optimization model, optimize the driving path of urban solid waste recycling vehicles, and obtain the optimal path.

2. The method for constructing an urban solid waste recycling and metabolism network based on multi-source data as described in claim 1, characterized in that, In step S1, the real-time data acquisition of multi-node urban solid waste recycling includes: The system monitors the weight of solid waste at urban solid waste generation points using sensors, monitors the weight of solid waste collected by vehicles using sensors, monitors the location of solid waste collected by vehicles using locators, and monitors the total weight of vehicles entering and leaving the urban solid waste treatment facilities by installing weighbridges at the entrances and exits of the treatment facilities.

3. The method for constructing an urban solid waste recycling and metabolism network based on multi-source data as described in claim 1, characterized in that, Step S2 includes: Step S2.1: Identify the multi-source data in step S1, distinguish between numerical data and spatiotemporal data, and output the identification results; Step S2.2: Based on the recognition results output in step S2.1, construct cleaning rules, and clean and repair the multi-source data in step S1 based on the cleaning rules to obtain multiple high-quality datasets; Step S2.3: Merge the multiple high-quality datasets obtained in step S2.2 to obtain a merged dataset; Step S2.4: Perform spatiotemporal alignment on the fused dataset.

4. The method for constructing an urban solid waste recycling and metabolism network based on multi-source data as described in claim 3, characterized in that, In step S2.2, the cleaning rules include invalid value handling rules, missing value handling rules, format standardization rules, and logical consistency rules. The invalid value handling rules include: marking and removing values ​​with negative weights or location information that exceeds the target area. The missing value handling rules include: linear interpolation to fill consecutive missing parts of time series data; The format standardization rules include: unifying the weight place and date format; The logical consistency rules include: the start time of solid waste collection and transportation vehicles in the same city is earlier than the end time of collection and transportation; and the weight of solid waste at the start of collection and transportation of solid waste by solid waste collection and transportation vehicles in the same city is equal to the total weight of the vehicle monitored by the weighbridge minus the vehicle weight.

5. The method for constructing an urban solid waste recycling and metabolism network based on multi-source data as described in claim 3, characterized in that, The urban solid waste recycling metabolism network optimization model mentioned in step S3 includes: Network optimization decision variables include the amount of solid waste handled by firm i. ,and And the amount of solid waste transferred from enterprise i to treatment point j ,and ;in, Let J be the total amount of solid waste generated by enterprise i, where i = 1, 2, ..., I, j = 1, 2, ..., J; The network optimization objective function aims to minimize the total cost and takes carbon emissions into account. The formula is as follows: ； In the formula, The cost of solid waste handled by the company itself is expressed in yuan / ton. The carbon emissions per unit of solid waste that the enterprise handles itself; The unit solid waste transfer cost from enterprise i to treatment point j is expressed in yuan / ton. The cost per unit of solid waste treated by enterprise i at treatment point j, expressed in yuan / ton. The carbon emissions at treatment point j. This is the carbon price conversion factor, which is used to convert... and Unit converted to yuan / ton; The network optimization constraints are given by the following formula: ； ； ； In the formula, This represents the maximum processing capacity of the j-th processing point.

6. The method for constructing an urban solid waste recycling and metabolism network based on multi-source data as described in claim 1, characterized in that, The urban solid waste recycling vehicle route optimization model described in step S4 includes: Path optimization decision variables, including allocation variables and driving path variables ; The multi-objective function for route optimization, designed based on transshipment cost and carbon emissions, is as follows: ； In the formula, and These represent the maximum and minimum values ​​of the ideal transportation cost, respectively. and These represent the maximum and minimum values ​​of carbon emissions under ideal conditions. , These are the weighting coefficients; The constraints for vehicle routing optimization include: the load capacity of vehicle k ≤ the maximum load capacity; the receiving capacity of the processing point ≤ the remaining capacity of the processing point.

7. The method for constructing an urban solid waste recycling and metabolism network based on multi-source data as described in claim 6, characterized in that, Transportation costs Carbon emissions E are calculated using the following formulas: ； ； In the formula, Indicates fuel cost, Indicates labor costs, Indicates depreciation cost. Indicates the carbon emission coefficient of fuel. The length of road segment (a, b) is in km. For fuel consumption function, This refers to emissions during vehicle transport.

8. The method for constructing an urban solid waste recycling and metabolism network based on multi-source data as described in claim 7, characterized in that, fuel costs Labor costs and depreciation costs Calculated using the following formulas respectively: ； ； ； In the formula, This indicates the unit price of fuel, expressed in yuan / L; This indicates the worker's hourly wage, expressed in yuan / h. This represents the speed at which vehicle k travels from a to b, expressed in km / h. The loading and unloading time at the i-th processing point is expressed in hours. Depreciation per unit mileage for vehicles, expressed in yuan / km.

9. The method for constructing an urban solid waste recycling and metabolism network based on multi-source data as described in claim 7, characterized in that, The solution results described in step S4 include: the driving path of each vehicle, the amount of solid waste loaded and unloaded by each vehicle at each node, the cost, and the carbon emissions.

Images