Green product full life cycle analysis system based on big data

Abstract

The invention relates to the technical field of green product analysis, and discloses a green product full life cycle analysis system based on big data. The system comprises a data acquisition module, a preprocessing module, an environmental impact assessment module, a resource consumption optimization module, an association modeling and result generation module and a visual interaction module. The system collects data of all stages of a full life cycle and related element data of environment, resources, carbon emission and the like, after preprocessing of abnormal value elimination, entropy weight method weighting and the like, environment influence is dynamically evaluated through a fuzzy membership function, resource consumption is subjected to multi-objective optimization by utilizing a genetic algorithm, and the resource utilization rate is improved. A key stage is determined by means of grey relational degree, an analysis result is generated in combination with a multi-target decision model, and finally the analysis result is visually presented in the form of a three-dimensional map and a dynamic thermodynamic diagram. The system realizes efficient analysis and comprehensive evaluation of full-life-cycle data of green products, and provides scientific support for product environment performance optimization and decision making.

Description

Technical Field

[0001] The present invention relates to the technical field of green product analysis, and in particular to a green product full life cycle analysis system based on big data. Background Art

[0002] As global environmental issues become increasingly severe, the concept of sustainable development has become a global consensus. The research, development, and promotion of green products have become a crucial approach to addressing resource shortages and environmental pollution. Green product lifecycle analysis, a core method for evaluating product environmental performance, aims to comprehensively assess a product's environmental impact and resource consumption throughout its entire lifecycle, from raw material acquisition, production and processing, distribution and sales, use and maintenance, to recycling and disposal. This provides a scientific basis for green product design, production, and management. However, traditional green product lifecycle analysis faces numerous challenges and struggles to meet the current complex demands of environmental governance and industrial upgrading.

[0003] From a data perspective, traditional analytical methods have limited access to data, relying primarily on manual collection and data from a small number of monitoring points. This results in narrow data coverage, poor timeliness, and an inability to fully reflect the true status of each stage of the product's lifecycle. Furthermore, the data types are limited, often focusing only on a few environmental impact factors or resource consumption indicators. They lack comprehensive consideration of multi-dimensional correlated factors, including environmental impact factor data (such as pollutant emission types, emission concentrations, and environmental restoration costs), resource consumption factor data (water consumption intensity, energy consumption intensity, and raw material utilization), carbon emission factor data (direct carbon emissions, indirect carbon emissions, and carbon sink offsets), policy and regulatory factor data, and user behavior factor data. Furthermore, raw data often contains a large number of outliers, noise, and missing values. Traditional data preprocessing methods struggle to efficiently remove outliers, filter noise, and interpolate missing data, and lack a scientific weighting mechanism, significantly compromising the accuracy of subsequent analysis.

[0004] In terms of analytical methods, traditional environmental impact assessments mostly use static assessment models, which are unable to dynamically track changes in environmental impacts at various stages of the product life cycle. For example, pollutant emissions and resource consumption have significant dynamic characteristics at different stages, and traditional models find it difficult to capture these changes in real time and conduct comprehensive assessments. In terms of resource consumption optimization, traditional methods usually only optimize for a single goal, such as simply reducing total resource consumption or reducing carbon emissions, ignoring the need for collaborative optimization among multiple goals, making it difficult to maximize resource utilization efficiency and optimize environmental benefits. In terms of correlation modeling, traditional methods lack correlation analysis of data at various life cycle stages and are unable to accurately identify stages that play a key role in product environmental performance and resource consumption, resulting in a lack of targeted optimization measures.

[0005] From a technical implementation perspective, traditional analysis systems lack deep integration with big data technologies, making them difficult to process massive amounts of data throughout the entire lifecycle. With the development of technologies like the Internet of Things and sensors, the data generated throughout the lifecycle of green products has exploded. Traditional data storage, management, and analysis technologies are insufficient in terms of processing speed and computing power. Furthermore, traditional systems lack interactive visualization capabilities, making it difficult to present complex analysis results in an intuitive and dynamic manner, hindering decision makers' ability to quickly understand and apply analytical findings.

[0006] At the policy level, regulatory requirements for green products are becoming increasingly stringent in various countries. For example, the EU's Ecodesign Directive (ErP) and China's green product certification system require companies to provide detailed environmental impact reports throughout their product lifecycles. Traditional analytical methods, unable to meet regulatory requirements for data comprehensiveness, accuracy, and timeliness, can expose companies to compliance risks. Furthermore, intensified market competition is forcing companies to continuously enhance the green competitiveness of their products. However, traditional analytical methods struggle to provide accurate decision-making support, hindering their ability to innovate in green product R&D and management. Summary of the Invention

[0007] The purpose of the present invention is to provide a green product full life cycle analysis system based on big data to solve the problems raised in the above background technology.

[0008] To achieve the above objectives, the present invention provides the following technical solution: a green product full life cycle analysis system based on big data, the system comprising: Data acquisition module, used to obtain green product life cycle data and related element data; A data preprocessing module performs multi-dimensional preprocessing on the green product life cycle data and associated factor data acquired by the data acquisition module; Environmental impact assessment module, used to dynamically evaluate the environmental impact of green products throughout their life cycle; Resource consumption optimization module, used to perform multi-objective optimization of resource consumption throughout the life cycle of green products; The association modeling and result generation module is used to perform association modeling on data from various stages of the green product life cycle, and generate full life cycle analysis results in combination with a multi-objective decision-making model.

[0009] Preferably, the full life cycle data includes: raw material acquisition stage data, production and processing stage data, circulation and sales stage data, use and maintenance stage data, and recycling and processing stage data; the associated element data includes: environmental impact factor data, resource consumption factor data, carbon emission factor data, policy and regulation factor data, and user behavior factor data; the environmental impact factor data includes: pollutant emission type data, emission concentration data, and environmental restoration cost data.

[0010] Preferably, the multi-dimensional pre-processing of the green product life cycle data and associated factor data acquired by the data acquisition module includes: Eliminate outliers and filter noise from the acquired raw data; Interpolate missing data and assign weights to data based on the entropy weight method; The processed data is divided into raw material acquisition time series, production and processing time series, circulation and sales time series, use and maintenance time series, and recycling and processing time series according to the life cycle stage.

[0011] Preferably, the dynamic assessment of the environmental impact of the green product throughout its life cycle includes: Decompose the environmental impact factor data into resource consumption subsequence, pollution emission subsequence and environmental restoration cost subsequence; Construct a fuzzy membership function to perform fuzzy processing on each subsequence. The calculation formula is: ; in, Indicates the Environmental factors, Indicates the evaluation indicators, Indicates the Under the environmental factors The fuzzy membership of the evaluation indicators, is the fuzzy factor, Indicates the Under the environmental factors The actual measurement value of the evaluation indicator, is the benchmark value; The fuzzy evaluation results are fused through the weighted average operator to generate a comprehensive environmental impact score.

[0012] Preferably, the multi-objective optimization of resource consumption throughout the life cycle of green products includes: The objective function of resource optimization is set as minimizing total resource consumption, maximizing resource utilization efficiency and minimizing carbon emission intensity; Construct chromosome encoding rules and map resource allocation plans to chromosome gene sequences; The chromosome population is iteratively optimized through crossover, mutation, and selection operations until the preset convergence conditions are met.

[0013] Preferably, the correlation modeling of data at each stage of the green product life cycle includes: Extract feature sequences of data at each stage, including raw material acquisition feature sequences, production and processing feature sequences, circulation and sales feature sequences, use and maintenance feature sequences, and recycling and treatment feature sequences; Calculate the grey relational degree between each feature sequence and the target sequence. The calculation formula is: ; in, Indicates the The grey correlation degree between the characteristic sequence of each life cycle stage and the target sequence, Indicates the The absolute difference between the characteristic sequence of each life cycle stage and the target sequence at the corresponding time point, Indicates all The minimum value in Indicates all The maximum value in is the resolution coefficient; Identify key life cycle stages based on relevance ranking.

[0014] Preferably, the multi-objective decision-making model includes: Construct a decision matrix and use environmental impact score, resource optimization plan and grey correlation as decision variables; The ideal point method is used to calculate the closeness of each solution to the ideal solution; The solution with the highest degree of closeness is selected as the optimal full life cycle analysis result.

[0015] Preferably, in the full life cycle data, the data in the raw material acquisition stage include: raw material type data, mining energy consumption data and transportation distance data; the data in the production and processing stage include: process energy consumption data, waste generation data and equipment efficiency data; the data in the circulation and sales stage include: logistics carbon emission data, warehousing cost data and sales channel type data.

[0016] Preferably, the resource consumption factor data include: water resource consumption intensity data, energy consumption intensity data and raw material utilization rate data; the carbon emission factor data include: direct carbon emission data, indirect carbon emission data and carbon sink offset data.

[0017] Preferably, the system further comprises: Visual interaction module, used to visualize the analysis results through three-dimensional maps and dynamic heat maps; In the visualization interaction module, the three-dimensional map includes: a life cycle stage relationship network diagram, a resource consumption intensity distribution diagram and a carbon emission spatiotemporal evolution diagram; a dynamic heat map is used to display the changing trend of environmental impact scores in different regions.

[0018] Compared with the prior art, the present invention has the following beneficial effects: The system's data acquisition module can comprehensively collect data on the entire life cycle of green products and related factor data, covering data from all stages such as raw material acquisition, production and processing, circulation and sales, use and maintenance, and recycling and disposal, while also incorporating multi-dimensional related factor data such as environmental impact, resource consumption, carbon emissions, policies and regulations, and user behavior. This design breaks through the limitations of insufficient data coverage of traditional methods, ensuring that the analysis is based on a complete data source, and providing a solid foundation for subsequent evaluation and optimization. For example, data from the raw material acquisition stage includes details such as raw material type, mining energy consumption, and transportation distance, while the production and processing stage includes indicators such as process energy consumption, waste generation, and equipment efficiency, enabling the system to trace the environmental performance and resource consumption of products from source to terminal.

[0019] The data preprocessing module effectively improves data quality through multi-dimensional processing, including outlier removal, noise filtering, missing data interpolation, and data weight assignment based on the entropy weight method. The removal of outliers and noise prevents false data from interfering with analysis results, while missing data interpolation ensures data integrity. The entropy weight method objectively assigns weights based on the degree of data variation, making it more scientific than traditional subjective weighting methods. The processed data is divided into time series according to the lifecycle stage, providing a standardized and orderly data structure for subsequent dynamic analysis and association modeling. This allows for a clear presentation of the temporal evolution of data at each stage, facilitating analysis of trends and interrelationships across different data stages.

[0020] The environmental impact assessment module dynamically assesses the environmental impact of green products throughout their life cycle by decomposing environmental impact factor data into subsequences of resource consumption, pollution emissions, and environmental restoration costs. It then applies fuzzy membership functions to each subsequence, generating a comprehensive score using a weighted average operator. Fuzzy mathematical methods can effectively address uncertainty and ambiguity in environmental assessments, such as whether pollutant emission concentrations exceed standards or whether environmental restoration costs are reasonable. By calculating fuzzy membership, qualitative issues are quantified, making the assessment results more realistic. The dynamic assessment mechanism can track changes in a product's environmental impact at different stages of its life cycle, promptly identifying environmental risk points and providing real-time feedback for companies to adjust production processes and optimize environmental protection measures.

[0021] The resource consumption optimization module uses the multi-objective goals of minimizing total resource consumption, maximizing resource utilization efficiency, and minimizing carbon emission intensity. It iteratively optimizes resource allocation plans using genetic algorithms' chromosome encoding, crossover, mutation, and selection operations. This multi-objective optimization model overcomes the limitations of traditional single-objective optimization and can find the optimal balance between resource consumption, utilization efficiency, and carbon emissions, achieving a win-win situation for both economic and environmental benefits. For example, by optimizing resource allocation, energy consumption intensity can be reduced while improving raw material utilization, and carbon emissions can be reduced while maintaining production efficiency, making a company's resource utilization more scientific and efficient.

[0022] The correlation modeling and result generation module can accurately identify the life cycle stages that play a key role in the environmental impact and resource consumption of products by extracting the characteristic sequences of data at each stage and calculating the grey correlation degree. The grey correlation analysis method is suitable for complex system analysis with small samples and multiple factors, and can reveal the degree of correlation between factors without a large amount of historical data. By determining the key stages, companies can focus their optimization resources on the links that have the greatest impact on the green performance of products. If the resource consumption in the raw material acquisition stage has the highest correlation with the target sequence, then the energy consumption in the raw material mining and transportation process should be optimized first to improve the pertinence and effectiveness of the optimization measures. The multi-objective decision-making model constructs a decision matrix and adopts the ideal point method to select the optimal solution. It comprehensively considers multi-dimensional indicators such as environmental impact score, resource optimization plan and grey correlation degree to ensure the scientific nature and reliability of the final analysis results, providing companies with a comprehensive and objective decision-making basis.

[0023] The interactive visualization module presents analysis results intuitively through three-dimensional graphs (such as a life cycle phase relationship network diagram, a resource consumption intensity distribution diagram, and a spatiotemporal carbon emission evolution diagram) and dynamic heat maps. The three-dimensional graphs provide a three-dimensional representation of the interrelationships between life cycle phases, the spatial distribution of resource consumption, and the temporal evolution of carbon emissions. The dynamic heat maps display real-time changes in environmental impact scores across different regions, making complex analysis results easier to understand and interpret. This visualization approach not only allows business managers to quickly grasp the green performance of their products but also provides intuitive decision-making references for policymakers, promoting the scientific formulation and effective implementation of green product-related policies.

[0024] Furthermore, the system, based on a big data technology architecture, boasts powerful data storage, processing, and computing capabilities, enabling it to efficiently handle massive amounts of full-lifecycle data and meet the demands of real-time analysis and dynamic assessment. Furthermore, the system can flexibly adjust assessment indicators and optimization targets based on evolving policies, regulations, and market demand. Its strong adaptability and scalability provide strong technical support for the continuous improvement of green products and industrial upgrading, helping to achieve the coordinated advancement of economic development and environmental protection. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 This is a working principle diagram of the green product full life cycle analysis system based on big data according to the present invention; Figure 2 Schematic diagram of the data preprocessing process; Figure 3 Flowchart for dynamic environmental impact assessment; Figure 4 Schematic diagram of the grey relational analysis process. DETAILED DESCRIPTION

[0026] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0027] See also Figures 1-4 The present invention provides a green product full life cycle analysis system based on big data, the system comprising: Data Acquisition Module: This module is used to acquire green product lifecycle data and associated factor data. The full lifecycle data covers raw material acquisition, production and processing, distribution and sales, use and maintenance, and recycling and disposal. Associated factor data includes environmental impact factors, resource consumption factors, carbon emissions factors, policy and regulatory factors, and user behavior factors.

[0028] Data preprocessing module: This module performs multi-dimensional preprocessing on the acquired full lifecycle data and associated factor data. This includes removing outliers and filtering noise from the raw data, interpolating missing data, assigning weights to the data based on the entropy weight method, and categorizing the processed data into time series based on the lifecycle stages: raw material acquisition, production and processing, distribution and sales, use and maintenance, and recycling and disposal.

[0029] Environmental impact assessment module: Dynamically assess the environmental impact of green products throughout their life cycle.

[0030] Resource consumption optimization module: multi-objective optimization of resource consumption throughout the life cycle of green products.

[0031] Association modeling and result generation module: performs association modeling on data from each stage of the green product life cycle, and generates full life cycle analysis results in combination with a multi-objective decision-making model.

[0032] The present invention will be further described below in conjunction with Examples 1 to 5: Example 1:

[0033] The data acquisition module of the system needs to realize the comprehensive collection of green product life cycle data and related factor data. The full life cycle data covers the complete chain of the product from raw material acquisition to recycling and processing: the data of the raw material acquisition stage includes the type of raw materials (such as metals, plastics, glass and other different material categories), the energy consumption of the mining process (such as the electricity and fuel consumed by the operation of mining equipment), and the transportation distance (the transportation distance of raw materials from the mining site to the production plant); the data of the production and processing stage involves the energy consumption of the production process (such as the power consumption of production line equipment, the energy loss of heating or cooling process), the amount of waste generated (the amount of scraps, wastewater, exhaust gas and other wastes generated during the production process), equipment efficiency (the operating time of production equipment, the output per unit time, the failure rate, etc.); the data of the circulation and sales stage includes the carbon emissions of the logistics link (transportation Carbon emissions converted from vehicle fuel consumption), warehousing costs (warehouse rental fees, storage equipment energy consumption costs, inventory management costs, etc.), sales channel types (online e-commerce platforms, offline physical stores, dealer distribution and other different sales models); data from the use and maintenance stage include the frequency of user use of the product (such as daily and weekly usage time), maintenance operation records (maintenance cycles, replacement of parts), energy consumption (electricity or fuel consumption during product operation); data from the recycling and processing stage covers the recovery rate of waste products (the proportion of recycled volume to scrapped volume), treatment methods (reuse, remanufacturing, resource processing or harmless disposal), and energy consumption during the processing process (energy consumption in recycling sorting, disassembly, regeneration processing and other links).

[0034] The associated factor data needs to collect multiple types of influencing factors: environmental influencing factor data include pollutant emission types (such as sulfur dioxide, nitrogen oxides, heavy metal ions and other specific pollutant types), emission concentration (the content of pollutants per unit volume or unit mass), and environmental restoration costs (the capital investment required for pollution control and ecological restoration); resource consumption factor data include water resource consumption intensity (the amount of water consumed during the production or use of a unit product), energy consumption intensity (the amount of standard coal consumed per unit output value or unit product), and raw material utilization rate (the ratio of the actual amount of raw materials put into production to the total amount of raw materials purchased); carbon emission factor data include direct carbon emissions (product production, transportation, use, etc. Data on policy and regulatory factors include carbon dioxide emissions directly generated by the production process, indirect carbon emissions (such as carbon emissions generated by upstream links such as raw material production and power supply), and carbon sink offsets (carbon emissions offset by carbon sink projects such as afforestation). Data on policy and regulatory factors include national and local environmental protection standards (such as pollutant emission standards and energy consumption limit standards), resource utilization specifications (such as raw material recycling policies and waste management regulations), and green product certification systems. Data on user behavior factors include user usage habits of the product (such as whether the product is frequently turned on and off, and whether there is excessive packaging demand), maintenance preferences (self-maintenance or professional maintenance), and scrapping disposal choices (actively sending the product to a recycling point or discarding it at will).

[0035] The data acquisition module collects data through multiple channels: for equipment operation data in the production and processing stages, sensors (such as current sensors, temperature sensors, flow meters, etc.) are installed on the production equipment to collect data in real time and transmit them to the system; for data in the raw material acquisition and circulation and sales stages, procurement records, transportation orders, warehousing data, etc. are obtained by connecting to the company's supply chain management system (such as the ERP system); data related to environmental impact and resource consumption are obtained from industry databases (such as the pollutant emission data platform and energy statistical yearbook disclosed by the environmental protection department) and government public data platforms (such as the Ministry of Ecology and Environment Data Center and the National Bureau of Statistics Data Release System); user behavior data is collected through user operation logs through built-in smart terminals in the product (such as the networking module of smart home appliances), or obtained through questionnaires, user feedback platforms, etc.

[0036] The data preprocessing module performs multi-dimensional processing on the collected raw data. First, outlier removal and noise filtering are performed: statistical analysis methods are used to identify abnormal data points. For example, through the box plot detection method, data that exceeds 1.5 times the interquartile range is considered as outliers and eliminated; the sliding average filter algorithm is used to smooth the time series data to reduce the interference of random noise on the data. For missing data, the interpolation strategy is selected according to the data type and the degree of missingness: if the raw material procurement volume data is missing in a certain time period, and the data has temporal continuity, the average value of the adjacent time periods is used for linear interpolation; if the user maintenance habit data is a categorical missing value, the common maintenance methods of users of this type of product are counted and the mode is used for interpolation.

[0037] After data cleaning is completed, the data is weighted based on the entropy weight method. The core logic of the entropy weight method is to measure the information value of each indicator by calculating its information entropy. The smaller the information entropy of the indicator, the greater the degree of data variation and the higher the weight of its impact on the analysis results. The specific operation steps are: first, standardize the data of each indicator to eliminate dimensional differences; then calculate the information entropy of each indicator. The formula is: (in For the In the sample The proportion of indicators, ); Finally, the weight is calculated based on the information entropy: , thereby determining the importance ranking of each data indicator in subsequent analysis.

[0038] The final step in data preprocessing is to divide the data into time series by lifecycle stage. Data from the raw material acquisition stage (e.g., raw material purchase types, corresponding mining energy consumption, and transportation distances by month) are organized chronologically into a raw material acquisition time series. Data from the production and processing stage, such as process energy consumption, waste generation, and equipment efficiency, are organized into a production and processing time series by production batch or date. Data from the distribution and sales stage, such as logistics carbon emissions, warehousing costs, and sales channels, are organized into a distribution and sales time series by sales cycle (e.g., monthly or quarterly). Data from the maintenance stage, such as user usage frequency, energy consumption, and maintenance records, are organized into a maintenance time series by user timeline. Data from the recycling and disposal stage, such as recovery rate, disposal method, and disposal energy consumption, are organized into a recycling and disposal time series by recycling batch or year. Through this processing, the previously scattered raw data is transformed into a structured, time-series dataset, providing standardized input data for the environmental impact assessment module, resource consumption optimization module, and association modeling module. This ensures that each module can perform analysis based on a unified, clean data foundation, improving the accuracy and reliability of the overall system analysis results.

[0039] Example 2: After the data preprocessing module completes multi-dimensional preprocessing of green product lifecycle data and associated factor data, the environmental impact assessment module performs a dynamic assessment of the environmental impact of the green product throughout its lifecycle. This assessment process, based on the structured time series data output by the data preprocessing module, achieves a quantitative analysis of the environmental impact of the product throughout its lifecycle through decomposition, fuzzification, and comprehensive scoring of environmental impact factor data.

[0040] The environmental impact assessment module decomposes environmental impact factor data into three subsequences: a resource consumption subsequence, a pollution emission subsequence, and an environmental restoration cost subsequence. The resource consumption subsequence covers various data related to resource utilization, such as mining energy consumption during the raw material acquisition stage, process energy consumption during the production and processing stage, and energy consumption during the use and maintenance stage. The pollution emission subsequence includes data related to pollutants generated during each life cycle stage, such as the concentration of exhaust gas emissions during the production and processing stage, the amount of pollutant emissions from logistics activities during the circulation and sales stage, and the types of wastewater emissions during the recycling and treatment stage. The environmental restoration cost subsequence involves cost data required to reduce or eliminate environmental impacts, such as the cost of controlling pollutant emissions during the production process and the cost of repairing ecological damage caused by product disposal. Through this decomposition process, complex environmental impact factor data is divided into more targeted dimensions, facilitating subsequent refined analysis.

[0041] The module needs to construct a fuzzy membership function to fuzzify each subsequence. The role of the fuzzy membership function is to convert the actual measured value of a specific evaluation indicator into a fuzzy membership that can reflect the degree of its impact on the environment, solving the uncertainty and ambiguity problems in environmental impact assessment. Take an evaluation indicator under a certain type of environmental impact factor as an example. Suppose that the indicator is the concentration of a pollutant emission in the production and processing stage, and its actual measured value is , the benchmark value is (The benchmark value can refer to the pollutant emission standards formulated by the country or industry, the average emission level of similar products or the environmental protection goals set by the enterprise), fuzzy factor It is determined based on the characteristics of the indicator and historical data experience and is used to adjust the shape and sensitivity of the membership function. ; Calculate the fuzzy membership of the indicator , its value range is arrive When the actual measured value Equal to the baseline value When , the fuzzy membership is , indicating that the impact of this indicator on the environment is in an ideal state; with Deviation from baseline As the degree of fuzzy membership increases, it gradually decreases, indicating that the degree of environmental impact increases. For example, if the baseline value of a pollutant emission concentration is When the actual measured value is lower than the benchmark value, it means that the emission situation is better than the standard, and the fuzzy membership is close to or equal to When the actual measured value exceeds the benchmark value, the greater the excess, the smaller the fuzzy membership, which reflects that the negative impact of the indicator on the environment is greater.

[0042] For indicators in the resource consumption subsequence, such as process energy consumption in the production and processing stage, the benchmark value It can be set to the industry average energy consumption level or the energy consumption limit set by the enterprise, the actual measured value is the actual energy consumption data of this stage. Through the fuzzy membership function calculation, the lower the energy consumption index is, the higher the fuzzy membership degree will be, indicating that its resource utilization efficiency is higher and its positive impact on the environment is greater; conversely, the higher the energy consumption index is, the lower the fuzzy membership degree will be, reflecting greater resource waste and environmental pressure. In the environmental restoration cost subsequence, the baseline value is The actual measured value can be determined based on the historical cost data of similar environmental governance projects or the industry average cost level. The cost of restoring the environmental impacts of this product lifecycle stage is calculated. Lower cost indicators have higher fuzzy membership, indicating lower difficulty and cost of environmental restoration and a relatively low overall environmental impact. Higher cost indicators have lower fuzzy membership, indicating more severe environmental damage and complex and costly restoration.

[0043] After fuzzifying all evaluation indicators in each subsequence, the environmental impact assessment module combines the fuzzy evaluation results using a weighted average operator to generate a comprehensive environmental impact score. This weighted average operator is calculated in conjunction with the weights for each indicator determined using the entropy weighting method in the data preprocessing module. The entropy weighting method analyzes the degree of data variation to assign objective weights to each evaluation indicator, eliminating the subjectivity of manually set weights. For example, if a pollutant emission concentration indicator in the pollution emission subsequence receives a high weight calculated using the entropy weighting method during the data preprocessing phase, this indicator is important in the environmental impact assessment, and its fuzzy membership degree accounts for a significant portion of the comprehensive score. The specific fusion process involves multiplying the fuzzy membership degree of each evaluation indicator by its corresponding weight to obtain a weighted value for that indicator. The weighted values ​​of all indicators are then summed to produce a comprehensive environmental impact score. This score is a comprehensive quantitative indicator that comprehensively reflects the overall environmental impact of a green product throughout its life cycle. The higher the score, the better the product's environmental performance and the smaller its environmental impact; the lower the score, the heavier the burden the product places on the environment during production, circulation, use and recycling, requiring targeted improvement and optimization.

[0044] In actual operation, the environmental impact assessment module will conduct an environmental impact assessment for each life cycle stage of green products, generate an environmental impact score for each stage, and also conduct a comprehensive assessment of the environmental impact of the entire life cycle. For example, in the raw material acquisition stage, the impact of indicators such as mining energy consumption and transportation distance on the environment is assessed to generate an environmental impact score for that stage; in the production and processing stage, indicators such as process energy consumption, waste generation, and pollutant emission concentration are assessed to obtain a score for that stage; by analyzing the scores of each stage, it is possible to locate key stages with greater environmental impact, providing a basis for subsequent resource consumption optimization and life cycle stage correlation modeling. In addition, the module can also conduct dynamic comparative analysis of environmental impacts in different time periods based on time series data, such as comparing the changing trends of environmental impacts of products in different production batches and different years, so as to promptly discover fluctuations or improvement effects in environmental performance, and provide data support for enterprises to adjust production processes, optimize supply chain management, and formulate environmental protection strategies.

[0045] The dynamic assessment process of the environmental impact assessment module has the following characteristics: First, it is data-driven, and the analysis is based entirely on the real data collected by the data acquisition module and the results processed by the data preprocessing module, ensuring the objectivity and credibility of the assessment results; second, it is multi-dimensional and comprehensive, and the assessment system is constructed from three dimensions: resource consumption, pollution emissions, and environmental restoration costs, comprehensively covering the main aspects of environmental impact; third, it is dynamic and adaptable, and can continuously assess environmental impacts according to the advancement of the product life cycle and the real-time update of data, and promptly reflect the changes in the environmental performance of products at different stages. Through the operation of this module, the system can provide a scientific basis for environmental impact assessment for the design, production, circulation, use and recycling of green products, helping enterprises achieve green development goals and promote the formation of sustainable production and consumption patterns.

[0046] Example 3: The Resource Consumption Optimization module performs multi-objective optimization of resource consumption throughout the green product lifecycle. Its core approach is to iteratively optimize resource allocation plans by setting multi-objective functions, constructing chromosome encoding rules, and executing genetic algorithm operations. This process, based on the structured data output by the Data Preprocessing Module, incorporates the resource consumption characteristics of green products across the stages of raw material acquisition, production and processing, distribution and sales, maintenance, and recycling to develop a scientific optimization strategy.

[0047] The module needs to set the objective function of resource optimization, specifically including minimizing total resource consumption, maximizing resource utilization efficiency, and minimizing carbon emission intensity. Minimizing total resource consumption aims to reduce the total input of various resources (such as water, energy, and raw materials) throughout the product life cycle, and reduce unnecessary resource waste by optimizing resource allocation in procurement, production, transportation, and other links; maximizing resource utilization efficiency focuses on improving resource conversion efficiency, such as increasing the utilization rate of raw materials and reducing the energy consumption ratio of production equipment, so that unit resource input can produce more products or services; minimizing carbon emission intensity is to reduce carbon emissions per unit product or unit output value by optimizing energy structure and improving production processes, in line with low-carbon development goals. These three objective functions are interrelated and mutually constrained, and together constitute the core framework of multi-objective optimization, aiming to achieve a balance between the economic and environmental benefits of resource utilization.

[0048] The module constructs chromosome encoding rules, mapping resource allocation plans to chromosome gene sequences. In genetic algorithms, chromosomes are encoded representations of the solution to an optimization problem. Real-number encoding is used here, with each gene bit corresponding to a resource allocation variable. For example, in the raw material acquisition phase, gene bits could correspond to the procurement quantities of different raw materials or the energy consumption quotas for mining equipment. In the production and processing phase, gene bits could represent energy consumption thresholds for production processes and waste recycling ratio parameters. In the distribution and sales phase, gene bits could involve the selection of logistics transportation routes (encoded by mileage or carbon emission coefficients) and energy management parameters for storage facilities. In the maintenance phase, gene bits could represent parameter values ​​for optimizing product energy consumption. In the recycling phase, gene bits could correspond to energy consumption control indicators for the waste product disassembly process and recycled material utilization targets. This encoding method transforms complex resource allocation plans into computable and actionable chromosome gene sequences, providing a foundation for subsequent genetic algorithm operations.

[0049] After completing the chromosome encoding, the module iteratively optimizes the chromosome population through crossover, mutation, and selection operations. Crossover operation is the main way to generate new individuals in genetic algorithms. It generates daughter chromosomes by exchanging some genes of two parent chromosomes. In the specific operation, first randomly select two parent chromosomes in the population, then randomly determine the location of the crossover point, and exchange the gene segments of the parent chromosomes on both sides of the crossover point to form two new daughter chromosomes. For example, suppose the parent chromosome The gene sequence is , the parent chromosome The gene sequence is , if the intersection point is determined to be gene positions, the offspring chromosomes generated after crossover The gene sequence is , daughter chromosomes The gene sequence is The crossover operation can make full use of the excellent gene combination of the parent chromosomes to produce offspring individuals with stronger adaptability.

[0050] Mutation is a method used in genetic algorithms to introduce new mutant individuals. By randomly changing the value of a gene bit on a chromosome, the population's local optimum is disrupted, maintaining diversity. The mutation operation involves randomly selecting a chromosome, randomly determining the gene bit to mutate, and then randomly generating a new value within the value range of that gene bit to replace the original value. For example, if the gene bit representing the energy consumption threshold of a production process on a chromosome originally had a value of 500kWh and its value range is 300-800kWh, the value of that gene bit might change to 650kWh after mutation. The probability of mutation is typically low, typically between 0.1% and 1%, to avoid excessive mutations that could slow algorithm convergence or destroy optimal genetic structure.

[0051] The selection operation is the survival of the fittest mechanism in the genetic algorithm. Each chromosome in the population is evaluated through the fitness function, and individuals with higher fitness are selected to enter the next generation of the population, while individuals with lower fitness are eliminated. The fitness function is constructed based on the set objective function and has the following form: ; in, represents the fitness value of the chromosome, are the weight coefficients of the three objective functions of minimizing total resource consumption, maximizing resource utilization efficiency, and minimizing carbon emission intensity, and satisfy The value of the weight coefficient is determined according to the actual needs of the enterprise and policy orientation. For example, when the enterprise focuses on low-carbon development, it can appropriately increase The weight of is the normalized value of the total resource consumption (by mapping the actual total resource consumption to The smaller the value, the less total resource consumption). is the normalized value of resource utilization efficiency (a larger value indicates a higher resource utilization efficiency), is the normalized value of carbon emission intensity (smaller values ​​indicate lower carbon emission intensity). By calculating the fitness function, we can quantify the quality of the resource allocation solution represented by each chromosome, ensuring that the population evolves towards a more optimal solution.

[0052] During the iterative optimization process, the module first randomly generates an initial chromosome population. The population size is typically set to 50-200 individuals to balance computational efficiency and search space. The module then performs a fitness calculation on each chromosome in the initial population. A selection operation is performed based on the fitness value, retaining individuals with higher fitness as parents. Crossover and mutation operations are then performed on the parent individuals to generate a daughter population. Fitness calculation, selection, crossover, and mutation operations are then repeated on the daughter population, repeating this cycle until the preset convergence criteria are met. Convergence criteria typically include reaching a set number of iterations (e.g., 100 or 200 generations) or the fitness value not changing significantly over several consecutive generations (e.g., the fitness value changes by less than 0.1% over 10 consecutive generations).

[0053] During resource consumption optimization, the module must consider the resource association characteristics between different lifecycle stages. For example, the purchase volume during the raw material acquisition stage directly affects the raw material inventory and production plan during the production and processing stage, which in turn affects energy consumption and waste generation during the production stage. The logistics route selection during the distribution and sales stage not only affects carbon emissions during transportation but may also affect resource consumption during the warehousing stage through inventory strategies. Therefore, in chromosome encoding and genetic algorithm operations, it is necessary to ensure logical consistency and constraint compatibility between resource allocation variables at each stage to avoid conflicting resource allocation plans (such as situations where the raw material purchase volume is insufficient to support the production plan).

[0054] Furthermore, the module must address conflicts in multi-objective optimization. For example, minimizing total resource consumption and maximizing resource efficiency may create synergistic effects, while minimizing carbon emission intensity may require increased investment in low-carbon technologies, thereby increasing total resource consumption to a certain extent. By adjusting the weight coefficients of the objective function and the operating parameters of the genetic algorithm, the module can balance different objectives and generate a set of Pareto optimal solutions that meet specific requirements, allowing decision makers to select the optimal solution based on the actual situation.

[0055] The operation of the resource consumption optimization module relies on accurate data and weighting information provided by the data preprocessing module. For example, the weights of resource consumption factors (such as water consumption intensity and energy consumption intensity) determined by the entropy weight method will influence the importance of each objective function in the fitness function, thereby guiding the genetic algorithm to optimize towards higher-weighted indicators. Furthermore, the optimization solutions generated by the module (such as resource allocation parameters, energy consumption thresholds, and carbon emission control targets for each stage) will serve as input data for the association modeling and result generation module, used to generate full lifecycle analysis results and make decisions.

[0056] Example 4: The Association Modeling and Result Generation module performs association modeling on data from each stage of the green product lifecycle. This aims to identify the key lifecycle stages that contribute to a product's environmental impact and resource consumption by exploring the inherent connections between these data stages. This process, based on the time series data output by the Data Preprocessing module, achieves in-depth analysis of the full lifecycle data through three core steps: feature sequence extraction, grey correlation calculation, and key stage identification.

[0057] The module extracts characteristic sequences from data from each stage of a green product's lifecycle. Feature sequence extraction involves filtering out key variables from the raw data that effectively reflect the core attributes and patterns of change at each stage, thereby reducing data dimensionality and highlighting key information. Specifically, feature sequence extraction in the raw material acquisition stage focuses on data such as raw material type, mining energy consumption, and transportation distance. Using dimensionality reduction techniques such as principal component analysis (PCA), this multidimensional data is transformed into a few comprehensive indicators. For example, the principal component of "resource acquisition intensity" (combining mining energy consumption and transportation distance) and the "raw material diversity" indicator are extracted. In the production and processing stage, "production efficiency characteristics" (such as unit product energy consumption and equipment failure rate) and "environmental load characteristics" (waste generation density) are extracted from data such as process energy consumption, waste generation, and equipment efficiency. Feature sequences in the distribution and sales stage include logistics carbon emission intensity, warehousing cost ratio, and sales channel response speed. In the maintenance stage, features such as user usage frequency, maintenance cost ratio, and energy consumption volatility are extracted. In the recycling and processing stage, key indicators such as recovery rate, processing energy intensity, and recycled material utilization rate are extracted. The extraction of feature sequences needs to be combined with industry characteristics and product features, and the core feature variables of each stage should be determined through data mining algorithms or expert experience to ensure that the extracted feature sequences can accurately characterize the main attributes of the corresponding stage.

[0058] After completing the feature sequence extraction at each stage, the module needs to calculate the grey correlation between each feature sequence and the target sequence. Grey correlation analysis is a method used to measure the degree of correlation between sequences. It is suitable for system analysis with small amounts of data and incomplete information. The target sequence can be set according to the analysis requirements. For example, the comprehensive score of the environmental impact of the entire life cycle can be used as the target sequence, or a single indicator such as total resource consumption or carbon emission intensity can be selected as the target sequence. The calculation formula for grey correlation is: ; in, Indicates the The grey correlation degree between the characteristic sequence of each life cycle stage and the target sequence is in the range of arrive The larger the value, the higher the degree of correlation; For the The absolute difference between the characteristic sequence of each life cycle stage and the target sequence at the corresponding time point reflects the degree of local difference between the two. For all The minimum value in represents the minimum difference between the feature sequence and the target sequence at each stage; For all The maximum value in represents the maximum difference; is the resolution coefficient, and its value range is usually arrive , used to adjust the resolution of difference information, generally To balance resolution and data stability.

[0059] Take the calculation of the correlation between the characteristic sequence of the raw material acquisition stage and the comprehensive scoring target sequence of the whole life cycle environmental impact as an example: Assume that at a certain time point , the characteristic value of “resource acquisition intensity” in the raw material acquisition stage is , the environmental impact score of the target sequence is , then the absolute difference at that time point Traverse all time points and calculate the absolute difference sequence between the feature sequence of this stage and the target sequence , and then determine and . Substitute into the formula to get the grey relational degree of this stage Similarly, the grey correlation between the characteristic sequence and the target sequence in the production and processing, circulation and sales, use and maintenance, and recycling stages can be calculated. .

[0060] In the process of calculating grey relational degree, it is necessary to pay attention to the dimensionless processing of data. Since the indicator dimensions of the characteristic sequence and the target sequence at each stage may be different (such as energy consumption in kWh, cost in yuan, and score in dimensionless numbers), directly calculating the absolute difference will cause the result to be affected by the dimension. Therefore, all sequences need to be standardized before calculation. Common methods include initialization method (dividing each data in the sequence by the first data), averaging method (dividing each data in the sequence by the mean), or normalization method (mapping the data to the interval), to ensure that indicators of different dimensions are comparable.

[0061] After completing the grey correlation calculation for each stage, the module sorts them according to the correlation value to determine the key life cycle stage. The correlation sorting results can intuitively reflect the degree of influence of each stage on the target sequence: the stage with the highest correlation indicates that the change trend of its feature sequence is most consistent with that of the target sequence, and its influence on the target is the most significant, which is the key life cycle stage. For example, if the grey correlation of the production and processing stage is The largest value indicates that the characteristics of this stage (such as process energy consumption and waste generation) are most closely linked to the environmental impact or resource consumption of the entire life cycle, making it a key link influencing the green performance of the product. After identifying the key stage, companies can focus on optimizing it, such as improving production processes to reduce energy consumption and increasing waste recycling rates, thereby more effectively improving the overall environmental performance and resource utilization efficiency of the product.

[0062] In practical applications, the association modeling process needs to consider multi-objective association analysis. For example, when using environmental impact score, total resource consumption, and carbon emission intensity as multiple target sequences, the module needs to calculate the gray correlation between the characteristic sequence of each stage and each target sequence separately to form a correlation matrix. By comprehensively analyzing the correlation ranking under each target, the key stages under different dimensions are determined, providing a more comprehensive basis for multi-objective optimization. For example, the key stage of a product under the environmental impact dimension is the production and processing stage, while the key stage under the resource consumption dimension is the raw material acquisition stage. Enterprises can develop phased optimization strategies based on the priority of different goals.

[0063] Furthermore, grey correlation analysis is dynamic, calculating the correlation between each phase in real time based on updated time series data, reflecting key changes in different stages of the product lifecycle. For example, when product upgrades significantly reduce energy consumption during the maintenance phase, the correlation between that phase and the environmental impact target sequence may decrease. However, the correlation between the production and processing phase and the introduction of new processes may increase. The module can promptly capture these changes and provide support for companies to dynamically adjust their management strategies.

[0064] The results of association modeling serve as one of the inputs to the multi-objective decision-making model. In the association modeling and result generation module, the gray correlation values ​​at each stage, along with data such as environmental impact scores and resource optimization plans, form a decision matrix. Using multi-objective decision-making methods such as the ideal point method, the full life cycle analysis results are ultimately generated. Therefore, the accuracy of association modeling directly impacts the scientific nature of decision-making, ensuring the rationality of feature sequence extraction, standardized data preprocessing, and accurate gray correlation calculation.

[0065] Example 5: The multi-objective decision-making model within the Correlation Modeling and Result Generation module integrates the results of environmental impact assessment, resource consumption optimization, and correlation modeling to form a final full lifecycle analysis plan. This process, based on the quantitative data output by each module, transforms multi-dimensional data into scientific decision-making by constructing a decision matrix, calculating the closeness of solutions, and selecting the optimal solution. The following details the implementation method using specific examples.

[0066] Suppose the full life cycle analysis of a green home appliance involves three different design options (Option A, Option B, and Option C). Each option exhibits different performance in terms of environmental impact, resource consumption, and phase correlation. The multi-objective decision model first requires the construction of a decision matrix, using environmental impact scores, resource optimization indicators (such as total resource consumption, resource utilization efficiency, and carbon emission intensity), and gray correlation as decision variables. For example: Environmental impact score: Calculated through the Environmental Impact Assessment Module, Plan A scored 85 points, Plan B scored 78 points, and Plan C scored 90 points (a higher score indicates a lower environmental impact).

[0067] Resource optimization indicators: Total resource consumption (unit: tons of standard coal): Plan A is 1200, Plan B is 1150, and Plan C is 1300; Resource utilization efficiency (percentage): Plan A is 75%, Plan B is 82%, and Plan C is 70%; Carbon emission intensity (unit: kg / 10,000 yuan output value): Plan A is 450, Plan B is 420, and Plan C is 480.

[0068] Grey correlation degree: Taking the environmental impact of the entire life cycle as the target sequence, the mean correlation degree of the characteristic sequence of each stage in each scheme is calculated. The mean correlation degree of scheme A is 0.72, that of scheme B is 0.68, and that of scheme C is 0.75 (the higher the correlation degree, the stronger the correlation between the stages).

[0069] The above data was organized into a decision matrix, with the decision variables listed horizontally (six items in total: environmental impact score, total resource consumption, resource utilization efficiency, carbon emission intensity, and gray correlation), and the options listed vertically (three rows). Because different variables have different dimensions and trends (for example, the environmental impact score is a positive indicator, with higher values ​​being preferred; total resource consumption is a negative indicator, with lower values ​​being preferred), the data must first be normalized to eliminate dimensional differences. For example, negative indicators such as total resource consumption and carbon emission intensity can be converted to positive indicators by taking their reciprocals or normalizing them to their maximum values, ensuring that all variables have the same direction (higher values ​​are preferred).

[0070] After standardization, the ideal point method is used to calculate the closeness of each option to the ideal solution. The ideal solution is the optimal value combination of each variable in the decision matrix (such as the standardized value corresponding to the maximum environmental impact score of 90, the minimum total resource consumption of 1150, the standardized value corresponding to the maximum resource utilization efficiency of 82%, the standardized value corresponding to the minimum carbon emission intensity of 420, and the maximum gray correlation of 0.75). The negative ideal solution is the worst value combination of each variable. The Euclidean distance between each option and the ideal solution and the negative ideal solution is calculated. The closeness formula is: ; The closeness value range is [0,1], and the larger the value, the closer the solution is to the ideal solution.

[0071] Taking Option A as an example, calculate its distance from the ideal solution (e.g., the square root of the sum of the squared difference between the environmental impact score and 90, the square root of the difference between the standardized total resource consumption value and the corresponding optimal value, and so on), and its distance from the negative ideal solution (the square root of the sum of the squared difference between each value and the worst value). Substitute these into the formula to obtain the closeness value. Similarly, calculate the closeness of Options B and C. Assuming the calculated closeness is 0.65 for Option A, 0.78 for Option B, and 0.59 for Option C, Option B has the highest closeness and is selected as the optimal option.

[0072] In practice, the weighting of decision variables must be combined with the results of the entropy weighting method in the data preprocessing module. For example, if the environmental impact score is weighted 0.3, total resource consumption is weighted 0.2, resource utilization efficiency is weighted 0.2, carbon emission intensity is weighted 0.2, and the gray correlation is weighted 0.1, then the difference between the variables should be weighted when calculating the distance to emphasize the influence of the higher-weighted indicators on the decision. For example, although Option B has a lower environmental impact score than Option C, its total resource consumption and carbon emission intensity perform better, and the resource-related indicators are weighted more highly, resulting in a higher overall degree of closeness.

[0073] The following points should be noted when applying the multi-objective decision-making model: Comprehensiveness of decision variables: The core outputs of each module of the system must be covered, such as the comprehensive score of the environmental impact assessment module, the multi-objective solution of the resource consumption optimization module (total resource consumption, utilization efficiency, carbon emission intensity), and the grey correlation degree of the association modeling module, to ensure that decisions are based on multi-dimensional analysis of the entire life cycle.

[0074] Accuracy of data normalization: Dimensional differences between different variables can lead to decision bias, so appropriate normalization methods should be selected based on the nature of the variables. For example, scoring variables can be directly normalized, while physical dimension variables (such as energy consumption and emissions) require normalization using extreme value methods or Z-score methods.

[0075] Objectivity in weighting: Data-driven weighting methods, such as the entropy weighting method, are used to avoid the subjectivity of manually setting weights. For example, if the data during the raw material acquisition phase of a product exhibits significant variability (e.g., significant differences in mining energy consumption between different suppliers), the entropy weighting method for the correlation indicator at that phase may be higher, giving it a more significant role in decision-making.

[0076] To illustrate, consider another example: an automobile manufacturer analyzed its full lifecycle plans for electric vehicles. The decision variables included a "policy and regulatory compliance score" (e.g., compliance with new energy subsidy policies and carbon emission regulations) and a "user behavior impact index" (e.g., the impact of user charging frequency on battery life). When constructing the decision matrix, these two new variables were incorporated, and the standardized values ​​and closeness scores were recalculated. If Plan D had the highest policy and regulatory score (due to compliance with the latest subsidy policies) and the best user behavior impact index (due to high compatibility with charging facilities), even if its total resource consumption was slightly higher than Plan E, it could still be the optimal solution due to the high weighting of the policy and user dimensions, demonstrating the decision model's adaptability to external factors.

[0077] The optimal solution generated by the decision-making model must be fed back to each module for verification. For example, if the key lifecycle stage of the optimal solution is the production and processing stage (based on the results of the correlation modeling), the resource consumption optimization module must be checked for reasonable energy consumption thresholds for that stage, and the environmental impact assessment module must be checked for comprehensive assessment of pollution emission indicators for that stage. If data is found to be missing in the logistics carbon emissions calculations of a particular solution during the distribution and sales stage, the data acquisition module must be returned to collect additional data on transportation routes, vehicle types, and other aspects of that stage, and re-preprocessing and analysis must be performed to ensure the integrity of the decision-making basis.

[0078] Visual interaction modules play a key role in this process. For example, they present each variable in the decision matrix as a dynamic heat map, contrasting the performance of different options with different color shades (e.g., green for superior, red for inferior), helping decision makers quickly identify the strengths and weaknesses of each option. A three-dimensional lifecycle phase relationship network diagram reveals the strength of the correlation between each phase in the optimal solution (e.g., a thicker line connecting the production and processing and recycling stages indicates significant synergistic optimization between the two), providing intuitive guidance for solution implementation.

[0079] Another characteristic of the multi-objective decision-making model is its iterative nature. As the product lifecycle progresses (for example, after entering the sales phase, actual user behavior data is collected), the variable values ​​in the decision matrix can be updated, the closeness can be recalculated, and the optimal solution can be dynamically adjusted. For example, if a home appliance product is found to have higher energy consumption than the design expectations after launch, resulting in an increase in the gray correlation degree during the maintenance phase, the closeness of each solution needs to be reassessed, potentially triggering optimization of the energy-saving design during the use phase.

[0080] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "includes," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0081] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A green product life cycle analysis system based on big data, characterized by: include: Data acquisition module, used to obtain green product life cycle data and related element data; A data preprocessing module performs multi-dimensional preprocessing on the green product life cycle data and associated factor data acquired by the data acquisition module; Environmental impact assessment module, used to dynamically evaluate the environmental impact of green products throughout their life cycle; Resource consumption optimization module, used to perform multi-objective optimization of resource consumption throughout the life cycle of green products; The association modeling and result generation module is used to perform association modeling on data from various stages of the green product life cycle, and generate full life cycle analysis results in combination with a multi-objective decision-making model.

2. The green product life cycle analysis system based on big data according to claim 1 is characterized in that: The full life cycle data includes: raw material acquisition stage data, production and processing stage data, circulation and sales stage data, use and maintenance stage data, and recycling and processing stage data; the associated element data includes: environmental impact factor data, resource consumption factor data, carbon emission factor data, policy and regulation factor data, and user behavior factor data; the environmental impact factor data includes: pollutant emission type data, emission concentration data, and environmental restoration cost data.

3. The green product life cycle analysis system based on big data according to claim 1 is characterized in that: The multi-dimensional preprocessing of the green product life cycle data and associated factor data acquired by the data acquisition module includes: Eliminate outliers and filter noise from the acquired raw data; Interpolate missing data and assign weights to data based on the entropy weight method; The processed data is divided into raw material acquisition time series, production and processing time series, circulation and sales time series, use and maintenance time series, and recycling and processing time series according to the life cycle stage.

4. The green product life cycle analysis system based on big data according to claim 3 is characterized in that: The dynamic assessment of the environmental impact of green products throughout their life cycle includes: Decompose the environmental impact factor data into resource consumption subsequence, pollution emission subsequence and environmental restoration cost subsequence; Construct a fuzzy membership function to perform fuzzy processing on each subsequence. The calculation formula is: ； in, Indicates the Environmental factors, Indicates the evaluation indicators, Indicates the Under the environmental factors The fuzzy membership of the evaluation indicators, is the fuzzy factor, Indicates the Under the environmental factors The actual measurement value of the evaluation indicator, is the benchmark value; The fuzzy evaluation results are fused through the weighted average operator to generate a comprehensive environmental impact score.

5. The green product life cycle analysis system based on big data according to claim 1 is characterized in that: The multi-objective optimization of resource consumption throughout the life cycle of green products includes: The objective function of resource optimization is set as minimizing total resource consumption, maximizing resource utilization efficiency and minimizing carbon emission intensity; Construct chromosome encoding rules and map resource allocation plans to chromosome gene sequences; The chromosome population is iteratively optimized through crossover, mutation, and selection operations until the preset convergence conditions are met.

6. The green product life cycle analysis system based on big data according to claim 2 is characterized in that: The association modeling of data from each stage of the green product life cycle includes: Extract feature sequences of data at each stage, including raw material acquisition feature sequences, production and processing feature sequences, circulation and sales feature sequences, use and maintenance feature sequences, and recycling and treatment feature sequences; Calculate the grey correlation degree between each feature sequence and the target sequence. The calculation formula is: ； in, Indicates the The grey correlation degree between the characteristic sequence of each life cycle stage and the target sequence, Indicates the The absolute difference between the characteristic sequence of each life cycle stage and the target sequence at the corresponding time point, Indicates all The minimum value in Indicates all The maximum value in is the resolution coefficient; Identify key life cycle stages based on relevance ranking.

7. The green product life cycle analysis system based on big data according to claim 6 is characterized in that: The multi-objective decision-making model includes: Construct a decision matrix and use environmental impact score, resource optimization plan and grey correlation as decision variables; The ideal point method is used to calculate the closeness of each solution to the ideal solution; The solution with the highest degree of closeness is selected as the optimal full life cycle analysis result.

8. The green product full life cycle analysis system based on big data according to claim 1 is characterized in that: Among the full life cycle data, the data of the raw material acquisition stage includes: raw material type data, mining energy consumption data and transportation distance data; the data of the production and processing stage includes: process energy consumption data, waste generation data and equipment efficiency data; the data of the circulation and sales stage includes: logistics carbon emission data, warehousing cost data and sales channel type data.

9. The green product life cycle analysis system based on big data according to claim 8 is characterized in that: The resource consumption factor data include: water resource consumption intensity data, energy consumption intensity data and raw material utilization rate data; the carbon emission factor data include: direct carbon emission data, indirect carbon emission data and carbon sink offset data.

10. The green product life cycle analysis system based on big data according to claim 1 is characterized in that: The system further comprises: Visual interaction module, used to visualize the analysis results through three-dimensional maps and dynamic heat maps; In the visualization interaction module, the three-dimensional map includes: a life cycle stage relationship network diagram, a resource consumption intensity distribution diagram and a carbon emission spatiotemporal evolution diagram; a dynamic heat map is used to display the changing trend of environmental impact scores in different regions.

Images