Intelligent management method and system for green waste

Abstract

The application discloses a kind of intelligent management method and system for green garbage, it is related to green garbage processing technical field, for solving the problems of high degree of blindness of garbage classification, opaque garbage resource processing process and low resource utilization in prior art, it is by setting several garbage receiving points for deploying green garbage operating equipment to handle green garbage, to obtain different categories of green garbage material to separate vehicle packing, plan the transportation route of each vehicle for transporting green garbage material to corresponding resource utilization point, construct the resource process simulation model of each resource utilization point to simulate the utilization process of green garbage material, based on the simulation results of resource process simulation model, the utilization process of green garbage material at corresponding resource utilization point is optimized, the material resources obtained by each resource utilization point are resource bidding, accurate classification of green garbage and transparent garbage resource utilization process are realized, and resource utilization is improved.

Description

Technical Field

[0001] This invention relates to the field of green waste treatment technology, specifically to a smart management method and system for green waste. Background Technology

[0002] With the increase in urban green coverage, the amount of green waste generated during landscaping, such as tree branches, fallen leaves, and grass clippings, is increasing. Currently, the methods for handling green waste are still relatively crude, and the following significant problems exist: First, the degree of blindness in garbage sorting is high, mainly relying on manual sorting or simple mechanical screening, which makes it impossible to accurately identify and classify the complex green waste. This leads to uneven raw material properties in the subsequent resource recovery process, making it difficult to achieve efficient conversion and utilization. Secondly, the waste resource treatment process is opaque. Throughout the entire waste treatment chain, each treatment step lacks effective digital monitoring and simulation optimization, resulting in a "black box" in the treatment process and making it difficult to accurately control the process. Finally, the resource utilization rate is low. Due to inaccurate front-end classification and non-optimized processing, the quality of the output materials is unstable and the value is not fully explored. At the same time, the lack of a matching mechanism between resources and users restricts the improvement of resource conversion efficiency. Therefore, existing technologies urgently need a smart management solution that can achieve precise classification and transparent treatment of green waste and improve resource utilization. Summary of the Invention

[0003] The purpose of this invention is to provide a smart management method and system for green waste, so as to solve the problems in the background technology.

[0004] To achieve the above objectives, the present invention provides the following technical solution: a smart management method for green waste, comprising the following steps: Step S1: Set up several waste receiving points, deploy green waste processing equipment at each waste receiving point, process green waste through the green waste processing equipment, and obtain different types of green waste materials; Step S2: Pack different types of green waste materials into separate vehicles and plan the corresponding transportation routes for each vehicle to transport the green waste materials to the corresponding resource utilization points. Construct a resource process simulation model for each resource utilization point and simulate the utilization process of green waste materials through the resource process simulation model. Step S3: Based on the simulation results of the resource process simulation model at each resource utilization point, optimize the utilization process of green waste materials at the corresponding resource utilization point, and conduct resource bidding for the material resources obtained at each resource utilization point.

[0005] In a preferred embodiment, several waste receiving points are set up, and green waste processing equipment is deployed at each waste receiving point. The process of processing green waste through green waste processing equipment to obtain different types of green waste materials includes: Several waste receiving points are set up and labeled. Green waste handling equipment is deployed at each waste receiving point. Based on the green waste handling equipment, the green waste received at the corresponding waste receiving point is sequentially subjected to multimodal sensing, initial screening, tag binding and adaptive sorting. The green waste corresponding to each waste receiving point is processed into several categories of green waste materials, including grass and leaf scraps, fine wood chips, wood chips and wood blocks.

[0006] In a preferred embodiment, the green waste handling equipment includes: The green waste handling equipment consists of an image processing unit, a spectral analysis unit, a tagging unit, an automatic crushing unit, and a sorting unit. Multimodal perception includes visual perception and composition perception. The image processing unit obtains several image blocks representing different properties of green waste. The spectral analysis unit performs composition perception on the waste target object corresponding to each frame image block to determine its respective composition attribute parameters. The tag unit binds a digital material tag to each waste target object based on its own composition attribute parameters, and integrates waste target objects with the same digital material tag into a raw material cluster, thereby completing the initial screening of the feed. The automatic crushing unit uses the digital material tag of each raw material cluster to call the crushing parameters that match the corresponding raw material cluster in the preset crushing strategy library. Based on the crushing parameters, the crushing equipment is activated to crush the raw material cluster to obtain materials of different sizes to be sorted. The sorting unit adaptively sorts the materials to be sorted. The sorting unit is equipped with an air separator, a conveying device, and discharge ports of different specifications. The air separator is set with different airflow rates and blows the materials to be sorted into different specifications of green waste materials based on quality. The green waste materials of different specifications are conveyed on the conveying device and discharged to different discharge ports according to specifications to complete the sorting.

[0007] In a preferred embodiment, the visual perception and component perception include: The system acquires a video clip of green waste received in one go, segments the video clip into several frames of video images, creates a stacked layer for each video clip, the stacked layer consists of several planar layers, each stacked layer is used to store one frame of video image, and sets the minimum processing unit of the layer to divide the video images in the planar layer into several image blocks. Image feature analysis is performed on each image block to obtain the visual modal features of the corresponding green waste in each image block. Several image blocks in each planar layer under the same stacked layer are connected between layers based on the same position coordinates on different planar layers to construct the interlayer channels of image blocks with the same position coordinates in different planar layers. On different planar layers of the interlayer channel, a data display node is set according to the time sequence to display the visual modal features of the image block in the corresponding time sequence. The visual modal features of all data display nodes in the interlayer channel are integrated to obtain the overall visual modal features of the corresponding image block in the entire time sequence range. The spectral analysis unit includes a near-infrared spectroscopy and a hyperspectral imager. The spectral analysis unit performs component sensing on green waste, including organic component analysis and impurity detection, to determine the component attribute parameters of the green waste.

[0008] In a preferred embodiment, the process of separating and packaging different types of green waste materials into different vehicles, and planning corresponding transportation routes for each vehicle to transport the green waste materials to the appropriate resource utilization points includes: The total volume of each type of green waste material during the set material transfer period is counted. The number of garbage trucks corresponding to the total volume of each type of green waste material is scheduled to be transferred. Different types of resource utilization points are selected, and the number of resource utilization points corresponds to the type of green waste material. Each resource utilization point is used to process the resource utilization of one type of green waste material. Construct a material scheduling master map, mark each waste receiving point and resource utilization point on the material scheduling master map, take the maximum common number of waste transfer vehicles required to be scheduled for different types of green waste materials as the initial scheduling number, set the number of waste receiving points corresponding to the initial scheduling number as the path starting point on the material scheduling master map, and schedule several waste transfer vehicles covering all types of green waste materials at each path starting point for transporting green waste materials. Other waste receiving points near the starting point of the route are used as route connection points to connect the starting point of the route and the route connection points. Green waste materials are received at each route connection point until the green waste materials are fully loaded and then transported to the nearest resource utilization point at the current location. The starting point of the route, the resource utilization point, and several resource utilization points between the starting point of the route and the resource utilization point are connected on the material scheduling master map to construct the current transportation route of the waste transfer vehicle. The transportation routes of several vehicles under different categories are obtained and displayed on the material scheduling master map. All garbage receiving points not covered by the transportation routes on the material scheduling master map are designated as secondary scheduling points. All remaining unused garbage transfer vehicles are dispatched to each secondary scheduling point in sequence. The garbage transfer vehicles receive one type of green waste material at the secondary scheduling point until all green waste material at all secondary scheduling points has been transferred to the corresponding resource utilization point.

[0009] In a preferred embodiment, a resource process simulation model is constructed for each resource utilization point. The utilization process of green waste materials is simulated using the resource process simulation model. Based on the simulation results of the resource process simulation model at each resource utilization point, the process optimization of the utilization process of green waste materials at the corresponding resource utilization point includes: Physical entity modeling is performed on the resource processing equipment at each resource utilization point, creating their own simulated physical entities, defining the entity attributes of the simulated physical entities, monitoring the entire process of resource utilization of green waste materials at each resource utilization point, decomposing the entire process into several execution procedures, constructing a time-series coordinate axis, and arranging the several execution procedures to the corresponding positions on the time-series coordinate axis based on their respective procedure timestamps; A simulated scene space is created at each arrangement position. All simulated physical entities are assigned to the corresponding simulated scene space based on their respective execution processes. Constraint rules are set for each execution process as simulation reference data for simulating the utilization of green waste materials. Based on the simulation reference data, a simulation is performed in the corresponding simulation scenario space to obtain the performance simulation index of the corresponding process. The performance simulation index is correlated with the performance index range set for the corresponding process under ideal working conditions to construct a comparison dataset to record the simulation results of the corresponding process. The comparison dataset is analyzed to determine whether there is an optimization requirement for the corresponding process. If yes, then the corresponding simulation training optimization parameters for the relevant process are reset in the simulation scene space, and the simulation of the current process is executed again until the simulation result meets expectations, and then the simulation of the next process continues; if no, then the simulation of the next process is performed directly.

[0010] In a preferred embodiment, the process of bidding for material resources obtained at each resource utilization point includes: A resource package is constructed at each resource utilization point, and all resource packages from each resource utilization point are published to a bidding pool. Several bidders participate in the bidding based on the bidding pool. The bidding is evaluated based on the bidding information of each bidder, and several bidders matching several resource packages are selected. Contracts for the resource packages are signed and delivery procedures are executed. After delivery, the bidders settle funds and provide data feedback based on the resource utilization details of the resource packages. A bidding optimization model is constructed based on the data feedback results, and the resource bidding is optimized and managed through the bidding optimization model.

[0011] This invention also provides a smart management system for green waste, the system comprising: The intelligent equipment processing module is used to set up several waste receiving points, deploy green waste handling equipment at each waste receiving point, process green waste through green waste handling equipment, and thus obtain different types of green waste materials; The route planning and simulation module is used to sort and package different types of green waste materials, plan the transportation routes for each vehicle to transport the green waste materials to the corresponding resource utilization points, construct a resource process simulation model for each resource utilization point, and simulate the utilization process of green waste materials through the resource process simulation model. The process optimization and resource adaptation module optimizes the utilization process of green waste materials at each resource utilization point based on the simulation results of the resource process simulation model at each resource utilization point, and conducts resource bidding for the material resources obtained at each resource utilization point.

[0012] The technical effects and advantages provided by the present invention in the above technical solution are as follows: 1. This invention deploys green waste processing equipment at various waste receiving points to accurately process green waste into different categories of green waste materials, ensuring the uniformity and accuracy of material classification from the source, laying a solid foundation for subsequent efficient resource utilization, and to a certain extent avoiding the adverse effects caused by the high degree of blindness in traditional manual sorting. 2. This invention digitizes, visualizes, and predicts the entire process of green waste material from transportation to resource utilization by planning transportation routes, constructing resource process simulation models, and simulating and optimizing the utilization process. This makes the entire processing process free from a black box state, enabling precise optimization of the process based on simulation results, thereby improving the efficiency and controllability of the processing flow. 3. This invention optimizes the process at resource utilization points, ensuring that green waste materials can be efficiently transformed into the required material resources. By using a resource bidding process, the material resources are matched with the most suitable demanders, thereby improving the overall resource utilization rate of green waste. Attached Figure Description

[0013] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0014] Figure 1 This is a flowchart of the method of the present invention.

[0015] Figure 2 This is a schematic diagram of the bidding process for resource bidding in this invention.

[0016] Figure 3 This is a system block diagram of the present invention. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, 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, 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.

[0018] Example 1, please refer to Figure 1 As shown in this embodiment, a smart management method for green waste includes the following steps: Step S1: Set up several waste receiving points, deploy green waste processing equipment at each waste receiving point, process green waste through the green waste processing equipment, and obtain different types of green waste materials; Step S2: Pack different types of green waste materials into separate vehicles and plan the corresponding transportation routes for each vehicle to transport the green waste materials to the corresponding resource utilization points. Construct a resource process simulation model for each resource utilization point and simulate the utilization process of green waste materials through the resource process simulation model. Step S3: Based on the simulation results of the resource process simulation model at each resource utilization point, optimize the utilization process of green waste materials at the corresponding resource utilization point, and conduct resource bidding for the material resources obtained at each resource utilization point.

[0019] It should be further explained that, in the specific implementation process, several waste receiving points are set up, and green waste processing equipment is deployed at each waste receiving point. The process of processing green waste through green waste processing equipment to obtain different types of green waste materials includes: Set up several garbage collection points, label them, and record the labels as follows: Then there is = 1, 2, 3, ..., n, where n is a natural number greater than 0. Obtain the location coordinates corresponding to each garbage receiving point, and label them as follows: The coordinates of the corresponding garbage receiving points are marked. ; Green waste processing equipment is deployed at each waste receiving point. Based on the green waste processing equipment, the green waste received at the corresponding waste receiving point is sequentially subjected to multimodal sensing, initial screening, tag binding, and adaptive sorting, so that the green waste at each waste receiving point is processed into several categories of green waste materials.

[0020] The green waste handling equipment consists of an image processing unit, a spectral analysis unit, a tagging unit, an automatic crushing unit, and a sorting unit. Each component of the green waste handling equipment performs the following functions in sequence: The multimodal perception includes visual perception and composition perception. The image processing unit processes the green waste to obtain several image blocks representing different properties. The composition of the waste target object corresponding to each frame image block is perceived by the spectral analysis unit to determine the composition attribute parameters of each waste target object.

[0021] The visual perception and component perception include: taking several images of the green waste at each waste receiving point, with each image taking being used to obtain an image segment corresponding to the green waste received once, and then dividing the image segment into several frames of image images. For each garbage receiving point, a stacked layer is created for the image fragments of green waste received. The stacked layer consists of several planar layers. Each stacked layer is used to store one frame of image image corresponding to the image fragment. The minimum processing unit of the layer is set, and the image images stored in the planar layer are divided into several image blocks based on the minimum processing unit of the layer. Image feature analysis is performed on each image block to obtain the visual modal features of the green waste recorded in each image block. The visual modal features include shape and outline, such as the overall shape of the green waste in the image block, such as branch-like, leaf-like, sheet-like and block-like, and the size of the green waste, such as length, area and volume. Visual modal characteristics also include the roughness, texture, and wrinkles of the surface of the green waste, the basic color and color difference distribution of the green waste, and the physical state of the green waste, such as whether it has surface reflection due to entanglement, clumping, or water content, or whether it contains foreign objects, including but not limited to non-green waste components such as plastics and stones.

[0022] Each planar layer in the same stacked layer is connected to several image blocks based on the same position coordinates on different planar layers, thus constructing an inter-layer channel for each image block with the same position coordinates on different planar layers. On different planar layers of the interlayer channel, a data display node is set according to the time sequence. The data display node is used to display the visual modal features of the image block in the corresponding time sequence. By integrating the visual modal features of all data display nodes under an interlayer channel, the overall visual modal features of the corresponding image block in the entire time sequence range can be obtained. The visual modal features of an image patch at a certain time sequence are used to characterize the appearance and visual properties of the green waste represented by the image patch at a certain point in time. By integrating the visual modal features of the same image patch at different time sequences, the overall visual modal features of the image patch are obtained, which reflect the appearance and visual properties over the entire time range. The visual modal features at a certain time sequence may have omissions in the representation of appearance features, while the visual modal features over the entire time range can avoid this phenomenon as much as possible. Through mutual corroboration between the visual modal features at different time sequences, the accuracy of visual perception is improved.

[0023] The spectral analysis unit includes near-infrared spectroscopy and hyperspectral imaging. The spectral analysis unit performs component sensing on green waste, including organic component analysis and impurity detection. The organic component analysis obtains lignin content, cellulose / hemicellulose content, total sugar and starch content, carbon-nitrogen ratio, moisture content, and ash content. The impurity detection detects the presence of heavy metal elements, such as lead and cadmium, and identifies the presence of trace amounts of non-target components such as plastics or chemical dyes, thereby determining the component attribute parameters of the green waste.

[0024] The tag unit is used to bind a corresponding digital material tag to each waste target object based on its own composition attribute parameters, and to integrate waste target objects with the same digital material tag into a raw material cluster, thereby completing the initial screening of the feed. The initial screening of the feed is used to remove stones, plastic film and other waste materials that are not related to greening components from the green waste. The composition attribute parameters include physical attributes and chemical attributes. Physical attributes include the category, estimated volume, and outline shape of the waste target object, while chemical attributes include the lignin content range, cellulose / hemicellulose content, moisture content, ash content, and carbon-nitrogen ratio of the waste target object. The number of the waste receiving point and the receiving timestamp corresponding to each waste target object are obtained and used as the corresponding traceability information. The composition attribute parameters and traceability information are integrated as the digital material tags that need to be bound to each.

[0025] The automatic crushing unit, based on the digital material tag of each raw material cluster, calls the crushing parameters that match the corresponding raw material cluster in the preset crushing strategy library, and activates the crushing equipment to crush the raw material cluster based on the crushing parameters to obtain several materials of different sizes to be sorted. The sorting unit is used to adaptively sort the materials to be sorted. The sorting unit is equipped with an air separator, a conveying device and discharge ports of different specifications. The air separator is set with different airflow rates. Based on the different airflow rates, the heavy materials and light materials in the materials to be sorted are separated, and the heavy materials and light materials are further sorted into green waste materials of different specifications.

[0026] All green waste materials are transported on the conveyor device. Different sizes of discharge ports are arranged on the conveyor device in order of distance from the starting point of the conveyor. The smaller the size of the discharge port, the closer it is to the starting point of the conveyor. This is used to screen the smaller size of the green waste materials. The larger size of the green waste materials continue to be transported to the next discharge port through the conveyor device. When the size meets the requirements, the green waste materials are screened to the corresponding discharge port. The lightweight materials include grass scraps and fine wood chips, while the heavyweight materials include wood chips and wood blocks. The discharge ports include discharge port A, discharge port B, and discharge port C. Discharge ports A, B, and C are arranged from near to far at the starting point of the conveyor, and the specifications of discharge ports A, B, and C increase sequentially. Discharge port A is used to screen grass scraps, discharge port B is used to screen fine wood chips, and discharge port C is used to screen wood chips and wood blocks. The grass scraps, wood chips, wood chips, and wood blocks are green waste materials of different specifications.

[0027] It should be further explained that, in the specific implementation process, the process of separating and packaging different types of green waste materials into different vehicles, and planning corresponding transportation routes for each vehicle to transport the green waste materials to the appropriate resource utilization points includes: Set material transfer time periods, calculate the total volume of each type of green waste material during the material transfer time period, and schedule the number of garbage trucks corresponding to the total volume of each type of green waste material to be transferred. Different types of green waste materials are selected for their corresponding resource utilization points. The number of resource utilization points corresponds to the type of green waste material. Each resource utilization point is used to process the resource utilization of one type of green waste material.

[0028] Construct a material scheduling master map covering all waste receiving points and resource utilization points. Mark each waste receiving point and resource utilization point on the material scheduling master map. Use the maximum common number of waste transfer vehicles required to be scheduled for different types of green waste materials as the initial scheduling number. On the material scheduling master plan, the number of waste receiving points corresponding to the initial scheduling number are set as the starting point of the path. At each starting point of the path, several waste transfer vehicles covering all categories of green waste materials are scheduled, and the waste transfer vehicles receive one type of green waste material for transfer.

[0029] Other waste receiving points near the starting point of the route are used as route connection points. The starting point of the route is connected to the route connection points. Green waste materials are received at each route connection point until the waste transfer truck is fully loaded with green waste materials and then transported to the nearest resource utilization point at the current location. The starting point of the route, the resource utilization point, and several resource utilization points between the starting point of the route and the resource utilization point are connected on the material scheduling master map, thereby constructing the transportation route corresponding to the current waste transfer truck. Repeat the above operation of the garbage truck to transfer green waste materials to obtain the transportation routes corresponding to several vehicles under different categories and display them on the material scheduling master map. All garbage receiving points not covered by the transportation routes on the material scheduling master map are used as secondary scheduling points. All remaining unused garbage trucks are dispatched sequentially to each secondary dispatch point. Each garbage truck receives one type of green waste material at the secondary dispatch point until all green waste materials corresponding to all secondary dispatch points have been transferred to the corresponding resource utilization points.

[0030] It should be further explained that, in the specific implementation process, a resource process simulation model is constructed for each resource utilization point. This model is used to simulate the utilization process of green waste materials. Based on the simulation results of the resource process simulation model at each resource utilization point, the process optimization of the utilization of green waste materials at that corresponding resource utilization point includes: Each resource utilization point implements resource utilization for a specific type of green waste material; The resource process simulation model is constructed using a digital twin technology framework, which consists of three layers: a physical layer, a data layer, and a model layer. The physical layer represents the resource processing equipment system at the actual resource utilization point; the data layer is used to collect and store the operating data and historical data of the resource processing equipment in real time; and the model layer contains the state equations and output equations of the resource process simulation model. Specifically, let the state variable be x(t), the control input be u(t), the output be y(t), and the disturbance be w(t), then the state equation of the resource process simulation model is: x(t+1) = A·x(t) + B·u(t) + w(t); Where x(t) represents the state vector of the resource process simulation model at time t, which includes the operating state parameters of each resource processing device; u(t) represents the control input vector of the resource process simulation model, which includes the operating parameters of each process; w(t) represents the environmental disturbance vector, which includes random events such as equipment failure and material supply fluctuations; and A and B are model matrices, which represent the mapping relationship between state variables and control inputs. The output equation of the resource process simulation model is: y(t) = C·x(t); Where y(t) is the output vector of the resource process simulation model at time t, which includes output indicators such as the real-time processing efficiency, equipment load rate and resource utilization rate of each process, and C is the observation matrix, which is used to map the state variables to the output indicators.

[0031] The resource process simulation model is interconnected with the actual resource processing equipment system. Equipment failures, processing anomalies, or material supply fluctuations in the actual resource processing equipment system can all be realistically reflected in the resource process simulation model. The resource process simulation model is constructed using process simulation software, including but not limited to Aspen Plus, MATLAB / Simulink, or Plant Simulation. Specifically, Aspen Plus software is used to perform steady-state modeling and simulation of the processing flow at resource utilization points, or MATLAB / Simulink software is used to build a dynamic simulation model of the resource processing system, or Plant Simulation software is used to establish a discrete event simulation model of the resource processing process.

[0032] Physical entity modeling is performed on the resource processing equipment at each resource utilization point, creating a simulated physical entity corresponding to each resource processing equipment, and defining the entity attributes corresponding to each simulated physical entity, including geometric attributes, material attributes, and dynamic performance attributes. Monitor the entire process of resource utilization of green waste materials at each resource utilization point, decompose the entire resource utilization process into several execution procedures, construct a time-series coordinate axis, and arrange the several execution procedures in sequence to the corresponding positions on the time-series coordinate axis based on their respective procedure timestamps, and create a simulated scene space at each arrangement position; All simulated physical entities corresponding to the resource processing equipment are assigned to the corresponding simulated scene space based on their respective execution processes. Constraint rules are set for each execution process, which serve as simulation reference data for simulating the corresponding processes of green waste materials during utilization in the simulated scene space.

[0033] Based on the simulation reference data, a simulation is performed in the corresponding simulation scenario space to obtain the performance simulation index of the corresponding process. The performance simulation index is correlated with the performance index range set for the corresponding process under ideal working conditions to construct a comparison dataset for the corresponding process. The comparison dataset is used to record the simulation results of the corresponding process. By analyzing the comparison dataset of each process, it is determined whether there is an optimization requirement for the corresponding process. The performance simulation metrics include, but are not limited to, the following metrics: Processing efficiency indicators include the processing capacity per unit time (tons / hour), process cycle time (minutes / batch), equipment utilization rate (%), and material waiting time between processes (minutes). Energy consumption indicators include the unit material handling energy consumption (kWh / ton) and thermal efficiency (%) of each process, as well as the overall energy consumption of the entire process (kWh / ton). Quality indicators include the content of target components in the output material (such as lignin content, moisture content, etc.), the pass rate of particle size distribution of the output material (%), and the removal rate of impurities (%). Stability indicators include the volatility (%) of operating parameters for each process, the frequency of equipment failures (times / hundred hours), and the robustness score of the system to fluctuations in material properties.

[0034] The performance index range set under ideal operating conditions is based on the design parameters of the resource utilization point and industry standards. For example, for the composting process, the processing efficiency index range under ideal operating conditions is set as follows: processing capacity per unit time ≥ 2 tons / hour, composting cycle ≤ 21 days, and organic matter content of the finished product ≥ 45%; for the pyrolysis process, the energy consumption index range under ideal operating conditions is set as follows: energy consumption per unit material processing ≤ 200 kWh / ton, and thermal efficiency ≥ 75%.

[0035] If yes, then the corresponding process will have its simulation training optimization parameters reset in the simulation scene space. Based on the simulation training optimization parameters, the simulation of the current process will be performed again until the simulation result meets expectations. Then, the simulation of the current process will be stopped, and the simulation of the next process will continue. If no, the simulation of the next process will continue directly. The simulation training optimization parameters include the following categories: Equipment operating parameters: including the rotational speed of the crushing equipment (rpm), the airflow rate of the air classifier (m / s), the operating speed of the conveying equipment (m / min), the temperature setpoint of the heating equipment (°C), and the holding time (min); process connection parameters: including the buffer capacity (tons) between each process, the material transfer interval (min), and the process start threshold; material proportioning parameters: including the mixing ratio of different types of green waste materials and the amount of additives added (kg / ton); environmental control parameters: including the pH value, moisture content (%), and oxygen content (%) of the reaction environment; simulation training optimization parameters are optimized and adjusted using intelligent optimization algorithms, including but not limited to genetic algorithms, particle swarm optimization algorithms, and model predictive control algorithms; Specifically: When using a genetic algorithm for global optimization of process parameters, the fitness function is to minimize the deviation between the performance simulation index and the ideal performance index range. The parameter population is iteratively evolved through selection, crossover, and mutation operations until the fitness function converges or the preset maximum number of iterations is reached. When using a particle swarm optimization algorithm, the parameters to be optimized in each process are encoded as particle position vectors. Through the collaborative search of the particle swarm in the parameter space, the particle velocity and position are iteratively updated to finally obtain the parameter combination that optimizes the performance simulation index. When using a model predictive control algorithm, based on the state equation of the resource process simulation model, the optimization of the performance index within a few future time steps is the objective. The optimal control sequence is calculated in each step, and the first control variable is applied to the current process.

[0036] When each resource utilization point corresponds to each process that needs to be optimized under the resource process simulation model, and each process optimization is completed, the entire utilization process of the green waste material at the corresponding resource utilization point achieves the simulation under the expected condition. Based on the simulation results under the expected condition, the resource utilization processing of the green waste material at the resource utilization point is actually performed according to each process of the resource process simulation model, thereby converting the green waste material into material resources.

[0037] In a specific application example, a resource utilization site used a resource process simulation model to optimize the pyrolysis process of green waste. Before optimization, the energy consumption per unit material processed in the pyrolysis process at this resource utilization site was 245 kWh / ton, the thermal efficiency was 68%, and the fixed carbon content of the produced biochar was 62%. The pyrolysis process was simulated using the resource process simulation model, with the optimization objectives of minimizing energy consumption per unit material processed and maximizing thermal efficiency. A genetic algorithm was used to optimize the pyrolysis temperature (500℃~800℃) and heating rate (5℃ / min~20℃ / min). The optimal parameter combination was obtained after 50 iterations and optimizations of three key parameters: pyrolysis temperature 650℃, heating rate 12℃ / min, and holding time 75 minutes. After applying this optimal parameter combination to the actual pyrolysis process, the energy consumption per unit material was reduced to 198 kWh / ton (a decrease of 19.2%), the thermal efficiency was increased to 79% (an increase of 16.2%), and the fixed carbon content of the produced biochar was increased to 71% (an increase of 14.5%), verifying the effectiveness of the resource process simulation model for process optimization.

[0038] In another application example, a resource utilization site used a resource process simulation model to optimize the composting process of green waste materials. By combining simulation with particle swarm optimization algorithm, the three parameters of ventilation rate (0.1~0.5 cubic meters / minute·ton), turning frequency (1~5 times / day) and initial moisture content (45%~65%) were optimized, shortening the composting cycle from 28 days to 21 days (a reduction of 25%), and increasing the organic matter content of the finished product from 42% to 48% (an increase of 14.3%).

[0039] It should be further explained that, in the specific implementation process, the process of bidding for material resources obtained at each resource utilization point includes: Please refer to the schematic diagram of the bidding process for the resource bidding. Figure 2 As shown; At each resource utilization point, based on the material resources produced after optimization and processing according to the simulation model of their respective resource processes, a corresponding resource package is constructed. Each package contains a digital material file corresponding to the material resources. Each resource utilization point is equipped with an IoT sensing layer, including weighing sensors, online near-infrared analyzers, and particle size monitors. The material quality, composition parameters (organic matter content, moisture content, etc.) and particle size distribution collected in real time are uploaded to the edge gateway via industrial Ethernet. After preprocessing, the data is transmitted to the cloud digital twin platform via the MQTT protocol, automatically generating a digital material file containing real production data to ensure that the resource package data is traceable and tamper-proof. The digital material archive is constructed based on the data obtained from all the operations performed on green waste in the above steps. It serves as the identity details of each material resource. The digital material archive specifically records the category, total mass, key component parameters, physical specifications, traceability information, and suggested uses of the material resource. All resource packages from all resource utilization points are published in a digitally constructed bidding pool. The bidding pool is connected to the Internet and serves as an online platform that can be accessed and operated. The bidding pool is used to publicize the digital material files of all resource packages and sets up data interfaces for data connection between several bidders and the bidding pool. Each bidder accesses the digital material files in the bidding pool through its own data interface. The bidding pool adopts a microservice architecture B / S online platform with a RESTful API interface. After OAuth 2.0 authentication, bidders can call the interface to obtain structured data of resource packages or submit bidding information. During the bidding evaluation, the system calls the bag-of-words model to segment and remove stop words from the bidding information and material files, uses the TF-IDF algorithm to calculate word weights, and maps the text into low-dimensional dense vectors through Word2Vec. Then, it calculates the cosine similarity between the bidding profile and the material resource profile. The similarity calculation formula is sim(A,B)=(A·B) / (||A||×||B||). A threshold of 0.75 is set to filter matching pairs to achieve automated and accurate matching. After matching is completed, the platform's electronic contract engine automatically generates a draft contract. The bidding party and the tendering party use digital certificates based on the national cryptographic SM2 algorithm to electronically sign the contract. The contract hash value is uploaded to the blockchain storage platform to ensure that the contract is tamper-proof. During the delivery stage, the transport vehicle is equipped with a GPS positioning terminal and a weight sensor to upload the location and load data to the logistics monitoring subsystem in real time. The data is automatically compared with the delivery time window and quantity agreed in the contract. If the tolerance is exceeded, an alarm is triggered. When the delivery is completed, the tendering party confirms receipt by scanning the RFID tag with a mobile terminal, forming a closed loop of delivery. Several bidders participate in the bidding based on the digital material files of the resource packages in the bidding pool. The types of bidders include, but are not limited to, organic fertilizer producers, biomass power plants and board manufacturers. Bidders submit their respective bidding information to the bidding pool, which includes the unit price, the total quantity to be purchased, the planned use and the logistics plan. The bidding evaluation process is as follows: based on the bidding information of each bidder, the bidding information is processed by calling the bag-of-words model to obtain the first text feature corresponding to the bidding information. Based on the first text feature, a bidding profile corresponding to the bidder is constructed. Several digital material files in the bidding pool are processed by the bag-of-words model to obtain the second text feature corresponding to each digital material file. Based on the second text feature, a material resource profile is constructed. Each bidding profile is taken as the bidding subject, and several material resource profiles are taken as the bidding target elements in turn. The similarity between each bidding subject and several bidding target elements is measured, and the bidding target element with the highest similarity is associated with each bidding subject. Then, the association between several resource packages and several bidders is screened out. In this process, a vector set is set for the bidding profile corresponding to the bidding entity, and a vector set is set for the material resource profile corresponding to the bidding target element. Each vector set consists of several vectors. The cosine similarity between the vector sets of the bidding entity and the vector set of the bidding target element is calculated. The average of several cosine similarities is taken as the set similarity between the bidding entity and the bidding target element. The bidding entity with the highest set similarity is finally matched with the bidding target element.

[0040] For each resource package that establishes a connection, a transaction contract is signed between the tendering party and the bidding party, and the corresponding delivery procedures are executed. The transaction contract is used to define the scope of rights and responsibilities, delivery time, delivery indicators and settlement methods between the tendering party and the bidding party. The entire delivery process is monitored through the Internet of Things to ensure transparent traceability management of material resources from the resource utilization point to the bidding party. After delivery, the bidder settles the funds and puts the acquired material resources into its actual production and use. It obtains the resource utilization details of the resource package during the actual production and use process, conducts data feedback based on the resource utilization details, and builds a bidding optimization model based on the data feedback results. The bidding optimization model then intervenes in the preparation and release of the resource package, thereby completing the optimized management of resource bidding.

[0041] The bidding optimization model is a data-driven model based on machine learning. It collects historical bidding data and corresponding data feedback, namely resource utilization details, to construct a training dataset. This training dataset takes the characteristics of bidder profiles and material resource profiles in the historical bidding data as input, and uses feedback indicators such as actual resource utilization efficiency, timely fund settlement rate, and customer satisfaction as optimization objectives to iteratively train the bidding optimization model. This allows the bidding optimization model to learn the historical bidding performance of different material resource profiles and their respective impact on the resource utilization of the corresponding bidders in the actual production and use process, so as to ultimately achieve the optimal matching between bidders and resource packages in the new round of resource bidding.

[0042] Example 2, please refer to Figure 3 As shown in this embodiment, a smart management system for green waste includes: The intelligent equipment processing module is used to set up several waste receiving points, deploy green waste handling equipment at each waste receiving point, process green waste through green waste handling equipment, and thus obtain different types of green waste materials; The route planning and simulation module is used to sort and package different types of green waste materials, plan the transportation routes for each vehicle to transport the green waste materials to the corresponding resource utilization points, construct a resource process simulation model for each resource utilization point, and simulate the utilization process of green waste materials through the resource process simulation model. The process optimization and resource adaptation module optimizes the utilization process of green waste materials at each resource utilization point based on the simulation results of the resource process simulation model at each resource utilization point, and conducts resource bidding for the material resources obtained at each resource utilization point.

[0043] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A smart management method for green waste, characterized in that, Includes the following steps: Step S1: Set up several waste receiving points, deploy green waste processing equipment at each waste receiving point, process green waste through the green waste processing equipment, and obtain different types of green waste materials; Step S2: Pack different types of green waste materials into separate vehicles and plan the corresponding transportation routes for each vehicle to transport the green waste materials to the corresponding resource utilization points. Construct a resource process simulation model for each resource utilization point and simulate the utilization process of green waste materials through the resource process simulation model. Step S3: Based on the simulation results of the resource process simulation model at each resource utilization point, optimize the utilization process of green waste materials at the corresponding resource utilization point, and conduct resource bidding for the material resources obtained at each resource utilization point.

2. The intelligent management method for green waste according to claim 1, characterized in that, The process of setting up several waste receiving points, deploying green waste processing equipment at each point, and processing green waste through this equipment to obtain different types of green waste materials includes: Several waste receiving points are set up and labeled. Green waste handling equipment is deployed at each waste receiving point. Based on the green waste handling equipment, the green waste received at the corresponding waste receiving point is sequentially subjected to multimodal sensing, initial screening, tag binding and adaptive sorting. The green waste corresponding to each waste receiving point is processed into several categories of green waste materials, including grass and leaf scraps, fine wood chips, wood chips and wood blocks.

3. The intelligent management method for green waste according to claim 2, characterized in that, The green waste handling equipment includes: The green waste handling equipment consists of an image processing unit, a spectral analysis unit, a tagging unit, an automatic crushing unit, and a sorting unit. Multimodal perception includes visual perception and composition perception. The image processing unit obtains several image blocks representing different properties of green waste. The spectral analysis unit performs composition perception on the waste target object corresponding to each frame image block to determine its respective composition attribute parameters. The tag unit binds a digital material tag to each waste target object based on its own composition attribute parameters, and integrates waste target objects with the same digital material tag into a raw material cluster, thereby completing the initial screening of the feed. The automatic crushing unit uses the digital material tag of each raw material cluster to call the crushing parameters that match the corresponding raw material cluster in the preset crushing strategy library. Based on the crushing parameters, the crushing equipment is activated to crush the raw material cluster to obtain materials of different sizes to be sorted. The sorting unit adaptively sorts the materials to be sorted. The sorting unit is equipped with an air separator, a conveying device, and discharge ports of different specifications. The air separator is set with different airflow rates and blows the materials to be sorted into different specifications of green waste materials based on quality. The green waste materials of different specifications are conveyed on the conveying device and discharged to different discharge ports according to specifications to complete the sorting.

4. The intelligent management method for green waste according to claim 3, characterized in that, The content of the visual perception and component perception includes: The system acquires a video clip of green waste received in one go, segments the video clip into several frames of video images, creates a stacked layer for each video clip, the stacked layer consists of several planar layers, each stacked layer is used to store one frame of video image, and sets the minimum processing unit of the layer to divide the video images in the planar layer into several image blocks. Image feature analysis is performed on each image block to obtain the visual modal features of the corresponding green waste in each image block. Several image blocks in each planar layer under the same stacked layer are connected between layers based on the same position coordinates on different planar layers to construct the interlayer channels of image blocks with the same position coordinates in different planar layers. On different planar layers of the interlayer channel, a data display node is set according to the time sequence to display the visual modal features of the image block in the corresponding time sequence. The visual modal features of all data display nodes in the interlayer channel are integrated to obtain the overall visual modal features of the corresponding image block in the entire time sequence range. The spectral analysis unit includes a near-infrared spectroscopy and a hyperspectral imager. The spectral analysis unit performs component sensing on green waste, including organic component analysis and impurity detection, to determine the component attribute parameters of the green waste.

5. The intelligent management method for green waste according to claim 4, characterized in that, The process of separating and packaging different types of green waste materials into different vehicles and planning corresponding transportation routes for each vehicle to transport the green waste materials to the appropriate resource utilization points includes: The total volume of each type of green waste material during the set material transfer period is counted. The number of garbage trucks corresponding to the total volume of each type of green waste material is scheduled to be transferred. Different types of resource utilization points are selected, and the number of resource utilization points corresponds to the type of green waste material. Each resource utilization point is used to process the resource utilization of one type of green waste material. Construct a material scheduling master map, mark each waste receiving point and resource utilization point on the material scheduling master map, take the maximum common number of waste transfer vehicles required to be scheduled for different types of green waste materials as the initial scheduling number, set the number of waste receiving points corresponding to the initial scheduling number as the path starting point on the material scheduling master map, and schedule several waste transfer vehicles covering all types of green waste materials at each path starting point for transporting green waste materials. Other waste receiving points near the starting point of the route are used as route connection points to connect the starting point of the route and the route connection points. Green waste materials are received at each route connection point until the green waste materials are fully loaded and then transported to the nearest resource utilization point at the current location. The starting point of the route, the resource utilization point, and several resource utilization points between the starting point of the route and the resource utilization point are connected on the material scheduling master map to construct the current transportation route of the waste transfer vehicle. The transportation routes of several vehicles under different categories are obtained and displayed on the material scheduling master map. All garbage receiving points not covered by the transportation routes on the material scheduling master map are designated as secondary scheduling points. All remaining unused garbage transfer vehicles are dispatched to each secondary scheduling point in sequence. The garbage transfer vehicles receive one type of green waste material at the secondary scheduling point until all green waste material at all secondary scheduling points has been transferred to the corresponding resource utilization point.

6. The intelligent management method for green waste according to claim 5, characterized in that, The process of constructing a resource process simulation model for each resource utilization point, simulating the utilization process of green waste materials using the resource process simulation model, and optimizing the utilization process of green waste materials at the corresponding resource utilization point based on the simulation results of the resource process simulation model at each resource utilization point includes: Physical entity modeling is performed on the resource processing equipment at each resource utilization point, creating their own simulated physical entities, defining the entity attributes of the simulated physical entities, monitoring the entire process of resource utilization of green waste materials at each resource utilization point, decomposing the entire process into several execution procedures, constructing a time-series coordinate axis, and arranging the several execution procedures to the corresponding positions on the time-series coordinate axis based on their respective procedure timestamps; A simulated scene space is created at each arrangement position. All simulated physical entities are assigned to the corresponding simulated scene space based on their respective execution processes. Constraint rules are set for each execution process as simulation reference data for simulating the utilization of green waste materials. Based on the simulation reference data, a simulation is performed in the corresponding simulation scenario space to obtain the performance simulation index of the corresponding process. The performance simulation index is correlated with the performance index range set for the corresponding process under ideal working conditions to construct a comparison dataset to record the simulation results of the corresponding process. The comparison dataset is analyzed to determine whether there is an optimization requirement for the corresponding process. If yes, then the corresponding simulation training optimization parameters for the relevant process are reset in the simulation scene space, and the simulation of the current process is executed again until the simulation result meets expectations, and then the simulation of the next process continues; if no, then the simulation of the next process is performed directly.

7. A smart management method for green waste according to claim 6, characterized in that, The process of bidding for material resources obtained at each resource utilization point includes: A resource package is constructed at each resource utilization point, and all resource packages from each resource utilization point are published to a bidding pool. Several bidders participate in the bidding based on the bidding pool. The bidding is evaluated based on the bidding information of each bidder, and several bidders matching several resource packages are selected. Contracts for the resource packages are signed and delivery procedures are executed. After delivery, the bidders settle funds and provide data feedback based on the resource utilization details of the resource packages. A bidding optimization model is constructed based on the data feedback results, and the resource bidding is optimized and managed through the bidding optimization model.

8. A smart management system for green waste, used to implement the smart management method according to any one of claims 1 to 7, characterized in that, The system includes: The intelligent equipment processing module is used to set up several waste receiving points, deploy green waste handling equipment at each waste receiving point, process green waste through green waste handling equipment, and thus obtain different types of green waste materials; The route planning and simulation module is used to sort and package different types of green waste materials, plan the transportation routes for each vehicle to transport the green waste materials to the corresponding resource utilization points, construct a resource process simulation model for each resource utilization point, and simulate the utilization process of green waste materials through the resource process simulation model. The process optimization and resource adaptation module optimizes the utilization process of green waste materials at each resource utilization point based on the simulation results of the resource process simulation model at each resource utilization point, and conducts resource bidding for the material resources obtained at each resource utilization point.

Images