Garbage collection and transportation vehicle carbon emission optimization management system based on Internet of Things

Abstract

The invention relates to the technical field of garbage collection, in particular to a garbage collection and transportation vehicle carbon emission optimization management system based on the Internet of Things. Vehicle information and operation information of a plurality of garbage collection and transportation vehicles are collected through a collection assembly, all data information is preprocessed through an optimization assembly, an optimization model is created, and the unit garbage collection and transportation cost and the garbage content of a unit route of each target collection and transportation vehicle are calculated through the optimization model. The method comprises the following steps: training an optimization model, establishing a collection and transportation standard of a garbage collection and transportation vehicle, optimizing an operation route based on the collection and transportation standard of the garbage collection and transportation vehicle, inputting real-time information into the trained optimization model, and optimizing the carbon emission of the real-time collection and transportation vehicle through the trained optimization model. According to the invention, the collection and transportation standard of the garbage collection and transportation vehicle is established, so that the user can optimize the carbon emission of the garbage collection and transportation vehicle from two different aspects of vehicle information or operation information, thereby improving the optimization efficiency and screening out the optimal scheme.

Description

Technical Field

[0001] This invention relates to the field of waste recycling and treatment technology, and more specifically, to an Internet of Things-based carbon emission optimization management system for waste collection vehicles. Background Technology

[0002] Garbage collection and transportation vehicles typically refer to vehicles used for collecting, transferring, and transporting household waste (or specific types of waste) within the urban environmental sanitation system. Their core function is to collect garbage scattered throughout residential areas, commercial districts, and public places, and efficiently transport it to waste treatment plants (such as incinerators, landfills, and food waste treatment centers). They are one of the key pieces of equipment in the modern sanitation system.

[0003] The core of achieving intelligent scheduling of garbage collection vehicles is to solve problems such as "longer routes, high empty running rate, delayed response, and waste of resources" in traditional manual scheduling by using data-driven algorithm optimization, real-time Internet of Things (IoT) perception, and dynamic decision-making system, and ultimately achieve the goals of "cost reduction, efficiency improvement, and environmental protection".

[0004] Chinese Patent CN111010427B discloses an Internet of Things (IoT)-based urban waste collection and recycling system. When the management server receives a full signal from the waste collection bins in the waste collection device via the IoT, the management server sends collection information to the nearest waste collection vehicle via the IoT, and the waste collection vehicle collects the waste from the waste collection device. This IoT-based urban waste collection and recycling system provides unified management of the waste collection device and waste collection vehicles. However, existing technologies do not intelligently manage the operating routes or vehicle conditions of waste collection vehicles, leading to increased collection costs and higher carbon emissions. Summary of the Invention

[0005] The purpose of this invention is to provide an Internet of Things-based carbon emission optimization management system for garbage collection vehicles to solve the problems mentioned in the background art.

[0006] To address the aforementioned technical problems, one objective of this invention is to provide an Internet of Things (IoT)-based carbon emission optimization management system for garbage collection vehicles. This system includes multiple garbage collection vehicles, a data acquisition component, and an optimization component. The data acquisition component collects vehicle information and operational information from the garbage collection vehicles. The optimization component is communicatively connected to the data acquisition component. All data collected by the data acquisition component is input into the optimization component, which then performs the following steps: All data information is preprocessed to obtain preprocessed information; Create an optimization model; Multiple preprocessed information is input into the optimization model. The optimization model calculates the unit waste collection cost and the waste content per unit route for each target collection vehicle. Based on this, the collection standards for waste collection vehicles are established. Finally, the operation routes are optimized based on the collection standards for waste collection vehicles. Real-time information from garbage collection vehicles is collected and input into a trained optimization model. The carbon emissions of the garbage collection vehicles are then optimized using the trained optimization model. The collection components include a vehicle collection module and an operation collection module. The vehicle collection module collects vehicle information of the garbage collection vehicles, and the operation collection module collects operation information of the garbage collection vehicles. The vehicle information includes vehicle model, vehicle fuel consumption, and vehicle volume. The operation information includes vehicle routes and the amount of garbage collected on each route.

[0007] Preferably, all data information is preprocessed to obtain preprocessed information, including: The vehicle information and operational information of a randomly selected garbage collection truck were collected. Determine if there is duplicate data in the vehicle information and operational information of the garbage collection truck; If there is duplicate data in the vehicle information or operation information of the garbage collection vehicle, the duplicate data will be deleted. The system returns the vehicle information and operational information of a randomly selected garbage collection truck until all garbage collection trucks have been selected, resulting in multiple pre-processed data sets. The pre-processed data sets include pre-processed vehicle information and pre-processed operational information.

[0008] Preferably, multiple preprocessed information items are input into the optimization model. The optimization model calculates the unit waste collection cost and waste content per unit route for each target collection vehicle, and establishes collection standards for the waste collection vehicles based on these standards. Finally, the operation routes are optimized based on these standards, including: All preprocessed data are divided into training and test sets according to a random ratio; The training set is input into the optimization model, which calculates the vehicle standards for different types of garbage collection vehicles based on the preprocessed vehicle information. The preprocessed operation information is then imported into the collection standards to create the collection standards for garbage collection vehicles. The operating routes of garbage collection vehicles are adjusted based on their collection standards to obtain a trained optimization model. Input the test set into the trained and optimized model to verify whether the trained and optimized model has been successfully trained.

[0009] Preferably, the training set is input into the optimization model, which calculates vehicle standards for different types of garbage collection vehicles based on preprocessed vehicle information. Then, the preprocessed operational information is imported into the collection standards to create garbage collection vehicle standards, including: Select the pre-processing vehicle information and pre-processing operation information of a garbage collection truck from the training set; The collection and transportation cost required for the garbage collection vehicle to collect a unit volume of garbage is calculated based on the pre-processed vehicle information; the collection and transportation cost required for the garbage collection vehicle to collect a unit volume of garbage is recorded as the unit garbage collection and transportation cost; The amount of waste per unit route of the waste collection vehicle is calculated based on pre-processing operation information; Establish a coupling relationship between unit waste collection and transportation cost and waste content per unit route; this coupling relationship is the collection and transportation standard for waste collection vehicles. Return the pre-processing vehicle information and pre-processing operation information of a garbage collection truck selected from the training set, until all garbage collection trucks have been selected, and obtain the collection standards for each garbage collection truck.

[0010] Preferably, the optimized model is obtained by adjusting the operating routes of garbage collection vehicles based on their collection standards, and then training the model, including: The vehicle information and operational information of the collection and transportation vehicles to be tested are input into the optimization model; The testing standards for the tested collection and transportation vehicles are calculated by optimizing the model. Set the difference threshold; The garbage collection vehicles corresponding to the tested collection vehicles are obtained through cluster analysis, and the garbage collection vehicles corresponding to the tested collection vehicles are recorded as target collection vehicles; Obtain the collection standard of the target collection vehicle and calculate the difference between the collection standard of the tested collection vehicle and the collection standard of the target collection vehicle. Determine whether the difference between the tested collection standard of the collection vehicle and the collection standard of the target collection vehicle is greater than or equal to the difference threshold. If the difference between the tested collection standard of the tested collection vehicle and the collection standard of the target collection vehicle is greater than or equal to the difference threshold, the operation information of the tested collection vehicle will be adjusted until the difference between the tested collection standard of the tested collection vehicle and the collection standard of the target collection vehicle is less than the difference threshold.

[0011] Real-time information from the real-time collection and transportation vehicles is collected and input into a trained optimization model. This model then optimizes the carbon emissions of the vehicles, including: Collect real-time information of the collection and transportation vehicles; the real-time information includes real-time collection and transportation vehicle information or real-time operation information; The real-time collection and transportation vehicle information is input into the trained optimization model. The trained optimization model is then used to perform cluster analysis on the real-time collection and transportation vehicles to obtain the target collection and transportation vehicles corresponding to the real-time collection and transportation vehicles. Obtain the collection standards for the target collection vehicle; Adjust the real-time operating routes of collection vehicles based on the collection standards of the target collection vehicles.

[0012] The process involves collecting real-time information from real-time collection vehicles, inputting this information into a trained optimization model, and then using this model to optimize the carbon emissions of the real-time collection vehicles. This also includes: Collect real-time information of the collection and transportation vehicles; the real-time information includes real-time collection and transportation vehicle information or real-time operation information. Real-time operational information is input into the trained optimization model, and the trained optimization model is used to perform cluster analysis on the real-time collection and transportation vehicles to obtain the target collection and transportation vehicles corresponding to the real-time collection and transportation vehicles. Obtain the collection standards for the target collection vehicle; Select appropriate real-time collection vehicles based on the collection standards of the target collection vehicles.

[0013] Adjusting the real-time operating routes of collection vehicles based on the collection standards of the target collection vehicles, including: Calculate the real-time waste collection and transportation cost of real-time collection vehicles based on real-time collection vehicle information; Obtain the amount of waste per unit route from the collection standards of the target collection vehicles; The target route is obtained based on the amount of waste per unit route, and this target route is the operating route of the real-time collection vehicle.

[0014] Compared with the prior art, the beneficial effects of the present invention are as follows: This application collects vehicle and operational information from multiple waste collection vehicles using a data acquisition component. The collected data is then input into an optimization component. This optimization component preprocesses all data to obtain preprocessed information and creates an optimization model. The preprocessed information is then input into the optimization model, which calculates the unit waste collection cost and waste content per route for each target collection vehicle. Based on this, a waste collection standard is established. Finally, operational routes are optimized based on this standard. Real-time information from the collection vehicles is collected and input into the trained optimization model. This trained model then optimizes the carbon emissions of the real-time collection vehicles. By establishing waste collection standards, this application allows users to optimize the carbon emissions of waste collection vehicles from two different perspectives: vehicle information and operational information. This improves optimization efficiency and helps identify the optimal solution. Attached Figure Description

[0015] Figure 1 A schematic diagram of the connection of the IoT-based waste collection vehicle carbon emission optimization management system; Figure 2 A flowchart illustrating the optimization components of an IoT-based waste collection vehicle carbon emission optimization management system; Reference numerals: 100, garbage collection vehicle; 200, data acquisition component; 201, vehicle data acquisition module; 202. Operations data collection module; 300. Optimization components. Detailed Implementation

[0016] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0017] Example 1 like Figure 1 and Figure 2 As shown, one of the objectives of this invention is to provide an Internet of Things-based carbon emission optimization management system for garbage collection vehicles, including multiple garbage collection vehicles, a data acquisition component, and an optimization component. The data acquisition component collects vehicle information and operational information of the garbage collection vehicles. The optimization component is communicatively connected to the data acquisition component. All data collected by the data acquisition component is input into the optimization component, which then performs the following steps: S100, preprocess all data information to obtain preprocessed information; S200, create an optimization model; S300 inputs multiple preprocessed information into the optimization model, calculates the unit waste collection cost and waste content per unit route for each target collection vehicle through the optimization model, establishes the collection standards for waste collection vehicles based on these standards, and finally optimizes the operation routes based on the collection standards of the waste collection vehicles. The S400 collects real-time information from the real-time collection and transportation vehicles, inputs this information into a trained optimization model, and optimizes the carbon emissions of the vehicles through the trained optimization model.

[0018] It should be noted that the data acquisition component collects vehicle and operational information from multiple garbage collection vehicles, and inputs the collected data into the optimization component. All data from the optimization component is preprocessed to obtain preprocessed information, and an optimization model is created. Then, multiple preprocessed data are input into the optimization model, which calculates the unit garbage collection cost and garbage content per route for each target collection vehicle, establishing collection standards for the garbage collection vehicles. Finally, operational routes are optimized based on these standards. Real-time information from the collection vehicles is collected and input into the trained optimization model, which then optimizes the carbon emissions of the real-time collection vehicles. This application, by establishing collection standards for garbage collection vehicles, allows users to optimize the carbon emissions of garbage collection vehicles from two different perspectives: vehicle information and operational information, thereby improving optimization efficiency and selecting the optimal solution.

[0019] In one embodiment of this application, the data collection component includes a vehicle data collection module and an operation data collection module. The vehicle data collection module collects vehicle information of the garbage collection vehicles, and the operation data collection module collects operation information of the garbage collection vehicles.

[0020] It should be noted that different data information of the target chip is collected by different acquisition components to avoid information leakage due to information overlap. In order to increase the number of training samples and ensure data reliability, the operation acquisition module is set up not only in the garbage collection truck, but also at each garbage recycling station to estimate the amount of garbage recycled at each garbage recycling station.

[0021] In one embodiment of this application, the vehicle information includes vehicle model, vehicle fuel consumption and vehicle volume, and the operation information includes vehicle routes and the amount of garbage collected on each route.

[0022] It should be noted that, in order to reduce the carbon emissions of garbage collection vehicles, intelligent scheduling of garbage collection vehicles is used to reduce the energy consumed by garbage collection vehicles during garbage collection, thereby reducing carbon emissions. The core data for achieving intelligent scheduling is the vehicle information of garbage collection vehicles, which mainly includes the basic attribute information, operating status information, and operational capacity information of garbage collection vehicles, thereby clarifying the recycling capacity of garbage collection vehicles.

[0023] In one embodiment of this application, S100 includes: S110, randomly select the vehicle information and operation information of a garbage collection truck; S120, determine whether there is duplicate data in the vehicle information and operation information of the garbage collection vehicle; S130, If there is duplicate data in the vehicle information or operation information of the garbage collection vehicle, delete the duplicate data; S140, return the vehicle information and operation information of a randomly selected garbage collection truck until all garbage collection trucks have been selected, and obtain multiple pre-processed data; the pre-processed data includes pre-processed vehicle information and pre-processed operation information.

[0024] It should be noted that after collecting data from different models of garbage collection vehicles, all data was preprocessed to remove invalid data in order to improve the quality of the data. This reduced the amount of data required for subsequent optimization model processing, thus improving the training efficiency of the optimization model. Furthermore, the improved data quality made the trained optimization model more reliable.

[0025] In one embodiment of this application, S300 includes: S310, divide all preprocessed data into training and test sets according to a random ratio; S320 inputs the training set into the optimization model, and the optimization model calculates the vehicle standards for different types of garbage collection vehicles based on the preprocessed vehicle information. Then, the preprocessed operation information is imported into the collection standards to create the collection standards for garbage collection vehicles. S330, based on the collection and transportation standards of garbage collection vehicles, adjusts the operating routes of garbage collection vehicles to obtain a trained optimized model; S340: Input the test set into the trained optimization model to verify whether the trained optimization model has been successfully trained.

[0026] It should be noted that when dividing the training set and the test set, the proportion of the training set should be greater than that of the test set to ensure that there is a sufficient amount of training data in the training set.

[0027] After dividing the training and testing sets, the training data in the training set is input into the optimization model. The optimization model creates collection standards for each garbage collection vehicle of the same model. Based on the collection standards, the optimization model is subjected to multi-classification learning to obtain the trained optimization model. The trained optimization model has the ability to automatically output the collection standards of the garbage collection vehicle based on the data information of the input garbage collection vehicle.

[0028] After obtaining the trained and optimized model, the training of the optimized model is verified by inputting the test set into the trained and optimized model and using the response speed / accuracy as the judgment criteria.

[0029] In one embodiment of this application, S320 includes: S321, Select the pre-processing vehicle information and pre-processing operation information of a garbage collection truck from the training set; S322, Calculate the collection cost required for the garbage collection vehicle to collect a unit volume of garbage based on the pre-processed vehicle information; record the collection cost required for the garbage collection vehicle to collect a unit volume of garbage as the unit garbage collection cost; S323, Calculate the amount of garbage per unit route of the garbage collection vehicle based on pre-processing operation information; S324, Establish the coupling relationship between unit waste collection and transportation cost and waste content per unit route. This coupling relationship is the collection and transportation standard for waste collection vehicles. S325 returns the pre-processing vehicle information and pre-processing operation information of a garbage collection vehicle selected from the training set, until all garbage collection vehicles have been selected, and obtains the collection standards for each garbage collection vehicle.

[0030] It should be noted that Formula 1 is used to calculate the unit waste collection cost of a waste collection vehicle; P=CS (Formula 1) Where P is the unit waste collection cost of the waste collection vehicle, C is the maximum amount of waste collected by the waste collection vehicle in a single complete collection route, and S is the consumption cost of the waste collection vehicle in a single complete collection route. The amount of garbage per unit route of a garbage collection vehicle is calculated using Formula 2; M=i=1i=Nmi Formula 2; Where M is the amount of garbage per unit route of the garbage collection truck, mi is the amount of garbage at the i-th garbage collection station on the operating route of the garbage collection truck, and N is the total number of garbage collection stations included in the operating route of the garbage collection truck. After obtaining the unit waste collection cost of a waste collection vehicle and the amount of waste per unit route, the two data points can be coupled to obtain the cost required for the waste collection vehicle to collect waste on its unit route. Therefore, by optimizing the cost of the waste collection vehicle or increasing the amount of waste per unit route, the carbon emissions of the waste collection vehicle can be optimized.

[0031] In one embodiment of this application, S330 includes: S331, input the vehicle information and operation information of the collection and transportation vehicle to be tested into the optimization model; S332, calculates the test collection and transportation standards of the tested collection and transportation vehicle through an optimization model; S333, set the difference threshold; S334, the garbage collection vehicle corresponding to the tested collection vehicle is obtained through cluster analysis, and the garbage collection vehicle corresponding to the tested collection vehicle is recorded as the target collection vehicle; S335, obtain the collection standard of the target collection vehicle, and calculate the difference between the measured collection standard of the tested collection vehicle and the collection standard of the target collection vehicle; S336, determine whether the difference between the tested collection standard of the tested collection vehicle and the collection standard of the target collection vehicle is greater than or equal to the difference threshold. S337 If the difference between the measured collection standard of the tested collection vehicle and the collection standard of the target collection vehicle is greater than or equal to the difference threshold, the operation information of the tested collection vehicle shall be adjusted until the difference between the measured collection standard of the tested collection vehicle and the collection standard of the target collection vehicle is less than the difference threshold.

[0032] It should be noted that in this application, the K-means clustering method can be used to perform cluster analysis on the tested collection and transportation vehicles and garbage collection vehicles, thereby selecting the target collection and transportation vehicle that is most similar to the tested collection and transportation vehicle from multiple garbage collection and transportation vehicles in the database of the optimization model. This "similarity" can be changed according to different clustering conditions. For example, when "vehicle information" is used as the clustering condition, the target collection and transportation vehicle is the vehicle that is most similar to the tested collection and transportation vehicle in terms of vehicle information. However, if "operational information" is used as the clustering condition, the target collection and transportation vehicle is the vehicle that is most similar to the tested collection and transportation vehicle in terms of operation information.

[0033] Depending on the clustering conditions, different target collection and transportation vehicles are obtained. Therefore, the collection and transportation vehicles under test can be adjusted in two ways: one is to adjust the vehicle type of the collection and transportation vehicles under test while keeping the operating route unchanged; the other is to adjust the operating route of the vehicles while keeping the vehicle information of the collection and transportation vehicles under test unchanged.

[0034] In one embodiment of this application, S400 includes: S410, collect real-time information of the collection and transportation vehicles; the real-time information includes real-time collection and transportation vehicle information or real-time operation information. S411, Input the real-time collection and transportation vehicle information into the trained optimization model, and perform cluster analysis on the real-time collection and transportation vehicles through the trained optimization model to obtain the target collection and transportation vehicles corresponding to the real-time collection and transportation vehicles; S412, Obtain the collection standards for the target collection vehicle; S413 adjusts the real-time operating routes of collection vehicles based on the collection standards of the target collection vehicles.

[0035] It should be noted that, in this embodiment, the adjustment of the real-time collection vehicle is to adjust the vehicle's operational information while keeping the vehicle information unchanged. Since the vehicle information cannot be adjusted, the carbon emissions of the real-time collection vehicle are optimized by improving the vehicle's operating route to increase the amount of waste per unit route.

[0036] In one embodiment of this application, S400 includes: S421, Collect real-time information of the collection and transportation vehicles; the real-time information includes real-time collection and transportation vehicle information or real-time operation information. S422, input real-time operation information into the trained optimization model, and perform cluster analysis on the real-time collection and transportation vehicles through the trained optimization model to obtain the target collection and transportation vehicles corresponding to the real-time collection and transportation vehicles; S423, Obtain the collection standards for the target collection vehicle; S424, Select a suitable real-time collection vehicle based on the collection standards of the target collection vehicle.

[0037] It should be noted that, in this embodiment, the adjustment of the real-time collection vehicle is to adjust the vehicle information while keeping the operating route of the collection vehicle unchanged, so as to select a suitable vehicle type and select the vehicle with the lower unit waste collection cost on the operating route as the real-time collection vehicle, thereby reducing the carbon emissions of the real-time collection vehicle.

[0038] In one embodiment of this application, S413 includes: S4131, Calculate the real-time waste collection cost of the real-time collection vehicle based on real-time collection vehicle information; S4132, Obtain the waste content per unit route from the collection standards of the target collection vehicle; S4133, obtain the target route based on the amount of waste per unit route, which is the real-time operating route of the collection vehicle.

[0039] It should be noted that since the target collection vehicles corresponding to the real-time collection vehicles were obtained through cluster analysis, and since the target collection vehicles are the vehicles that are most similar to or even identical to the real-time collection vehicles in terms of vehicle information, it can be assumed that the unit waste collection cost of the target collection vehicles is very close to the real-time waste collection cost of the real-time collection vehicles. Based on this, it is only necessary to customize the operating routes of the real-time collection vehicles according to the operating routes of the target collection vehicles, thereby improving the efficiency of adjusting the operating routes of the real-time collection vehicles and optimizing the carbon emissions of the real-time collection vehicles.

[0040] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely preferred examples and are not intended to limit the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of the present invention is defined by the appended claims and their equivalents.

Claims

1. A carbon emission optimization management system for garbage collection vehicles based on the Internet of Things, characterized in that, include: Multiple garbage collection trucks; Data acquisition components; The collection components collect vehicle information and operational information of garbage collection vehicles. Optimize components; The optimization component is communicatively connected to the acquisition component. All data acquired by the acquisition component is input into the optimization component, which then performs the following steps: All data information is preprocessed to obtain preprocessed information; Create an optimization model; Multiple preprocessed information is input into the optimization model. The optimization model calculates the unit waste collection cost and the waste content per unit route for each target collection vehicle. Based on this, the collection standards for waste collection vehicles are established. Finally, the operation routes are optimized based on the collection standards for waste collection vehicles. Real-time information from real-time collection and transportation vehicles is collected and input into a trained optimization model. The carbon emissions of the real-time collection and transportation vehicles are then optimized through the trained optimization model.

2. The IoT-based carbon emission optimization management system for garbage collection vehicles according to claim 1, characterized in that, The data collection components include a vehicle data collection module and an operation data collection module. The vehicle data collection module collects vehicle information of the garbage collection vehicles, and the operation data collection module collects operation information of the garbage collection vehicles.

3. The IoT-based carbon emission optimization management system for garbage collection vehicles according to claim 2, characterized in that, The vehicle information includes vehicle model, fuel consumption, and vehicle volume, while the operational information includes vehicle routes and the amount of waste collected on each route.

4. The IoT-based carbon emission optimization management system for garbage collection vehicles according to claim 3, characterized in that, All data is preprocessed to obtain preprocessed information, including: The vehicle information and operational information of a randomly selected garbage collection truck were collected. Determine if there is duplicate data in the vehicle information and operational information of the garbage collection truck; If there is duplicate data in the vehicle information or operation information of the garbage collection vehicle, the duplicate data will be deleted. The system returns the vehicle information and operational information of a randomly selected garbage collection truck until all garbage collection trucks have been selected, resulting in multiple pre-processed data sets. The pre-processed data sets include pre-processed vehicle information and pre-processed operational information.

5. The IoT-based carbon emission optimization management system for garbage collection vehicles according to claim 4, characterized in that, Multiple preprocessed information items are input into the optimization model. The model calculates the unit waste collection cost and waste content per unit route for each target collection vehicle, establishing collection standards for the vehicles. Finally, operational routes are optimized based on these standards, including: All preprocessed data are divided into training and test sets according to a random ratio; The training set is input into the optimization model, which calculates the vehicle standards for different types of garbage collection vehicles based on the preprocessed vehicle information. The preprocessed operation information is then imported into the collection standards to create the collection standards for garbage collection vehicles. The operating routes of garbage collection vehicles are adjusted based on their collection standards to obtain a trained optimization model. Input the test set into the trained and optimized model to verify whether the trained and optimized model has been successfully trained.

6. The IoT-based carbon emission optimization management system for garbage collection vehicles according to claim 5, characterized in that, The training set is input into the optimization model, which calculates vehicle standards for different types of garbage collection vehicles based on preprocessed vehicle information. Then, preprocessed operational information is imported into the collection standards to create garbage collection vehicle standards, including: Select the pre-processing vehicle information and pre-processing operation information of a garbage collection truck from the training set; The collection and transportation cost required for the garbage collection vehicle to collect a unit volume of garbage is calculated based on the pre-processed vehicle information; the collection and transportation cost required for the garbage collection vehicle to collect a unit volume of garbage is recorded as the unit garbage collection and transportation cost; The amount of waste per unit route of the waste collection vehicle is calculated based on pre-processing operation information; Establish a coupling relationship between unit waste collection and transportation cost and waste content per unit route; this coupling relationship is the collection and transportation standard for waste collection vehicles. Return the pre-processing vehicle information and pre-processing operation information of a garbage collection truck selected from the training set, until all garbage collection trucks have been selected, and obtain the collection standards for each garbage collection truck.

7. The IoT-based carbon emission optimization management system for garbage collection vehicles according to claim 6, characterized in that, The operational routes of garbage collection vehicles are adjusted based on their collection standards to obtain a trained optimization model, including: The vehicle information and operational information of the collection and transportation vehicles to be tested are input into the optimization model; The testing standards for the tested collection and transportation vehicles are calculated by optimizing the model. Set the difference threshold; The garbage collection vehicles corresponding to the tested collection vehicles are obtained through cluster analysis, and the garbage collection vehicles corresponding to the tested collection vehicles are recorded as target collection vehicles; Obtain the collection standard of the target collection vehicle and calculate the difference between the collection standard of the tested collection vehicle and the collection standard of the target collection vehicle. Determine whether the difference between the tested collection standard of the collection vehicle and the collection standard of the target collection vehicle is greater than or equal to the difference threshold. If the difference between the tested collection standard of the tested collection vehicle and the collection standard of the target collection vehicle is greater than or equal to the difference threshold, the operation information of the tested collection vehicle will be adjusted until the difference between the tested collection standard of the tested collection vehicle and the collection standard of the target collection vehicle is less than the difference threshold.

8. The IoT-based carbon emission optimization management system for garbage collection vehicles according to claim 7, characterized in that, Real-time information from the real-time collection and transportation vehicles is collected and input into a trained optimization model. This model then optimizes the carbon emissions of the vehicles, including: Collect real-time information of the collection and transportation vehicles; the real-time information includes real-time collection and transportation vehicle information or real-time operation information. The real-time collection and transportation vehicle information is input into the trained optimization model. The trained optimization model is then used to perform cluster analysis on the real-time collection and transportation vehicles to obtain the target collection and transportation vehicles corresponding to the real-time collection and transportation vehicles. Obtain the collection standards for the target collection vehicle; Adjust the real-time operating routes of collection vehicles based on the collection standards of the target collection vehicles.

9. The IoT-based carbon emission optimization management system for garbage collection vehicles according to claim 7, characterized in that, The process involves collecting real-time information from real-time collection vehicles, inputting this information into a trained optimization model, and then using this model to optimize the carbon emissions of the real-time collection vehicles. This also includes: Collect real-time information of the collection and transportation vehicles; the real-time information includes real-time collection and transportation vehicle information or real-time operation information. Real-time operational information is input into the trained optimization model, and the trained optimization model is used to perform cluster analysis on the real-time collection and transportation vehicles to obtain the target collection and transportation vehicles corresponding to the real-time collection and transportation vehicles. Obtain the collection standards for the target collection vehicle; Select appropriate real-time collection vehicles based on the collection standards of the target collection vehicles.

10. The IoT-based carbon emission optimization management system for garbage collection vehicles according to claim 8, characterized in that, Adjusting the real-time operating routes of collection vehicles based on the collection standards of the target collection vehicles, including: Calculate the real-time waste collection and transportation cost of real-time collection vehicles based on real-time collection vehicle information; Obtain the amount of waste per unit route from the collection standards of the target collection vehicles; The target route is obtained based on the amount of waste per unit route, and this target route is the operating route of the real-time collection vehicle.

Images