Life cycle-based polylactic acid green evaluation method and system

Abstract

The invention discloses a polylactic acid green evaluation method and system based on a life cycle, and the method comprises the steps: collecting the monitoring data and working data of preset polylactic acid in the life cycle, carrying out the carbon emission deduction of the monitoring data based on an emission factor, and obtaining the carbon emission data, introducing dynamic genetic self-correction to dynamically correct the carbon emission data, dividing a life cycle into a plurality of decision units according to the working data, and taking the carbon emission data as labels of the decision units; performing input-output correlation analysis according to the decision-making unit and the label to obtain cross-period dependency data, decomposing the production process of the decision-making unit into a plurality of sub-stages, and constructing a carbon emission efficiency green evaluation function based on a dynamic network according to the cross-period dependency data and the sub-stages; and constructing a life cycle polylactic acid green evaluation model according to the carbon emission efficiency green evaluation function, inputting to-be-evaluated data into the life cycle polylactic acid green evaluation model, and outputting an evaluation result.

Description

Technical Field

[0001] The present invention relates to the field of green evaluation, and in particular to a green evaluation method and system for polylactic acid based on a life cycle. Background Art

[0002] With growing global attention to sustainable development, polylactic acid (PLA), a biodegradable material, demonstrates tremendous potential as a viable alternative to traditional petrochemical plastics and a catalyst for reducing environmental pollution. However, PLA's "green attributes" are not absolute. Its life cycle encompasses multiple stages, from raw material cultivation and production and processing to use and disposal. Each stage exhibits significant differences in resource consumption, pollutant emissions, and energy efficiency. Optimizing a single stage cannot fully reflect PLA's overall green performance. Traditional evaluation methods often focus on a single stage or indicator of PLA, making it difficult to systematically consider its dynamic changes and cross-stage correlations throughout its life cycle. This results in incomplete and inaccurate evaluation results.

[0003] In recent years, although the life cycle assessment (LCA) theory has been widely used in material sustainability assessment, it still faces many challenges in practical application. On the one hand, the data at each stage of the PLA life cycle has significant temporal and complex characteristics, and traditional LCA models have difficulty capturing the inter-period dependencies between data. On the other hand, carbon emissions, as a core indicator for measuring greenness, are affected by raw material fluctuations, process improvements, environmental factors, and other factors. Traditional static assessment methods cannot adapt to their dynamic changes. In addition, existing evaluation models mostly rely on fixed parameters and preset weights, lacking the ability to adaptively correct data uncertainties and environmental dynamics, resulting in evaluation results lagging behind actual conditions and making it difficult to meet the needs of rapid iteration and upgrading of the industry.

[0004] Therefore, there is an urgent need for a method that can integrate time series data analysis, dynamic parameter correction, and cross-stage correlation evaluation to scientifically and comprehensively quantify the green performance of PLA life cycle and provide a reliable basis for industry optimization and policy formulation. Summary of the Invention

[0005] The purpose of the present invention is to provide a green evaluation method for polylactic acid based on life cycle.

[0006] To achieve the above object, the present invention is implemented according to the following technical solutions: The present invention comprises the following steps: Collect monitoring data and working data of preset polylactic acid during its life cycle, and pre-process the monitoring data and working data; the life cycle includes raw material planting, lactic acid production, PLA polymerization, product manufacturing, circulation and use, waste gas treatment and regeneration cycle stages; the monitoring data includes nitrogen fertilizer usage, pesticide usage, agricultural machinery diesel consumption, irrigation usage, crop yield, fermentation tank power consumption, steam usage, wastewater COD concentration, polymerization reactor heat energy consumption, solvent recovery rate, catalyst usage, injection molding machine power, operating time, waste material generation, transportation distance, load, packaging material weight, composting plant PLA degradation rate, chemical depolymerization energy consumption and recycled material performance retention rate; Carbon emission data is obtained by performing carbon emission deduction on the monitoring data based on emission factors, dynamic genetic self-correction is introduced to dynamically correct the carbon emission data, and the life cycle is divided into multiple decision-making units according to the working data, and the carbon emission data is used as a label for the decision-making unit; Performing input-output correlation analysis based on the decision-making unit and the label to obtain inter-period dependency data, decomposing the production process of the decision-making unit into multiple sub-stages, and constructing a carbon emission efficiency green evaluation function based on the inter-period dependency data and the sub-stages based on a dynamic network; A life cycle polylactic acid green evaluation model is constructed according to the carbon emission efficiency green evaluation function, the data to be evaluated is input into the life cycle polylactic acid green evaluation model, and an evaluation result is output.

[0007] Furthermore, the method of performing carbon emission deduction on the monitoring data based on the emission factor to obtain carbon emission data includes: Obtain emission factors for each life cycle and calculate carbon emissions during the raw material planting stage: , The nitrous oxide emission factor is , the conversion coefficient is , converting the global warming potential of nitrous oxide to carbon dioxide equivalent, the amount of nitrogen fertilizer used is , the volume of diesel consumed for irrigation is , the carbon dioxide emissions from each liter of diesel combustion are , the crop yield is , the average carbon content in crops is , the carbon conversion coefficient to carbon dioxide is , the carbon emissions during the raw material planting stage are ; Calculate the carbon emissions of lactic acid production: , The power consumption of the fermentation tank is , the grid emission factor is , steam consumption is , the carbon dioxide emissions per kilogram of steam are , the removal of chemical oxygen demand in wastewater treatment is , the methane emissions produced per kilogram of chemical oxygen demand is , the global warming potential of methane is , the carbon emissions in the lactic acid production stage are ; Calculate the carbon emissions of the PLA polymerization stage: , The carbon emissions during the PLA polymerization stage are: , the heat energy consumption of the polymerization reactor is , the emission factor of the fuel is , the amount of unrecovered solvent is , the carbon dioxide emissions generated by each kilogram of solvent loss is ; Calculate the carbon emissions during the product manufacturing phase: , The carbon emissions during the product manufacturing phase are , the injection molding machine power is P, the running time is s, and the grid emission factor is , the amount of waste generated is , the carbon dioxide emissions generated by burning each kilogram of waste are ; Calculate carbon emissions during the circulation and use phase: , The carbon emissions during the circulation and use phase are , the transport distance is d, and the transport emission factor is , load is , the weight of packaging materials is , the carbon dioxide emissions generated by each kilogram of packaging material is ; Calculate the carbon emissions during the exhaust gas treatment stage: , The degradation amount is , the methane emissions generated by degradation of each kilogram of PLA is , the amount of PLA burned is , the carbon dioxide emissions generated by burning each kilogram of PLA are , the energy recovery deduction is , the energy recovered during the incineration process is converted into carbon dioxide emissions for deduction; Calculate the carbon emissions during the regeneration cycle: , The regenerative power consumption is , the output of recycled materials is , the carbon emissions of virgin PLA are , the carbon deduction coefficient is .

[0008] Furthermore, a method for dynamically correcting the carbon emission data by introducing dynamic genetic self-correction includes: The input parameter pool is extracted through monitoring data; the input parameters include heat transfer coefficient, catalyst activity coefficient, solvent recovery rate, and polymerization time; The global sensitivity screening method is used to calculate the sensitivity index of each parameter to carbon emissions: , , The i-th sensitivity index is , the parameter perturbation step size is , the i-th input parameter is , the carbon emissions caused by parameter changes are , the number of randomly sampled paths is , the i-th basic effect value of the z-th sampling path is , the standard value of the i-th basic effect is ; Input parameters with a sensitivity index greater than 0.472 are considered sensitive parameters. Sensitive parameters enter the genetic algorithm optimization, and the population is initialized according to the sensitive parameters. Individuals represent potential solutions corresponding to the adjusted sensitive parameters. Given the fitness, the expression is: , The fitness function is , the vth predicted carbon emission is , the vth measured carbon emission is ; Iterate continuously until the fitness function value reaches the maximum, output the adjusted sensitivity coefficient, and perform self-correction dynamic adjustment on the adjusted sensitivity coefficient. The expression is: , The weight coefficient of genetic optimization is , the original carbon emissions are , the adjusted i-th sensitivity coefficient is , the corrected carbon emissions are .

[0009] Furthermore, the method of dividing the life cycle into multiple decision units according to the work data includes: The life cycle is initially divided into multiple dimensions to obtain initial units. The multiple dimensions include process dimension, time dimension and carbon source dimension. The process dimension is divided according to the physical equipment boundary; the time dimension divides intermittent production into operation stages; the carbon source dimension distinguishes direct emissions from indirect emissions. Obtain the sensitivity variance of the relevant parameters of the polymerization unit from the monitoring data. The relevant parameters include catalyst concentration and stirring speed, and calculate the difference of the relevant parameters: , The sensitivity variance of the a-th related parameter is , the difference of the a-th related parameter is The maximum value of the sensitivity variance is , the minimum value of the sensitivity variance is ; When the difference is greater than the judgment threshold, the carbon emissions of the relevant parameters are calculated based on the working data, and the sensitivity variance ratio of the relevant parameters is calculated based on the carbon emissions; A string function is used to split the elements in the unit list according to the catalyst concentration in the polymerization unit to obtain the first new unit and the second new unit; the first new unit is the catalyst part in the polymerization reaction, and the second new unit is the mixing part in the polymerization reaction; If the catalyst concentration of the split subunit exceeds the concentration threshold, the stirring speed is multiplied by 1.02; otherwise, the split subunit is merged into the adjacent unit; the final result is used as the decision unit.

[0010] Furthermore, a method for obtaining inter-period dependency data by performing input-output correlation analysis based on the decision-making unit and the label includes: A dynamic causal relationship model is established based on a dynamic Bayesian network to describe the dependency relationship between decision-making units at different time points. The same-specification time series captures the impact of upstream units on the current unit. A recursive method is used to take the carbon emissions of the upstream unit as input and gradually transfer them to the downstream units, simulating the actual flow process and converting it into a dynamic recursive relationship, which is expressed as follows: , The recursive relationship function of carbon emissions is: , the carbon emissions of the i-th decision-making unit at time t is , the carbon emissions of the jth decision-making unit at time t-1 are , the degree dependence coefficient is , the degree of dependence of the rth decision-making unit on the jth decision-making unit, and the constant term is , the basic carbon emissions of the i-th decision-making unit in the absence of upstream units; Use time series network analysis technology to model the dependencies between different life stages at different time points, analyze the changes in dependency intensity through time slicing, and use Kalman filtering and long-term and short-term neural network models to dynamically predict changes in carbon emissions at each stage to capture inter-period dependencies and trends; Adding time expands the input-output matrix into a 3D matrix , the degree of dependence of the i-th decision-making unit on the j-th decision-making unit at time t; using dynamic adjustment weights, calculate the inter-period cumulative dependence matrix: , The discount factor is , the total number of time periods is , the inter-period cumulative dependency matrix of the rth decision-making unit is ; A dependency value is generated according to the inter-period cumulative dependency matrix, and the dependency value is output as inter-period dependency data.

[0011] Furthermore, a method for constructing a green evaluation function of carbon emission efficiency based on the inter-period dependency data and the sub-stages based on a dynamic network includes: Taking the sub-stages as nodes, the inter-period dependency data as edges, and the node attribute as carbon emissions, calculate the inter-period cumulative carbon emissions: , The cumulative carbon emissions across sub-stage b are , the carbon emissions of the kth sub-stage are , the inter-period cumulative dependence data of the b-th sub-stage on the k-th sub-stage is ; Calculate the objectively weighted carbon emission efficiency per unit of output: , The carbon emission efficiency per unit output is , the performance index of the b-th sub-stage is , performance indicators include efficiency, total energy consumption and water footprint, the importance weight of the bth sub-stage ; Construct a green evaluation function for carbon emission efficiency, the expression is: ; The efficiency index is , the total energy consumption is , the water footprint indicator is The total water consumption is , the energy consumption index is , the efficiency weight is , the energy consumption weight is , the water footprint weight is , the green evaluation function of carbon emission efficiency is .

[0012] Furthermore, a method for constructing a life cycle polylactic acid green evaluation model based on the carbon emission efficiency green evaluation function includes: Taking the objective weighted sum of the carbon emission efficiency green evaluation function and the loss function as the objective function, the life cycle polylactic acid green evaluation model includes an autoencoder, a temporal attention mechanism, and a recurrent neural network algorithm; The autoencoder compresses the input data into a low-dimensional hidden layer feature vector through the encoder, and the decoder reconstructs the input with the goal of minimizing the reconstruction error, so that the model automatically extracts the core green features of the data during the compression process; The temporal attention mechanism dynamically weights the green features of polylactic acid at different time stages in its life cycle, focuses on the environmental impact characteristics of key periods, and analyzes the temporal correlation of green performance to obtain temporal green feature characteristics. The recurrent neural network algorithm captures the dependency of temporal green feature characteristics in the life cycle through the cyclic connection of hidden layer neurons, optimizes network parameters based on minimizing the evaluation error of the objective function, and dynamically models and comprehensively evaluates the green performance of each stage.

[0013] The second aspect is a green evaluation system for polylactic acid based on the life cycle, including: Data acquisition module: used to collect monitoring data and working data of the preset polylactic acid during its life cycle, and pre-process the monitoring data and working data; the life cycle includes raw material planting, lactic acid production, PLA polymerization, product manufacturing, circulation and use, waste gas treatment and regeneration cycle stages; Deduction and correction module: used to deduce carbon emissions from the monitoring data based on emission factors to obtain carbon emission data, introduce dynamic genetic self-correction to dynamically correct the carbon emission data, divide the life cycle into multiple decision units according to the working data, and use the carbon emission data as labels for the decision units; Production correlation efficiency module: used to perform input-output correlation analysis based on the decision-making unit and the label to obtain inter-period dependency data, decompose the production process of the decision-making unit into multiple sub-stages, and construct a carbon emission efficiency green evaluation function based on the inter-period dependency data and the sub-stages based on a dynamic network; Modeling output module: used to construct a life cycle polylactic acid green evaluation model according to the carbon emission efficiency green evaluation function, input the data to be evaluated into the life cycle polylactic acid green evaluation model, and output the evaluation results.

[0014] The beneficial effects of the present invention are: The present invention is a green evaluation method and system for polylactic acid based on the life cycle. Compared with the existing technology, the present invention has the following technical effects: The present invention can improve the accuracy of the green evaluation of polylactic acid in the life cycle through preprocessing, carbon emission deduction, dynamic correction, division into multiple decision-making units, input-output correlation analysis, construction of carbon emission efficiency green evaluation function and model construction steps, thereby improving the precision of the green evaluation of polylactic acid in the life cycle, optimizing the green evaluation of polylactic acid in the life cycle, greatly saving resources, improving work efficiency, and realizing scientific evaluation of the greenness of polylactic acid in the life cycle. The green evaluation of polylactic acid in the real-time life cycle is dynamically corrected and input-output correlation analyzed, which is of great significance to the green evaluation of polylactic acid in the life cycle, can adapt to the green evaluation of polylactic acid in the life cycle of different standards and the green evaluation requirements of polylactic acid in different life cycles, and has a certain universality. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 The present invention provides a flow chart of the steps of a green evaluation method for polylactic acid based on a life cycle. DETAILED DESCRIPTION

[0016] The present invention will be further described below through specific examples. The illustrative examples and descriptions of the present invention are used to explain the present invention but are not intended to limit the present invention.

[0017] The present invention provides a green evaluation method and system for polylactic acid based on a life cycle, comprising the following steps: like Figure 1 As shown, in this embodiment, the following steps are included: Collect monitoring data and working data of preset polylactic acid during its life cycle, and pre-process the monitoring data and working data; the life cycle includes raw material planting, lactic acid production, PLA polymerization, product manufacturing, circulation and use, waste gas treatment and regeneration cycle stages; the monitoring data includes nitrogen fertilizer usage, pesticide usage, agricultural machinery diesel consumption, irrigation usage, crop yield, fermentation tank power consumption, steam usage, wastewater COD concentration, polymerization reactor heat energy consumption, solvent recovery rate, catalyst usage, injection molding machine power, operating time, waste material generation, transportation distance, load, packaging material weight, composting plant PLA degradation rate, chemical depolymerization energy consumption and recycled material performance retention rate; In an actual evaluation, a green evaluation was conducted on process routes A and B of a PLA company. Process route A used a traditional solvent method, while process route B was a solvent-free method. Process route A had a solvent recovery rate of 85% and a chemical depolymerization energy consumption of 500kWh / t. Process route B reduced catalyst usage by 30% and retained 95% of the recycled material performance. Monitoring data includes nitrogen fertilizer application, agricultural machinery diesel consumption, crop yield, fermentation tank power consumption of 5000kWh, steam usage, wastewater COD removal, polymerization reactor heat consumption, solvent recovery rate, unrecovered solvent volume, injection molding machine power, operating time, and waste generation; Carbon emission data is obtained by performing carbon emission deduction on the monitoring data based on emission factors, dynamic genetic self-correction is introduced to dynamically correct the carbon emission data, and the life cycle is divided into multiple decision-making units according to the working data, and the carbon emission data is used as a label for the decision-making unit; In the actual evaluation, the carbon emissions of process route A in the raw material planting, lactic acid production, PLA polymerization, and product manufacturing stages were 1798.5 kg CO2e, 12001.8 kg CO2e, 1493 kg CO2e, and 812 kg CO2e, respectively; the carbon emissions of process route B in the raw material planting, lactic acid production, PLA polymerization, and product manufacturing stages were 1791.6 kg CO2e, 11987.8 kg CO2e, 1031.3 kg CO2e, and 604.1 kg CO2e, respectively. Solvent recovery rate is used as a sensitivity index. After dynamic correction, the carbon emissions of the PLA polymerization stage of process route A are 1795.8 kg CO2e; after dynamic correction, the carbon emissions of the PLA polymerization stage of process route B are 1206.4 kg CO2e. Performing input-output correlation analysis based on the decision-making unit and the label to obtain inter-period dependency data, decomposing the production process of the decision-making unit into multiple sub-stages, and constructing a carbon emission efficiency green evaluation function based on the inter-period dependency data and the sub-stages based on a dynamic network; In the actual evaluation, process route B reduced the dependence coefficient of PLA polymerization on upstream units by 30% due to its solvent-free process. The output efficiency of process route A was 0.0585, and the output efficiency of process route B was 0.0778. The green evaluation function values ​​of carbon emission efficiency of process routes A and B were 0.2606 and 0.2473, respectively. A life cycle polylactic acid green evaluation model is constructed according to the carbon emission efficiency green evaluation function, the data to be evaluated is input into the life cycle polylactic acid green evaluation model, and an evaluation result is output.

[0018] In this embodiment, the method for obtaining carbon emission data by performing carbon emission deduction on the monitoring data based on the emission factor includes: Obtain emission factors for each life cycle and calculate carbon emissions during the raw material planting stage: , The nitrous oxide emission factor is , the conversion coefficient is , converting the global warming potential of nitrous oxide to carbon dioxide equivalent, the amount of nitrogen fertilizer used is , the volume of diesel consumed for irrigation is , the carbon dioxide emissions from each liter of diesel combustion are , the crop yield is , the average carbon content in crops is , the carbon conversion coefficient to carbon dioxide is , the carbon emissions during the raw material planting stage are ; Calculate the carbon emissions of lactic acid production: , The power consumption of the fermentation tank is , the grid emission factor is , steam consumption is , the carbon dioxide emissions per kilogram of steam are , the removal of chemical oxygen demand in wastewater treatment is , the methane emissions produced per kilogram of chemical oxygen demand is , the global warming potential of methane is , the carbon emissions in the lactic acid production stage are ; Calculate the carbon emissions of the PLA polymerization stage: , The carbon emissions during the PLA polymerization stage are: , the heat energy consumption of the polymerization reactor is , the emission factor of the fuel is , the amount of unrecovered solvent is , the carbon dioxide emissions generated by each kilogram of solvent loss is ; Calculate the carbon emissions during the product manufacturing phase: , The carbon emissions during the product manufacturing phase are , the injection molding machine power is P, the running time is s, and the grid emission factor is , the amount of waste generated is , the carbon dioxide emissions generated by burning each kilogram of waste are ; Calculate carbon emissions during the circulation and use phase: , The carbon emissions during the circulation and use phase are , the transport distance is d, and the transport emission factor is , load is , the weight of packaging materials is , the carbon dioxide emissions generated by each kilogram of packaging material is ; Calculate the carbon emissions during the exhaust gas treatment stage: , The degradation amount is , the methane emissions generated by degradation of each kilogram of PLA is , the amount of PLA burned is , the carbon dioxide emissions generated by burning each kilogram of PLA are , the energy recovery deduction is , the energy recovered during the incineration process is converted into carbon dioxide emissions for deduction; Calculate the carbon emissions during the regeneration cycle: , The regenerative power consumption is , the output of recycled materials is , the carbon emissions of virgin PLA are , the carbon deduction coefficient is .

[0019] In this embodiment, a method for dynamically correcting the carbon emission data by introducing dynamic genetic self-correction includes: The input parameter pool is extracted through monitoring data; the input parameters include heat transfer coefficient, catalyst activity coefficient, solvent recovery rate, and polymerization time; The global sensitivity screening method is used to calculate the sensitivity index of each parameter to carbon emissions: , , The i-th sensitivity index is , the parameter perturbation step size is , the i-th input parameter is , the carbon emissions caused by parameter changes are , the number of randomly sampled paths is , the i-th basic effect value of the z-th sampling path is , the standard value of the i-th basic effect is ; Input parameters with a sensitivity index greater than 0.472 are considered sensitive parameters. Sensitive parameters enter the genetic algorithm optimization, and the population is initialized according to the sensitive parameters. Individuals represent potential solutions corresponding to the adjusted sensitive parameters. Given the fitness, the expression is: , The fitness function is , the vth predicted carbon emission is , the vth measured carbon emission is ; Iterate continuously until the fitness function value reaches the maximum, output the adjusted sensitivity coefficient, and perform self-correction dynamic adjustment on the adjusted sensitivity coefficient. The expression is: , The weight coefficient of genetic optimization is , the original carbon emissions are , the adjusted i-th sensitivity coefficient is , the corrected carbon emissions are .

[0020] In this embodiment, the method of dividing the life cycle into multiple decision units according to the work data includes: The life cycle is initially divided into multiple dimensions to obtain initial units. The multiple dimensions include process dimension, time dimension and carbon source dimension. The process dimension is divided according to the physical equipment boundary; the time dimension divides intermittent production into operation stages; the carbon source dimension distinguishes direct emissions from indirect emissions. Obtain the sensitivity variance of the relevant parameters of the polymerization unit from the monitoring data. The relevant parameters include catalyst concentration and stirring speed, and calculate the difference of the relevant parameters: , The sensitivity variance of the a-th related parameter is , the difference of the a-th related parameter is The maximum value of the sensitivity variance is , the minimum value of the sensitivity variance is ; When the difference is greater than the judgment threshold, the carbon emissions of the relevant parameters are calculated based on the working data, and the sensitivity variance ratio of the relevant parameters is calculated based on the carbon emissions; A string function is used to split the elements in the unit list according to the catalyst concentration in the polymerization unit to obtain the first new unit and the second new unit; the first new unit is the catalyst part in the polymerization reaction, and the second new unit is the mixing part in the polymerization reaction; If the catalyst concentration of the split subunit exceeds the concentration threshold, the stirring speed is multiplied by 1.02; otherwise, the split subunit is merged into the adjacent unit; the final result is used as the decision unit.

[0021] In this embodiment, the method for obtaining inter-period dependency data by performing input-output association analysis based on the decision-making unit and the label includes: A dynamic causal relationship model is established based on a dynamic Bayesian network to describe the dependency relationship between decision-making units at different time points. The same-specification time series captures the impact of upstream units on the current unit. A recursive method is used to take the carbon emissions of the upstream unit as input and gradually transfer them to the downstream units, simulating the actual flow process and converting it into a dynamic recursive relationship, which is expressed as follows: , The recursive relationship function of carbon emissions is: , the carbon emissions of the i-th decision-making unit at time t is , the carbon emissions of the jth decision-making unit at time t-1 are , the degree dependence coefficient is , the degree of dependence of the rth decision-making unit on the jth decision-making unit, and the constant term is , the basic carbon emissions of the i-th decision-making unit in the absence of upstream units; Use time series network analysis technology to model the dependencies between different life stages at different time points, analyze the changes in dependency intensity through time slicing, and use Kalman filtering and long-term and short-term neural network models to dynamically predict changes in carbon emissions at each stage to capture inter-period dependencies and trends; Adding time expands the input-output matrix into a 3D matrix , the degree of dependence of the i-th decision-making unit on the j-th decision-making unit at time t; using dynamic adjustment weights, calculate the inter-period cumulative dependence matrix: , The discount factor is , the total number of time periods is , the inter-period cumulative dependency matrix of the rth decision-making unit is ; A dependency value is generated according to the inter-period cumulative dependency matrix, and the dependency value is output as inter-period dependency data.

[0022] In this embodiment, the method for constructing a green evaluation function for carbon emission efficiency based on the inter-period dependency data and the sub-stages based on a dynamic network includes: Taking the sub-stages as nodes, the inter-period dependency data as edges, and the node attribute as carbon emissions, calculate the inter-period cumulative carbon emissions: , The cumulative carbon emissions across sub-stage b are , the carbon emissions of the kth sub-stage are , the inter-period cumulative dependence data of the b-th sub-stage on the k-th sub-stage is ; Calculate the objectively weighted carbon emission efficiency per unit of output: , The carbon emission efficiency per unit output is , the performance index of the b-th sub-stage is , performance indicators include efficiency, total energy consumption and water footprint, the importance weight of the bth sub-stage ; Construct a green evaluation function for carbon emission efficiency, the expression is: ; The efficiency index is , the total energy consumption is , the water footprint indicator is The total water consumption is , the energy consumption index is , the efficiency weight is , the energy consumption weight is , the water footprint weight is , the green evaluation function of carbon emission efficiency is .

[0023] In this embodiment, the method for constructing a life cycle polylactic acid green evaluation model according to the carbon emission efficiency green evaluation function includes: Taking the objective weighted sum of the carbon emission efficiency green evaluation function and the loss function as the objective function, the life cycle polylactic acid green evaluation model includes an autoencoder, a temporal attention mechanism, and a recurrent neural network algorithm; The autoencoder compresses the input data into a low-dimensional hidden layer feature vector through the encoder, and the decoder reconstructs the input with the goal of minimizing the reconstruction error, so that the model automatically extracts the core green features of the data during the compression process; The temporal attention mechanism dynamically weights the green features of polylactic acid at different time stages in its life cycle, focuses on the environmental impact characteristics of key periods, and analyzes the temporal correlation of green performance to obtain temporal green feature characteristics. The recurrent neural network algorithm captures the dependency of temporal green feature characteristics in the life cycle through the cyclic connection of hidden layer neurons, optimizes network parameters based on minimizing the evaluation error of the objective function, and dynamically models and comprehensively evaluates the green performance of each stage.

[0024] The second aspect is a green evaluation system for polylactic acid based on the life cycle, including: Data acquisition module: used to collect monitoring data and working data of the preset polylactic acid during its life cycle, and pre-process the monitoring data and working data; the life cycle includes raw material planting, lactic acid production, PLA polymerization, product manufacturing, circulation and use, waste gas treatment and regeneration cycle stages; Deduction and correction module: used to deduce carbon emissions from the monitoring data based on emission factors to obtain carbon emission data, introduce dynamic genetic self-correction to dynamically correct the carbon emission data, divide the life cycle into multiple decision units according to the working data, and use the carbon emission data as labels for the decision units; Production correlation efficiency module: used to perform input-output correlation analysis based on the decision-making unit and the label to obtain inter-period dependency data, decompose the production process of the decision-making unit into multiple sub-stages, and construct a carbon emission efficiency green evaluation function based on the inter-period dependency data and the sub-stages based on a dynamic network; Modeling output module: used to construct a life cycle polylactic acid green evaluation model according to the carbon emission efficiency green evaluation function, input the data to be evaluated into the life cycle polylactic acid green evaluation model, and output the evaluation results.

[0025] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A green evaluation method for polylactic acid based on life cycle, characterized in that: The following steps are involved: Collect monitoring data and working data of preset polylactic acid during its life cycle, and pre-process the monitoring data and working data; the life cycle includes raw material planting, lactic acid production, PLA polymerization, product manufacturing, circulation and use, waste gas treatment and regeneration cycle stages; the monitoring data includes nitrogen fertilizer usage, pesticide usage, agricultural machinery diesel consumption, irrigation usage, crop yield, fermentation tank power consumption, steam usage, wastewater COD concentration, polymerization reactor heat energy consumption, solvent recovery rate, catalyst usage, injection molding machine power, operating time, waste material generation, transportation distance, load, packaging material weight, composting plant PLA degradation rate, chemical depolymerization energy consumption and recycled material performance retention rate; Carbon emission data is obtained by performing carbon emission deduction on the monitoring data based on emission factors, dynamic genetic self-correction is introduced to dynamically correct the carbon emission data, and the life cycle is divided into multiple decision-making units according to the working data, and the carbon emission data is used as a label for the decision-making unit; Performing input-output correlation analysis based on the decision-making unit and the label to obtain inter-period dependency data, decomposing the production process of the decision-making unit into multiple sub-stages, and constructing a carbon emission efficiency green evaluation function based on the inter-period dependency data and the sub-stages based on a dynamic network; A life cycle polylactic acid green evaluation model is constructed according to the carbon emission efficiency green evaluation function, the data to be evaluated is input into the life cycle polylactic acid green evaluation model, and an evaluation result is output.

2. The green evaluation method for polylactic acid based on life cycle according to claim 1, characterized in that: The method for obtaining carbon emission data by performing carbon emission deduction on the monitoring data based on emission factors includes: Obtain emission factors for each life cycle and calculate carbon emissions during the raw material planting stage: ， The nitrous oxide emission factor is , the conversion coefficient is , converting the global warming potential of nitrous oxide to carbon dioxide equivalent, the amount of nitrogen fertilizer used is , the volume of diesel consumed for irrigation is , the carbon dioxide emissions from each liter of diesel combustion are , the crop yield is , the average carbon content in crops is , the carbon conversion coefficient to carbon dioxide is , the carbon emissions during the raw material planting stage are ; Calculate the carbon emissions of lactic acid production: ， The power consumption of the fermentation tank is , the grid emission factor is , steam consumption is , the carbon dioxide emissions per kilogram of steam are , the removal of chemical oxygen demand in wastewater treatment is , the methane emissions produced per kilogram of chemical oxygen demand is , the global warming potential of methane is , the carbon emissions in the lactic acid production stage are ; Calculate the carbon emissions of the PLA polymerization stage: ， The carbon emissions during the PLA polymerization stage are: , the heat energy consumption of the polymerization reactor is , the emission factor of the fuel is , the amount of unrecovered solvent is , the carbon dioxide emissions generated by each kilogram of solvent loss is ; Calculate the carbon emissions during the product manufacturing phase: ， The carbon emissions during the product manufacturing phase are , the injection molding machine power is P, the running time is s, and the grid emission factor is , the amount of waste generated is , the carbon dioxide emissions generated by burning each kilogram of waste are ; Calculate carbon emissions during the circulation and use phase: ， The carbon emissions during the circulation and use phase are , the transport distance is d, and the transport emission factor is , load is , the weight of packaging materials is , the carbon dioxide emissions generated by each kilogram of packaging material is ; Calculate the carbon emissions during the exhaust gas treatment stage: ， The degradation amount is , the methane emissions generated by degradation of each kilogram of PLA is , the amount of PLA burned is , the carbon dioxide emissions generated by burning each kilogram of PLA are , the energy recovery deduction is , the energy recovered during the incineration process is converted into carbon dioxide emissions for deduction; Calculate the carbon emissions during the regeneration cycle: ， The regenerative power consumption is , the output of recycled materials is , the carbon emissions of virgin PLA are , the carbon deduction coefficient is .

3. The green evaluation method for polylactic acid based on life cycle according to claim 1, characterized in that: A method for dynamically correcting the carbon emission data by introducing dynamic genetic self-correction includes: The input parameter pool is extracted through monitoring data; the input parameters include heat transfer coefficient, catalyst activity coefficient, solvent recovery rate, and polymerization time; The global sensitivity screening method is used to calculate the sensitivity index of each parameter to carbon emissions: ， ， The i-th sensitivity index is , the parameter perturbation step size is , the i-th input parameter is , the carbon emissions caused by parameter changes are , the number of randomly sampled paths is , the i-th basic effect value of the z-th sampling path is , the standard value of the i-th basic effect is ; Input parameters with a sensitivity index greater than 0.472 are considered sensitive parameters. Sensitive parameters enter the genetic algorithm optimization, and the population is initialized according to the sensitive parameters. Individuals represent potential solutions corresponding to the adjusted sensitive parameters. Given the fitness, the expression is: ， The fitness function is , the vth predicted carbon emission is , the vth measured carbon emission is ; Iterate continuously until the fitness function value reaches the maximum, output the adjusted sensitivity coefficient, and perform self-correction dynamic adjustment on the adjusted sensitivity coefficient. The expression is: ， The weight coefficient of genetic optimization is , the original carbon emissions are , the adjusted i-th sensitivity coefficient is , the corrected carbon emissions are .

4. The green evaluation method for polylactic acid based on life cycle according to claim 1, characterized in that: The method of dividing the life cycle into a plurality of decision units according to the work data includes: The life cycle is initially divided into multiple dimensions to obtain initial units. The multiple dimensions include process dimension, time dimension and carbon source dimension. The process dimension is divided according to the physical equipment boundary; the time dimension divides intermittent production into operation stages; the carbon source dimension distinguishes direct emissions from indirect emissions. Obtain the sensitivity variance of the relevant parameters of the polymerization unit from the monitoring data. The relevant parameters include catalyst concentration and stirring speed, and calculate the difference of the relevant parameters: ， The sensitivity variance of the a-th related parameter is , the difference of the a-th related parameter is The maximum value of the sensitivity variance is , the minimum value of the sensitivity variance is ; When the difference is greater than the judgment threshold, the carbon emissions of the relevant parameters are calculated based on the working data, and the sensitivity variance ratio of the relevant parameters is calculated based on the carbon emissions; A string function is used to split the elements in the unit list according to the catalyst concentration in the polymerization unit to obtain the first new unit and the second new unit; the first new unit is the catalyst part in the polymerization reaction, and the second new unit is the mixing part in the polymerization reaction; If the catalyst concentration of the split subunit exceeds the concentration threshold, the stirring speed is multiplied by 1.02; otherwise, the split subunit is merged into the adjacent unit; the final result is used as the decision unit.

5. The green evaluation method of polylactic acid based on life cycle according to claim 1, characterized in that: The method for obtaining inter-period dependency data by performing input-output association analysis based on the decision-making unit and the label includes: A dynamic causal relationship model is established based on a dynamic Bayesian network to describe the dependency relationship between decision-making units at different time points. The same-specification time series captures the impact of upstream units on the current unit. A recursive method is used to take the carbon emissions of the upstream unit as input and gradually transfer them to the downstream units, simulating the actual flow process and converting it into a dynamic recursive relationship, which is expressed as follows: ， The recursive relationship function of carbon emissions is: , the carbon emissions of the i-th decision-making unit at time t is , the carbon emissions of the jth decision-making unit at time t-1 are , the degree dependence coefficient is , the degree of dependence of the rth decision-making unit on the jth decision-making unit, and the constant term is , the basic carbon emissions of the i-th decision-making unit in the absence of upstream units; Use time series network analysis technology to model the dependencies between different life stages at different time points, analyze the changes in dependency intensity through time slicing, and use Kalman filtering and long-term and short-term neural network models to dynamically predict changes in carbon emissions at each stage to capture inter-period dependencies and trends; Adding time expands the input-output matrix into a 3D matrix , the degree of dependence of the i-th decision-making unit on the j-th decision-making unit at time t; using dynamic adjustment weights, calculate the inter-period cumulative dependence matrix: ， The discount factor is , the total number of time periods is , the inter-period cumulative dependency matrix of the rth decision-making unit is ; A dependency value is generated according to the inter-period cumulative dependency matrix, and the dependency value is output as inter-period dependency data.

6. The green evaluation method for polylactic acid based on life cycle according to claim 1, characterized in that: The method for constructing a green evaluation function of carbon emission efficiency based on the inter-period dependency data and the sub-stages based on a dynamic network includes: Taking the sub-stages as nodes, the inter-period dependency data as edges, and the node attribute as carbon emissions, calculate the inter-period cumulative carbon emissions: ， The cumulative carbon emissions across sub-stage b are , the carbon emissions of the kth sub-stage are , the inter-period cumulative dependence data of the b-th sub-stage on the k-th sub-stage is ; Calculate the objectively weighted carbon emission efficiency per unit of output: ， The carbon emission efficiency per unit output is , the performance index of the b-th sub-stage is , performance indicators include efficiency, total energy consumption and water footprint, the importance weight of the bth sub-stage ; Construct a green evaluation function for carbon emission efficiency, the expression is: ； The efficiency index is , the total energy consumption is , the water footprint indicator is The total water consumption is , the energy consumption index is , the efficiency weight is , the energy consumption weight is , the water footprint weight is , the green evaluation function of carbon emission efficiency is .

7. The green evaluation method for polylactic acid based on life cycle according to claim 1, characterized in that: The method for constructing a life cycle polylactic acid green evaluation model according to the carbon emission efficiency green evaluation function includes: Taking the objective weighted sum of the carbon emission efficiency green evaluation function and the loss function as the objective function, the life cycle polylactic acid green evaluation model includes an autoencoder, a temporal attention mechanism, and a recurrent neural network algorithm; The autoencoder compresses the input data into a low-dimensional hidden layer feature vector through the encoder, and the decoder reconstructs the input with the goal of minimizing the reconstruction error, so that the model automatically extracts the core green features of the data during the compression process; The temporal attention mechanism dynamically weights the green features of polylactic acid at different time stages in its life cycle, focuses on the environmental impact characteristics of key periods, and analyzes the temporal correlation of green performance to obtain temporal green feature characteristics. The recurrent neural network algorithm captures the dependency of temporal green feature characteristics in the life cycle through the cyclic connection of hidden layer neurons, optimizes network parameters based on minimizing the evaluation error of the objective function, and dynamically models and comprehensively evaluates the green performance of each stage.

8. A polylactic acid green evaluation system based on life cycle, used to implement the method according to any one of claims 1 to 7, characterized in that: include: Data acquisition module: used to collect monitoring data and working data of the preset polylactic acid during its life cycle, and pre-process the monitoring data and working data; the life cycle includes raw material planting, lactic acid production, PLA polymerization, product manufacturing, circulation and use, waste gas treatment and regeneration cycle stages; Deduction and correction module: used to deduce carbon emissions from the monitoring data based on emission factors to obtain carbon emission data, introduce dynamic genetic self-correction to dynamically correct the carbon emission data, divide the life cycle into multiple decision units according to the working data, and use the carbon emission data as labels for the decision units; Production correlation efficiency module: used to perform input-output correlation analysis based on the decision-making unit and the label to obtain inter-period dependency data, decompose the production process of the decision-making unit into multiple sub-stages, and construct a carbon emission efficiency green evaluation function based on the inter-period dependency data and the sub-stages based on a dynamic network; Modeling output module: used to construct a life cycle polylactic acid green evaluation model according to the carbon emission efficiency green evaluation function, input the data to be evaluated into the life cycle polylactic acid green evaluation model, and output the evaluation results.

Images