A plastic bag material recycling system
By constructing and optimizing the material structure diagram of plastic bags, identifying key molecular structural characteristics and predicting behavior patterns, and dynamically adjusting recycling parameters, the problems of intricate sorting and low chemical recycling efficiency in the existing technology are solved, and efficient plastic bags are achieved Material recycling reduces energy consumption and environmental burden.
Patent Information
- Application Number
- CN202411248382.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-06
- Publication Date
- 2024-11-19
- Estimated Expiration
- 2044-09-06
AI Technical Summary
The existing plastic bag material recycling technology has problems such as poor sorting, low chemical recycling efficiency, large environmental burden, high energy consumption and serious material waste, making it difficult to achieve ideal resource utilization efficiency and environmental protection effects.
The material structure diagram construction module is used to collect the molecular structure data of plastic bags, and through the graph data compression and optimization, the key molecular structure characteristics are identified, the material behavior patterns are predicted, and the recycling parameters are dynamically adjusted, mechanical sorting and chemical processing conditions are optimized to achieve real-time monitoring and Adjustment.
It improves the accuracy and efficiency of plastic material recycling, reduces energy consumption and material waste, and improves resource utilization efficiency and environmental protection effect.
Smart Images

Figure CN118762769B_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of recycling, and in particular to a plastic bag material recycling system. Background Art
[0002] The field of recycling technology is concerned with the treatment and reprocessing of used substances and products so that they can be put back into use. This field covers a wide range of material types, including metals, paper, glass and plastics. Specifically for plastics, technologies include physical and chemical recycling methods. Physical recycling typically involves collecting, washing, sorting and crushing plastic waste, which is then melted into pellets for the production of new plastic products. Chemical recycling involves breaking down plastics into monomers or other chemicals that can be reused as new raw materials. This technology field is constantly developing and aims to improve resource efficiency, reduce waste and environmental impact, and explore more sustainable methods of material management.
[0003] Among them, the plastic bag material recycling system refers to a technical system specially designed to process and reuse plastic bags. Discarded plastic bags are converted into reusable materials through mechanical and chemical treatment. Its main purpose is to reduce the environmental impact of plastic waste, increase the recycling rate of resources, and promote economic sustainable development. In this way, not only can the dependence on new raw materials be reduced, but also the burden on landfills and the environment can be reduced.
[0004] Existing technologies have deficiencies in the recycling process. Physical recycling methods rely on manual or primary mechanical screening, and the sorting is not fine, and mixed plastic types affect the quality and purity of recycled materials. Chemical recycling methods lack accurate identification and processing of different types of plastics, and chemical reactions are inefficient, with many by-products and a heavy environmental burden. In addition, existing technologies lag behind in real-time monitoring and adjustment of recycling processing parameters, lack a dynamic adjustment mechanism, and have high energy consumption and serious material waste in the recycling process. These deficiencies make it difficult for existing technologies to achieve ideal resource utilization efficiency and environmental protection effects. Summary of the invention
[0005] The purpose of the present invention is to solve the shortcomings in the prior art and to propose a plastic bag material recycling system.
[0006] In order to achieve the above object, the present invention adopts the following technical solution: A plastic bag material recycling system comprises:
[0007] The material structure graph building module collects the molecular structure data of plastic bags, identifies molecules and polymers, determines the chemical and physical interactions between molecules, labels the elements as nodes and edges, creates the initial plastic structure graph, performs graph data compression and optimization operations, batch processes data, and obtains optimized graph structure data;
[0008] The graph structure analysis module uses the optimized graph structure data to perform node and edge attribute aggregation, identifies key molecular structure features through sorting and screening operations, reflects the connection importance of nodes and the interaction strength of edges, and establishes graph structure feature data;
[0009] The material behavior prediction module applies the graph structure feature data, performs set operations to identify the behavior patterns of plastic materials under differentiated recycling environments, classifies and labels the patterns, processes the change relationships between nodes, predicts material behavior data, compares the material behavior data with the chemical and physical reaction data from the real-time monitoring system, compares and determines the prediction accuracy of the updated model, and obtains dynamically adjusted prediction data;
[0010] The recycling process optimization module adjusts the mechanical sorting line and chemical treatment conditions according to the dynamically adjusted prediction data, integrates a real-time feedback mechanism, adjusts the speed and pressure of the crusher, adjusts the chemical depolymerization conditions, determines whether the recycling efficiency reaches the preset standard through comparison operations, and generates an optimized recycling parameter configuration.
[0011] As a further solution of the present invention, the steps of obtaining the initial plastic structure diagram are specifically as follows:
[0012] The plastic bag samples were subjected to liquid chromatography and mass spectrometry analysis to separate and identify molecules and polymers, and the content of each molecule was quantitatively analyzed using the formula:
[0013] ;
[0014] Obtain molecular composition analysis results;
[0015] in, represents the proportion of the ith molecule, represents the peak area of the i-th molecule, represents the total number of molecules;
[0016] Based on the molecular composition analysis results, nuclear magnetic resonance technology is used to determine the chemical bonds and physical interactions between molecules using the formula:
[0017] ;
[0018] Obtain descriptions of intermolecular interactions;
[0019] in, Representative molecules and The bond strength between represents the intermolecular distance, , , is the experimental constant;
[0020] According to the description of the intermolecular interaction, the formula is adopted:
[0021]
[0022] Establish an initial plastic structure diagram;
[0023] in, represents the overall structural strength of the graph, represents the edges in the graph, Represents the weight of the edge.
[0024] As a further solution of the present invention, the step of obtaining the optimized graph structure data is specifically as follows:
[0025] Starting from the initial plastic structure graph, the graph is topologically optimized using the formula:
[0026]
[0027] The topology optimization result is obtained by adjusting the weights to minimize the energy in a nonlinear way;
[0028] in, represents the energy of the optimized graph, represents the weight of the edge, represents the intermolecular bonding strength of the edge;
[0029] The topology optimization results are used for data compression to optimize storage by reducing the number of edges in the graph, using the formula:
[0030]
[0031] Calculate the compression effect of graph data and obtain the data compression result;
[0032] Among them, S represents the average compression ratio, Represents the chain length after node optimization, Represents the original chain length of the node;
[0033] Combined with the data compression results, graph data optimization is performed using the formula:
[0034]
[0035] Combining compression effect and energy optimization, we can obtain optimized graph structure data;
[0036] in, Represents the overall efficiency, represents the weight coefficient, Represents the compression ratio of the node, Represents the optimized energy of the node.
[0037] As a further solution of the present invention, the step of acquiring the graph structure feature data is specifically as follows:
[0038] Nodes and their connection properties are extracted from the optimized graph structure data, and the overall efficiency and the degree of the nodes are combined to adopt the formula:
[0039]
[0040] Calculate the weighted connection value of each node;
[0041] in, represents the weighted connection value of the node, represents the weight of the edge, represents the intermolecular bond strength, represents the degree of node j connected to node i;
[0042] The weighted connection value is analyzed using the formula:
[0043]
[0044] Calculate the adjusted importance of each node;
[0045] in, represents the adjusted importance of the node, Represents the maximum value of the node connection value, represents the degree of node i;
[0046] Using the adjusted importance data of each node, the formula is used:
[0047]
[0048] Calculate the weighted sum of the absolute interaction strength between each node and its adjacent nodes to generate graph structure feature data;
[0049] in, Key molecular structural characteristic indicators representing nodes, Represents the absolute interaction strength between node i and connected node j.
[0050] As a further solution of the present invention, the step of acquiring the dynamically adjusted prediction data is specifically as follows:
[0051] Using the graph structure feature data, the behavior patterns of plastic materials in differentiated recycling environments are identified through set operations, and the formula is applied:
[0052]
[0053] Calculate the behavior pattern differences of each node to obtain preliminary behavior pattern data;
[0054] in, represents the difference in the behavior patterns of nodes, S represents the set of nodes in the target environment, Represents key molecular structure characteristic indicators, represents the distance between nodes, , To adjust the parameters;
[0055] The preliminary behavior pattern data is classified and labeled using the formula:
[0056]
[0057] Process the change relationship between nodes and mark the behavior category to which node i belongs;
[0058] in, represents the behavior category to which node i belongs, Represents the classification group, Represents differences in behavior patterns, represents the maximum value of the difference in behavior patterns, is the weight parameter;
[0059] The behavior of the material is predicted using the behavior categories and the prediction results are compared with the data from the real-time monitoring system using the formula:
[0060]
[0061] Compare and judge the prediction accuracy of the model and obtain dynamically adjusted prediction data;
[0062] in, represents the predicted material behavior data, is the weight parameter, Represents real-time monitoring data.
[0063] As a further solution of the present invention, the step of obtaining the optimized recycling parameter configuration is specifically as follows:
[0064] According to the dynamically adjusted forecast data, the mechanical sorting line and chemical treatment conditions are adjusted using the formula:
[0065]
[0066] Adjust the speed, pressure and temperature of the crusher and calculate the initial adjustment parameters;
[0067] in, represents the adjusted recovery parameter, Represents the crusher speed, Represents the crusher pressure, represents the adjusted temperature, is the adjustment factor;
[0068] The parameters of the preliminary adjustment are optimized, and the recovery efficiency is determined by comparative operation using the formula:
[0069]
[0070] Verify whether the recycling efficiency meets the preset standards;
[0071] in, Represents the recycling efficiency, represents the experimental conditions, is the weight parameter;
[0072] Based on the comparison results of the recovery efficiency of the parameters adjusted initially, the formula is adopted:
[0073]
[0074] Generate optimized recycling parameter configuration;
[0075] in, Represents the optimized recycling parameter configuration, is the adjustment factor.
[0076] Compared with the prior art, the advantages and positive effects of the present invention are:
[0077] In the present invention, by compressing and optimizing graph data, batch processing is performed to obtain optimized graph structure data. Using these data, node and edge attributes are summarized, key molecular structure features are identified by sorting and screening, and graph structure feature data is established. Graph structure feature data is applied to identify the behavior patterns of plastic materials under different recycling environments, classify and mark patterns, process changes between nodes, predict material behavior data, and compare with real-time monitoring system data to update the prediction accuracy of the model and obtain dynamically adjusted prediction data. By identifying and marking molecular structures, optimizing graph structure data and dynamic behavior prediction, the recycling system can more accurately identify material characteristics and behaviors, optimize recycling parameter configuration, improve resource utilization efficiency and recycling processing accuracy, and reduce energy consumption and material waste. BRIEF DESCRIPTION OF THE DRAWINGS
[0078] Figure 1 is a system flow chart of the present invention;
[0079] Figure 2 This is a flow chart of the steps for obtaining the initial plastic structure diagram of the present invention;
[0080] Figure 3 A flowchart of the steps for obtaining graph structure data optimized by the present invention;
[0081] Figure 4A flowchart of the steps for obtaining the graph structure feature data of the present invention;
[0082] Figure 5 A flow chart of the steps for obtaining the prediction data dynamically adjusted according to the present invention;
[0083] Figure 6 The figure is a flow chart of the steps for obtaining the optimized recycling parameter configuration of the present invention. DETAILED DESCRIPTION
[0084] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.
[0085] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined. Embodiment 1
[0086] See also Figure 1 , a plastic bag material recycling system comprises:
[0087] The material structure graph building module collects the molecular structure data of plastic bags, identifies molecules and polymers, determines the chemical and physical interactions between molecules, labels the elements as nodes and edges, creates the initial plastic structure graph, performs graph data compression and optimization operations, batch processes data, and obtains optimized graph structure data;
[0088] The graph structure analysis module uses optimized graph structure data to perform node and edge attribute aggregation, identifies key molecular structure features through sorting and screening operations, reflects the connection importance of nodes and the interaction strength of edges, and establishes graph structure feature data;
[0089] The material behavior prediction module applies graph structure feature data, performs set operations to identify the behavior patterns of plastic materials in differentiated recycling environments, classifies and labels the patterns, processes the change relationships between nodes, predicts material behavior data, compares the material behavior data with the chemical and physical reaction data from the real-time monitoring system, compares and judges the prediction accuracy of the updated model, and obtains dynamically adjusted prediction data;
[0090] The recycling process optimization module adjusts the mechanical sorting line and chemical treatment conditions according to the dynamically adjusted prediction data, integrates the real-time feedback mechanism, adjusts the speed and pressure of the crusher, adjusts the chemical depolymerization conditions, determines whether the recycling efficiency meets the preset standards through comparison operations, and generates the optimized recycling parameter configuration.
[0091] The optimized graph structure data includes node data, edge data, and topological structure; the graph structure feature data includes node features, edge features, and connection strength; the dynamically adjusted prediction data includes behavior patterns, classification labels, and change relationships; and the optimized recycling parameter configuration includes speed parameters, pressure parameters, and disaggregation conditions.
[0092] See also Figure 2 , the specific steps for obtaining the initial plastic structure diagram are:
[0093] The plastic bag samples were subjected to liquid chromatography and mass spectrometry analysis to separate and identify molecules and polymers, and the content of each molecule was quantitatively analyzed using the formula:
[0094] ;
[0095] Obtain molecular composition analysis results;
[0096] in, represents the proportion of the ith molecule, represents the peak area of the i-th molecule, represents the total number of molecules;
[0097] Based on the results of molecular composition analysis, nuclear magnetic resonance technology is used to determine the chemical bonds and physical interactions between molecules using the formula:
[0098]
[0099] Obtain descriptions of intermolecular interactions;
[0100] in, Representative molecules and The bond strength between represents the intermolecular distance, , , is the experimental constant;
[0101] According to the description of intermolecular interactions, the formula is used:
[0102]
[0103] Establish an initial plastic structure diagram;
[0104] in, represents the overall structural strength of the graph, represents the edges in the graph, Represents the weight of the edge.
[0105] The formula in step 1:
[0106]
[0107] Parameter details:
[0108] No. The ratio of a molecule indicates the percentage of this molecule in the total molecules.
[0109] : No. The peak areas of the molecules were analyzed by HPLC and MS.
[0110] : The total number of molecules, obtained by analyzing the types of molecules in a plastic sample.
[0111] Example derivation:
[0112] Assume that three molecules are obtained by analyzing the plastic sample, and their peak areas are ,and . Calculate the proportion of multiple molecules:
[0113]
[0114] Total peak area
[0115]
[0116]
[0117]
[0118] The results showed that the first molecule accounted for , the second molecule accounts for , the third molecule accounts for .
[0119] The formula in step 2:
[0120]
[0121] Parameter details:
[0122] :molecular The bond strength between them.
[0123] : A constant determined experimentally.
[0124] : Intermolecular distance, determined by NMR analysis.
[0125] : The content ratio of molecules i and j obtained from step 1.
[0126] Example derivation:
[0127] Assumptions:
[0128]
[0129]
[0130] Using the previously calculated and
[0131] calculate :
[0132] Calculate distance influence
[0133] Calculate concentration influence
[0134]
[0135] Final Result This indicates that the bond strength between molecules 1 and 2 is higher, and calculations show that the bond is driven by the concentration difference.
[0136] The formula in step 3:
[0137]
[0138] Parameter details:
[0139] : The overall structural strength of the graph.
[0140] :The edges in the figure represent the bonds between molecules.
[0141] : The weight of the edge, determined by experiment or design.
[0142] : Intermolecular bond strength obtained from step 2.
[0143] Example derivation:
[0144] Assume there is only one edge in the graph, connecting molecule 1 and molecule 2:
[0145]
[0146] Use the value calculated in step 2
[0147] calculate :
[0148]
[0149] Final Result Represents the structural strength of the graph, where lower weights reduce the overall contribution of that connection.
[0150] See also Figure 3 , the specific steps for obtaining optimized graph structure data are:
[0151] Starting from the initial plastic structure graph, the graph is topologically optimized using the formula:
[0152]
[0153] The topology optimization result is obtained by adjusting the weights to minimize the energy in a nonlinear way;
[0154] in, represents the energy of the optimized graph, represents the weight of the edge, represents the intermolecular bonding strength of the edge;
[0155] The topology optimization results are used for data compression to optimize storage by reducing the number of edges in the graph, using the formula:
[0156]
[0157] Calculate the compression effect of graph data and obtain the data compression result;
[0158] Among them, S represents the average compression ratio, Represents the chain length after node optimization, Represents the original chain length of the node;
[0159] Combined with the data compression results, graph data optimization is performed using the formula:
[0160]
[0161] Combining compression effect and energy optimization, we can obtain optimized graph structure data;
[0162] in, Represents the overall efficiency, represents the weight coefficient, Represents the compression ratio of the node, Represents the optimized energy of the node.
[0163] Formula for Step 1: Topology Optimization
[0164] formula:
[0165]
[0166] Parameter interpretation and calculation process:
[0167] -The energy of the optimized graph, which represents the minimum possible value of the weighted sum of all edges in the graph.
[0168] -side The initial weight of , which represents the importance or cost of the edge.
[0169] - Intermolecular bond strength, reflecting the connection between molecules and The stability of the bond.
[0170] Derivation process and examples:
[0171] Assume there is a simple graph with 3 nodes and the following connections:
[0172] side
[0173] side
[0174] side
[0175] According to the formula, the contribution of each edge is calculated as follows:
[0176] For edge
[0177] For edge
[0178] For edge
[0179] Optimization energy of the entire graph It is the sum of these values:
[0180]
[0181] This value indicates that after considering the weight adjustment of the intermolecular bond strength, the total energy of the graph is 6.92, which is an optimization indicator of the graph. The lower it is, the more stable the graph is or the lower the cost is.
[0182] Formula for Step 2: Calculation of data compression effect
[0183] formula:
[0184]
[0185] Parameter interpretation and calculation process:
[0186] -Average compression ratio, which measures the data compression efficiency of the entire graph.
[0187] -The chain length of node i after optimization, that is, the number of connections between node i and other nodes after topology optimization.
[0188] -The original chain length of the node, that is, the number of connections of the original node.
[0189] Assuming numbers:
[0190]
[0191]
[0192]
[0193]
[0194] Calculation process:
[0195] For Node 1:
[0196] For Node 2:
[0197] For Node 3:
[0198] Average compression ratio yes:
[0199]
[0200] This means that on average, the number of connections per node in the graph is reduced by about , indicating that data compression effectively reduces storage and processing requirements.
[0201] Formula for Step 3: Graph Data Optimization
[0202] formula:
[0203]
[0204] Parameter interpretation and calculation process:
[0205] -The overall efficiency of the optimized graph structure, a comprehensive indicator.
[0206] -Weight coefficient, which reflects the importance of the node.
[0207] - Compression ratio of the node.
[0208] -Optimized energy of nodes.
[0209] Assuming numbers:
[0210]
[0211] Use step 2 value
[0212]
[0213] Calculation process:
[0214]
[0215]
[0216] This value represents the efficiency of the overall graph optimization, and the higher the value, the better the optimization.
[0217] See also Figure 4 ,The specific steps for obtaining graph structure feature data are:
[0218] Extract nodes and their connection properties from the optimized graph structure data, combine the overall efficiency and the degree of the nodes, and use the formula:
[0219]
[0220] Calculate the weighted connection value of each node;
[0221] in, represents the weighted connection value of the node, represents the weight of the edge, represents the intermolecular bond strength, represents the degree of node j connected to node i;
[0222] The weighted connection value is analyzed using the formula:
[0223]
[0224] Calculate the adjusted importance of each node;
[0225] in, represents the adjusted importance of the node, Represents the maximum value of the node connection value, represents the degree of node i;
[0226] Using the adjusted importance data for each node, the formula is:
[0227]
[0228] Calculate the weighted sum of the absolute interaction strength between each node and its adjacent nodes to generate graph structure feature data;
[0229] in, Key molecular structural characteristic indicators representing nodes, Represents the absolute interaction strength between node i and connected node j.
[0230] Detailed explanation and example of step 1 formula
[0231] formula:
[0232]
[0233] Parameter Description:
[0234] Node weighted connection value.
[0235] : The overall optimization efficiency, assumed to be a constant, such as 0.85, represents the efficiency obtained from the optimization process.
[0236] side The weight of the edge depends on the importance or flow of the edge.
[0237] : The strength of the intermolecular bond, determined by the chemical properties, for example -0.5.
[0238] : Nodes connected to node i The degree of the node The number of connections.
[0239] Calculation example:
[0240] Assume a simple network where node i is connected to two nodes j and k:
[0241]
[0242]
[0243]
[0244]
[0245] Calculation process:
[0246] Calculate the weighted value of edge (i,j):
[0247]
[0248] Calculate Edges Weighted value of:
[0249]
[0250] sum:
[0251]
[0252] Result description:
[0253] Represents the total connection strength of the node after adjusting the weight and optimization efficiency.
[0254] Detailed explanation and example of step 2 formula
[0255] formula:
[0256]
[0257] Parameter Description:
[0258] : The adjusted importance of the node.
[0259] : The weighted connection value of the node calculated from step 1.
[0260] : The maximum value of the weighted connection values of all nodes.
[0261] node The degree.
[0262] Calculation example:
[0263] Assumptions The node degree is 1.269 calculated in the previous step. , the largest of all nodes The value is 1.5.
[0264] Calculation process:
[0265] calculate :
[0266]
[0267] Result description:
[0268] Indicates the adjusted value of the node's importance.
[0269] Detailed explanation and example of step 3 formula
[0270] formula:
[0271]
[0272] Parameter Description:
[0273] : Key molecular structure characteristic indicators of the node.
[0274] The importance of the node calculated in step 2.
[0275] : Absolute intermolecular bond strength.
[0276] Calculation example:
[0277] Continue to use the previous parameters. is 0.929, assuming that the node connects two nodes, .
[0278] Calculation process:
[0279] calculate :
[0280]
[0281] Result description:
[0282] Represents the key molecular structure feature indicators of the node.
[0283] See also Figure 5 , the specific steps for obtaining dynamically adjusted prediction data are:
[0284] Using graph structure feature data, the behavior patterns of plastic materials in differentiated recycling environments are identified through set operations, and the formula is applied:
[0285]
[0286] Calculate the behavior pattern differences of each node to obtain preliminary behavior pattern data;
[0287] in, represents the difference in the behavior patterns of nodes, S represents the set of nodes in the target environment, Represents key molecular structure characteristic indicators, represents the distance between nodes, , To adjust the parameters;
[0288] The preliminary behavior pattern data is classified and labeled using the formula:
[0289]
[0290] Process the change relationship between nodes and mark the behavior category to which node i belongs;
[0291] in, represents the behavior category to which node i belongs, Represents the classification group, Represents differences in behavior patterns, represents the maximum value of the difference in behavior patterns, is the weight parameter;
[0292] Use behavioral categories to predict the behavior of the material and compare the prediction results with the data from the real-time monitoring system using the formula:
[0293]
[0294] Compare and judge the prediction accuracy of the model and obtain dynamically adjusted prediction data;
[0295] in, represents the predicted material behavior data, is the weight parameter, Represents real-time monitoring data.
[0296] Detailed explanation and example of the formula and parameters of step 1
[0297] formula:
[0298]
[0299] Parameter Description:
[0300] : Differences in node behavior patterns.
[0301] : The node collection in the target environment.
[0302] : Node i and Key molecular structural characteristic indicators.
[0303] : Node i and The distance between.
[0304] : Adjustment coefficient used to control the sensitivity and response range of the model.
[0305] Parameter settings:
[0306] Assume there are three nodes: node 1, node 2, and node 3.
[0307] : These values represent key molecular structural features of the multi-nodes.
[0308] : The distance between nodes.
[0309] : These values are obtained through model testing and environmental adjustments to optimize the model's predictive power.
[0310] Calculation example:
[0311] Compute Node 1 Behavior Differences
[0312]
[0313] This result It indicates the degree of difference between the behavior pattern of node 1 and other nodes. A higher value indicates that the behavior pattern of node 1 is more different from other nodes.
[0314] Detailed explanation and example of the formula and parameters of step 2
[0315] formula:
[0316]
[0317] Parameter Description:
[0318] : The behavior category to which node i belongs.
[0319] : Classification group, a collection of nodes of multiple categories.
[0320] Differences in behavior patterns.
[0321] : The maximum value of the difference in behavior patterns.
[0322] : Weight parameter used to balance comparisons within multiple groups.
[0323] Parameter settings:
[0324] Assuming the behavior pattern differences are known: .
[0325] Divided into two groups: .
[0326] , set to 1 to simplify the calculation.
[0327] Calculation example:
[0328] Behavior category of compute node 1 :
[0329]
[0330] for :
[0331]
[0332] This calculation determines the most likely behavior category of node 1 based on the existing pattern differences by comparing the degree of differences within multiple categories.
[0333] For the behavior category of node 1 Calculate and continue to compare with Group:
[0334] Continue the calculation:
[0335] for :
[0336]
[0337] Final result:
[0338] exist middle, The score is 0.7876, while The score is 0.8458. Therefore, node 1 is most likely to belong to category.
[0339] Detailed explanation and example of the formula and parameters of step 3
[0340] formula:
[0341]
[0342] Parameter Description:
[0343] : Predicted material behavior data.
[0344] : Weight parameter, which controls the weight of prediction and real-time data.
[0345] : Behavior categories predicted from graph data models.
[0346] : Data provided by the real-time monitoring system.
[0347] Parameter settings:
[0348] Assumptions : Assume that the model predictions are more reliable.
[0349] : The behavior category calculated in the previous step.
[0350] : Assume that the data given by the real-time monitoring system.
[0351] Calculation example:
[0352] Predicted material behavior data for computational node 1 :
[0353]
[0354] This result Represents the predicted material behavior data of node 1 after considering the model prediction and real-time monitoring data. A higher value indicates that node 1 is more active or responsive in the current environment.
[0355] See also Figure 6 , the specific steps for obtaining the optimized recycling parameter configuration are:
[0356] According to the dynamically adjusted forecast data, the mechanical sorting line and chemical treatment conditions are adjusted using the formula:
[0357]
[0358] Adjust the speed, pressure and temperature of the crusher and calculate the initial adjustment parameters;
[0359] in, represents the adjusted recovery parameter, Represents the crusher speed, Represents the crusher pressure, represents the adjusted temperature, is the adjustment factor;
[0360] Optimize the parameters adjusted initially, and judge the recovery efficiency by comparing the operations, using the formula:
[0361]
[0362] Verify whether the recycling efficiency meets the preset standards;
[0363] in, Represents the recycling efficiency, represents the experimental conditions, is the weight parameter;
[0364] Based on the preliminary adjusted parameter recovery efficiency comparison results, the formula is used:
[0365]
[0366] Generate optimized recycling parameter configuration;
[0367] in, Represents the optimized recycling parameter configuration, is the adjustment factor.
[0368] Detailed explanation and example of the formula for step 1:
[0369] formula:
[0370]
[0371] Parameter Description:
[0372] : Adjustment coefficient, used to balance the influence of different physical quantities on the adjustment parameters.
[0373] : Predicted material behavior data, assumed to be unit interval [0,1] A value in .
[0374] : Crusher speed, assuming the speed range is [0 m / s,5 m / s] .
[0375] : Crusher pressure, assuming the pressure range is [0MPa,10MPa] .
[0376] : Adjusted temperature, assuming the temperature range is .
[0377] Assumed parameter values:
[0378]
[0379] (Based on actual forecast results)
[0380]
[0381]
[0382]
[0383] Calculation process:
[0384] Calculate the contribution to speed:
[0385] Calculate the contribution of pressure:
[0386] Calculate the contribution of temperature:
[0387] Calculate the total adjustment:
[0388] Result interpretation:
[0389] is the value of the adjustment parameter obtained by comprehensively considering the predicted behavior, machine speed, pressure and temperature, which will be used to further adjust the sorting line and chemical treatment conditions.
[0390] Detailed explanation and example of the formula for step 2:
[0391] formula:
[0392]
[0393] Parameter Description:
[0394] Weight parameter, adjusts the strength of each influence.
[0395] : The adjustment parameter calculated in the previous step.
[0396] : Experimental conditions, assuming the concentration of the chemical substance, the value range is [0,100] .
[0397] Assumed parameter values:
[0398]
[0399]
[0400] Calculation process:
[0401] Calculate the logarithmic effect of the experimental condition:
[0402] Computational efficiency:
[0403] Result interpretation:
[0404] Represents the adjusted operating efficiency and is used to assess whether the preset recovery standards are met.
[0405] Detailed explanation and example of the formula for step 3:
[0406] formula:
[0407]
[0408] Parameter Description:
[0409] Adjustment factor used to adjust the sensitivity of the final parameter configuration.
[0410] The efficiency value calculated in the previous step.
[0411] Assumed parameter values:
[0412]
[0413] Using the value calculated in step 2
[0414] Calculation process:
[0415] Calculate the exponential decay effect:
[0416] Compute optimized configuration:
[0417] Result interpretation:
[0418] It is the optimized recycling parameter configuration value, which is used to finally adjust and optimize the recycling process to improve efficiency and adaptability.
[0419] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.
Claims
1. A plastic bag material recycling system, characterized in that: The system comprises: The material structure graph building module collects the molecular structure data of plastic bags, identifies molecules and polymers, determines the chemical and physical interactions between molecules, labels the elements as nodes and edges, creates the initial plastic structure graph, performs graph data compression and optimization operations, batch processes data, and obtains optimized graph structure data; The steps for obtaining the initial plastic structure diagram are specifically as follows: The plastic bag samples were subjected to liquid chromatography and mass spectrometry analysis to separate and identify molecules and polymers, and the content of each molecule was quantitatively analyzed using the formula: ; Obtain molecular composition analysis results; in, represents the proportion of the ith molecule, represents the peak area of the i-th molecule, represents the total number of molecules; Based on the molecular composition analysis results, nuclear magnetic resonance technology is used to determine the chemical bonds and physical interactions between molecules using the formula: ; Obtain descriptions of intermolecular interactions; in, Representative molecules and The bond strength between represents the intermolecular distance, For molecules The content ratio, , , is the experimental constant; According to the description of the intermolecular interaction, the formula is adopted: ; Establish an initial plastic structure diagram; in, represents the overall structural strength of the graph, represents the edges in the graph, represents the weight of the edge; The steps for obtaining the optimized graph structure data are specifically as follows: Starting from the initial plastic structure graph, the graph is topologically optimized using the formula: ; The topology optimization result is obtained by adjusting the weights to minimize the energy in a nonlinear way; in, represents the energy of the optimized graph, represents the weight of the edge, represents the intermolecular bonding strength of the edge; The topology optimization results are used for data compression to optimize storage by reducing the number of edges in the graph, using the formula: ; Calculate the compression effect of graph data and obtain the data compression result; Among them, S represents the average compression ratio, Represents the chain length after node optimization, Represents the original chain length of the node; Combined with the data compression results, graph data optimization is performed using the formula: ; Combining compression effect and energy optimization, we can obtain optimized graph structure data; in, Represents the overall efficiency, represents the weight coefficient, Represents the compression ratio of the node, represents the optimized energy of the node; The graph structure analysis module uses the optimized graph structure data to perform node and edge attribute aggregation, identifies key molecular structure features through sorting and screening operations, reflects the connection importance of nodes and the interaction strength of edges, and establishes graph structure feature data; The material behavior prediction module applies the graph structure feature data, performs set operations to identify the behavior patterns of plastic materials under differentiated recycling environments, classifies and labels the patterns, processes the change relationships between nodes, predicts material behavior data, compares the material behavior data with the chemical and physical reaction data from the real-time monitoring system, compares and determines the prediction accuracy of the updated model, and obtains dynamically adjusted prediction data; The steps for obtaining the dynamically adjusted prediction data are specifically as follows: Using the graph structure feature data, the behavior patterns of plastic materials in differentiated recycling environments are identified through set operations, and the formula is applied: ; Calculate the behavior pattern differences of each node to obtain preliminary behavior pattern data; in, represents the difference in the behavior patterns of nodes, S represents the set of nodes in the target environment, Represents key molecular structure characteristic indicators, represents the distance between nodes, , , To adjust the parameters; The preliminary behavior pattern data is classified and labeled using the formula: ; Process the change relationship between nodes and mark the behavior category to which node i belongs; in, represents the behavior category to which node i belongs, Represents the classification group, Represents differences in behavior patterns, represents the maximum value of the difference in behavior patterns, is the weight parameter; The behavior of the material is predicted using the behavior categories and the prediction results are compared with the data from the real-time monitoring system using the formula: ; Compare and judge the prediction accuracy of the model and obtain dynamically adjusted prediction data; in, represents the predicted material behavior data, is the weight parameter, Represents real-time monitoring data; The recycling process optimization module adjusts the mechanical sorting line and chemical treatment conditions according to the dynamically adjusted prediction data, integrates a real-time feedback mechanism, adjusts the speed and pressure of the crusher, adjusts the chemical depolymerization conditions, determines whether the recycling efficiency reaches the preset standard through comparison operations, and generates an optimized recycling parameter configuration.
2. The plastic bag material recycling system according to claim 1, characterized in that: The steps for obtaining the graph structure feature data are specifically as follows: Nodes and their connection properties are extracted from the optimized graph structure data, and the overall efficiency and the degree of the nodes are combined to adopt the formula: ; Calculate the weighted connection value of each node; in, represents the weighted connection value of the node, represents the weight of the edge, represents the intermolecular bond strength, represents the degree of node j connected to node i; The weighted connection value is analyzed using the formula: ; Calculate the adjusted importance of each node; in, represents the adjusted importance of the node, Represents the maximum value of the node connection value, represents the degree of node i; Using the adjusted importance data of each node, the formula is used: ; Calculate the weighted sum of the absolute interaction strength between each node and its adjacent nodes to generate graph structure feature data; in, Key molecular structural characteristic indicators representing nodes, Represents the absolute interaction strength between node i and connected node j.
3. The plastic bag material recycling system according to claim 1, characterized in that: The steps for obtaining the optimized recycling parameter configuration are specifically as follows: According to the dynamically adjusted forecast data, the mechanical sorting line and chemical treatment conditions are adjusted using the formula: ; Adjust the speed, pressure and temperature of the crusher and calculate the initial adjustment parameters; in, represents the adjusted recovery parameter, Represents the crusher speed, Represents the crusher pressure, represents the adjusted temperature, is the adjustment factor; The parameters of the preliminary adjustment are optimized, and the recovery efficiency is determined by comparative operation using the formula: ; Verify whether the recycling efficiency meets the preset standards; in, Represents the recycling efficiency, represents the experimental conditions, is the weight parameter; Based on the comparison results of the recovery efficiency of the parameters adjusted initially, the formula is adopted: ; Generate optimized recycling parameter configuration; in, Represents the optimized recycling parameter configuration, is the adjustment factor.
Citation Information
Patent Citations
Method and system suitable for energetic compound data mining
CN115691699A
Material property prediction method, system and equipment based on graph neural network
CN116665809A
Inter-drug interaction prediction model based on drug sequence and substructure characteristics
CN117409983A
Real-time bridge stress detection method and system
CN117807914A
Motorcycle electrical system fault detection system
CN117849512A
