A method and system for constructing a green low-carbon evaluation index system for the petrochemical industry

Abstract

The application provides a construction method and system of a petrochemical industry green low-carbon evaluation index system, and relates to the technical field of low-carbon evaluation. The method comprises the following steps: formulating an evaluation target according to the green low-carbon demand of an enterprise; formulating an evaluation index based on whole-process management; obtaining an initial weight by using an analytic hierarchy process, obtaining actual environmental impact intensity by using a life cycle assessment method, and constructing a correction factor to perform secondary iteration calibration on the initial weight to obtain a calibrated weight; determining a current scene by using an application scene automatic identification model, extracting the demand and constraint conditions of green low-carbon for each scene, and refining the evaluation index into multiple levels of sub-evaluation indexes; quantifying the evaluation target, index and sub-index by using the life cycle assessment method, and combining the calibrated weight to construct an evaluation system. The application calibrates the weight by fusing the analytic hierarchy process and the life cycle assessment, refines the index in combination with the scene self-adaption, and improves the scientificity, pertinence and operability of the evaluation system.

Description

Technical Field

[0001] This application relates to the field of low-carbon evaluation technology, and in particular to a method and system for constructing a green and low-carbon evaluation index system for the petrochemical industry. Background Technology

[0002] With increasing global emphasis on environmental protection and sustainable development, the green transformation of the energy industry has become an irreversible trend. As a crucial sector in the use of fossil fuels, the petrochemical industry's environmental impact and resource consumption cannot be ignored in its entire management process. Traditional industry enterprise evaluation systems often focus on technical performance and economic costs, while neglecting green and low-carbon considerations, leading to numerous challenges in promoting the green development of the energy industry.

[0003] Currently, the concept of green and low-carbon development has gradually permeated all sectors, with the petrochemical industry taking the lead. However, a unified and standardized methodology for scientifically and systematically evaluating the green and low-carbon levels of petrochemical enterprises has yet to be established. Existing evaluation methods are mostly limited to assessments of single stages or single indicators, making it difficult to comprehensively reflect the environmental friendliness and resource utilization efficiency of petrochemical enterprises throughout their entire management process. Furthermore, the needs for green and low-carbon development in petrochemical enterprises vary across different application scenarios, and the lack of targeted evaluation indicators and detailed standards results in evaluations that lack practicality and guidance. Summary of the Invention

[0004] This application provides a method and system for constructing a green and low-carbon evaluation index system for the petrochemical industry. Through a systematic approach, a comprehensive, scientific, and practical evaluation index system is constructed to provide strong support for the green transformation of the petrochemical industry. This method not only helps to improve the green and low-carbon level of petrochemical enterprises and reduce negative environmental impacts, but also promotes the sustainable development of the entire petrochemical industry.

[0005] Firstly, this application provides a method for constructing a green and low-carbon evaluation index system for the petrochemical industry, the method comprising:

[0006] Evaluation targets are formulated based on the green and low-carbon needs of petrochemical enterprises. These evaluation targets include one or more combinations of reducing carbon emissions, improving resource utilization efficiency, reducing energy consumption, reducing pollutant generation and emissions, reducing environmental pollution, and improving environmental management.

[0007] For each evaluation objective, based on the full-process management of the petrochemical industry enterprise, at least one evaluation indicator is formulated to be associated with and support the evaluation objective. The full-process management includes the site selection stage, design stage, construction stage, and operation and maintenance stage.

[0008] Based on the green and low-carbon indicators and environmental impact indicators of the petrochemical industry enterprises, the initial weights of all evaluation indicators are obtained using the analytic hierarchy process (AHP). The green and low-carbon indicators characterize the environmental friendliness and resource utilization efficiency of the petrochemical industry enterprises in their whole-process management, while the environmental impact indicators characterize the comprehensive environmental impact of the petrochemical industry enterprises in their whole-process management. The life cycle assessment method is used to quantitatively analyze the evaluation indicators to obtain the actual environmental impact intensity. A correction factor is constructed based on the ratio of the actual environmental impact intensity to the initially predicted environmental impact intensity. The initial weights are then iteratively calibrated using the correction factor to obtain the calibrated weights.

[0009] Based on the application scenarios of the petrochemical industry enterprises, the current application scenario is determined by the application scenario automatic identification model, and the relevant data in the scenario database is analyzed by natural language processing to extract the green and low-carbon requirements and constraints under each application scenario. Based on the requirements and constraints, the evaluation index is refined into multi-level sub-evaluation indexes.

[0010] The evaluation objectives, evaluation indicators, and sub-evaluation indicators are quantified using a life cycle assessment method. The quantified evaluation objectives, evaluation indicators, and sub-evaluation indicators are then combined with the calibrated weights to construct an evaluation system.

[0011] As a preferred technical solution, for each evaluation target, based on the full-process management of the petrochemical industry enterprise, at least one evaluation indicator is formulated that is related to and supports the evaluation target, including:

[0012] Identify green strategies that contribute to green and low-carbon requirements at each stage of the entire process management;

[0013] Based on the green strategy, corresponding evaluation indicators are set for each stage of the whole process management;

[0014] The green strategies for the site selection phase include entering compliant industrial parks and staying away from environmental protection targets; for the design phase, green strategies include using environmentally friendly raw materials, auxiliary materials and fuels, optimizing designs to reduce fossil fuel use and improve energy efficiency; for the construction phase, green strategies include using energy-saving production equipment, reducing waste generation, and improving energy utilization efficiency; for the operation phase, green strategies include improving the operational efficiency of petrochemical companies and reducing energy consumption and emissions during operation; and for the maintenance phase, green strategies include optimizing maintenance plans, extending service life, and reducing energy consumption during maintenance.

[0015] As a preferred technical solution, based on the green and low-carbon indicators and environmental impact indicators of the petrochemical industry enterprises, the initial weights of all evaluation indicators are obtained using the analytic hierarchy process (AHP), including:

[0016] A hierarchical model is constructed, which includes a target layer, a criterion layer, and an indicator layer. The target layer is the overall target for green and low-carbon evaluation of petrochemical enterprises, the criterion layer is the intermediate link supporting the realization of the target layer, and the indicator layer is refined into quantifiable green and low-carbon indicators and environmental impact indicators.

[0017] Based on expert knowledge, pairwise comparisons are made between the relative importance of each criterion within the criterion layer and between each indicator within the indicator layer, and a judgment matrix is ​​constructed using the scaling method.

[0018] The maximum eigenvalue and corresponding eigenvector of each judgment matrix are calculated using the eigenvalue method, and then normalized to obtain the weight vector of each level element relative to the previous level element.

[0019] Calculate the consistency index CI for each judgment matrix, and compare the consistency index CI of each judgment matrix with the average random consistency index RI to obtain the consistency ratio CR. When the consistency ratio CR is less than a preset threshold, the judgment matrix meets the consistency condition, and the weight obtained at this time is used as the initial weight. Otherwise, the judgment matrix is ​​adjusted by modifying the score of the relative importance of each element in the judgment matrix until the consistency requirement is met, and the initial weight is obtained.

[0020] As a preferred technical solution, a correction factor is constructed based on the ratio of the actual environmental impact intensity to the initially predicted environmental impact intensity. The initial weights are then iteratively calibrated using this correction factor to obtain the calibrated weights, including:

[0021] The life cycle assessment method is used to collect data on the entire process of petrochemical enterprises, including energy consumption data, waste gas and wastewater pollutant emission data, and resource recycling rate data at each stage.

[0022] A weighted adjustment model is constructed, using the ratio of the actual environmental impact intensity to the initial predicted environmental impact intensity of each indicator as the adjustment factor. ;

[0023] The constraint condition for setting the correction factor is 0.5 ≤ ≤2.0, if exceeded, the boundary value is used;

[0024] Substituting the correction factor into the hierarchical single ranking process of the analytic hierarchy process, the initial weights are adjusted, and a consistency check is performed to ensure that the consistency ratio CR < 0.1, resulting in the calibrated weights. The formula for calculating the calibrated weights is as follows:

[0025]

[0026] In the formula, The weight after calibration for the i-th indicator. Let be the initial analytic hierarchy process weights for the i-th indicator. Let i be the weight adjustment factor for the i-th indicator. The total number of indicators in the sub-evaluation indicator layer.

[0027] As a preferred technical solution, based on the application scenarios of the petrochemical industry enterprises, an automatic application scenario identification model is used to determine the current application scenario, and natural language processing is used to parse relevant data in the scenario database to extract the green and low-carbon requirements and constraints under each scenario, including:

[0028] A database of green and low-carbon evaluation scenarios for petrochemical enterprises will be constructed. Industry standard data, enterprise information disclosure data, environmental management platform data and enterprise-side data will be captured from public data sources and platform interfaces to form characteristic parameters for three major categories of scenarios: enterprise application, public application and management application.

[0029] The support vector machine machine learning algorithm is used to construct an automatic scene matching and recognition model using the feature parameters in the scene database as training samples. The input of the automatic scene matching and recognition model is the basic information of the object to be evaluated, and the output is the matching application scene type.

[0030] Based on the automatic identification and matching of scenario types, natural language processing is used to parse relevant data in the scenario database, extract keywords for green and low-carbon evaluation requirements in each scenario, and multi-source data fusion technology is used to integrate industry production data, monitoring data and industry standard data to extract constraint boundaries and obtain the requirements and constraints of each scenario.

[0031] As a preferred technical solution, based on the aforementioned requirements and constraints, the evaluation index is refined into multi-level sub-evaluation indexes, including:

[0032] A sub-evaluation index database is constructed, and sub-evaluation indicators for each evaluation objective are formed based on industry standard data of the petrochemical industry and relevant industry and enterprise data captured under the evaluation objectives.

[0033] By using association rule mining algorithms, an association mapping model of scenario requirements, constraints, and evaluation indicators is established.

[0034] A hierarchical clustering algorithm is used to automatically decompose and generate multi-level sub-evaluation indicators based on the original evaluation objectives and the evaluation requirements of the scenario.

[0035] A real-time data optimization and adjustment mechanism is introduced, which connects to the regulatory platform data and industry standard data of the petrochemical industry to automatically verify the rationality of the sub-evaluation indicators. When the scenario requirements or constraints change, the associated mapping model is triggered to automatically update the sub-evaluation indicators.

[0036] As a preferred technical solution, the application scenarios include enterprise applications, public applications, and management applications;

[0037] Among them, the requirements for enterprise applications include high energy efficiency, high stability, and low cost, while the constraints include pollution emissions, resource and energy consumption, waste management, and recycling.

[0038] Requirements for public applications include ease of installation and maintenance, while constraints include environmental impact limits, pollution emissions, resource and energy consumption, and the impact of daily operation and maintenance.

[0039] The requirements for management applications include scientific rigor, comprehensiveness, low pollution, and low consumption, while the constraints include high requirements for green and low-carbon practices and comprehensiveness.

[0040] Furthermore, the content of the multi-level sub-evaluation indicators differs for different application scenarios: the sub-evaluation indicators for enterprise applications focus on energy efficiency and carbon emission indicators in the design, construction, operation, and maintenance phases; the sub-evaluation indicators for public applications focus on general indicators in the site selection, construction, operation, and maintenance phases; and the sub-evaluation indicators for management applications, in addition to those for public applications, further include risk prevention measures and changes in pollutant emissions after the project has been operating stably.

[0041] As a preferred technical solution, when using the life cycle assessment method to quantify the assessment target, the assessment index, and the sub-assessment index, for the index whose weight ratio in the calibrated weight is higher than a preset threshold, the data collection accuracy and time span of its sub-assessment index are improved during the life cycle assessment quantification process; for the index whose weight ratio in the calibrated weight is lower than a preset threshold, the life cycle assessment quantification process is optimized while ensuring data accuracy.

[0042] As a preferred technical solution, the multi-level sub-evaluation indicators include at least the following quantitative indicators: carbon dioxide emissions per ton of crude oil processed, comprehensive energy consumption per unit of oil refining, comprehensive energy consumption per unit of ethylene product, crude oil processing loss rate, industrial wastewater reuse rate, comprehensive utilization rate of industrial solid waste, proportion of clean transportation of bulk materials within the plant area, level of nitrogen oxide treatment technology in heating furnaces, and level of source control of fugitive VOCs in storage tanks.

[0043] Secondly, this application provides a system for constructing a green and low-carbon evaluation index system for the petrochemical industry, used to implement the method described above, the system comprising:

[0044] The evaluation target setting module is configured to set evaluation targets based on the green and low-carbon needs of petrochemical enterprises. The evaluation targets include one or more combinations of reducing carbon emissions, improving resource utilization efficiency, reducing energy consumption, reducing pollutant generation and emissions, reducing environmental pollution, and improving environmental management level.

[0045] The evaluation indicator formulation module is configured to formulate at least one evaluation indicator that is related to and supports the evaluation target for each evaluation target, based on the whole process management of the petrochemical industry enterprise. The whole process management includes the site selection stage, design stage, construction stage, operation and maintenance stage.

[0046] The weight determination module is configured to obtain the initial weights of all evaluation indicators based on the green and low-carbon indicators and environmental impact indicators of the petrochemical industry enterprises using the analytic hierarchy process (AHP). The green and low-carbon indicators characterize the environmental friendliness and resource utilization efficiency of the petrochemical industry enterprises in their whole-process management, while the environmental impact indicators characterize the comprehensive environmental impact of the petrochemical industry enterprises in their whole-process management. The evaluation indicators are quantitatively analyzed using a life cycle assessment method to obtain the actual environmental impact intensity. A correction factor is constructed based on the ratio of the actual environmental impact intensity to the initially predicted environmental impact intensity. The initial weights are then iteratively calibrated using the correction factor to obtain the calibrated weights.

[0047] The refined evaluation index module is configured to determine the current application scenario based on the application scenario of the petrochemical industry enterprise using an application scenario automatic identification model, and to extract the green and low-carbon requirements and constraints under each application scenario by parsing relevant data in the scenario database through natural language processing, and to refine the evaluation index into multi-level sub-evaluation indexes based on the requirements and constraints.

[0048] The system construction module is configured to use a life cycle assessment method to quantify the evaluation objectives, evaluation indicators and sub-evaluation indicators, and combine the quantified evaluation objectives, evaluation indicators and sub-evaluation indicators with the calibrated weights to construct an evaluation system.

[0049] The method and system for constructing a green and low-carbon evaluation index system for the petrochemical industry provided in this application have at least the following beneficial effects:

[0050] This application deeply integrates the Analytic Hierarchy Process (AHP) with Life Cycle Assessment (LCA). It utilizes the actual environmental impact intensity obtained during the LCA quantification process to construct correction factors, performing a secondary iterative calibration on the initial weights determined by the AHP. This effectively overcomes the shortcomings of traditional AHP, such as excessive subjectivity and disconnect from actual production scenarios, making the weight allocation of evaluation indicators more objective and scientific. Simultaneously, this application introduces an automatic application scenario identification model, combining machine learning algorithms and natural language processing technology to automatically extract green and low-carbon requirements and constraints under different application scenarios. Based on this, the evaluation indicators are adaptively refined into multi-level sub-evaluation indicators, achieving precise matching between the evaluation system and the actual application scenarios of petrochemical enterprises, significantly improving the relevance and operability of the evaluation indicators. Furthermore, this application also formulates green strategies and evaluation indicators based on the phased development of the entire process management of petrochemical enterprises, covering the entire life cycle from site selection, design, construction, operation, and maintenance, comprehensively reflecting the green and low-carbon level and environmental impact of enterprises at each stage. This application effectively addresses the limitations of existing evaluation methods that rely on single-stage or single-indicator assessments, providing a systematic, intelligent, and quantifiable evaluation tool for the green and low-carbon transformation of petrochemical enterprises, and contributing to the sustainable development of the entire petrochemical industry. Attached Figure Description

[0051] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0052] Figure 1 A flowchart illustrating a method for constructing a green and low-carbon evaluation index system for the petrochemical industry, provided as an embodiment of this application;

[0053] Figure 2 A graph illustrating the evaluation metrics provided in the embodiments of this application;

[0054] Figure 3 Flowchart for determining the initial weights of evaluation indicators provided in the embodiments of this application;

[0055] Figure 4 This is a flowchart of the calibration weight calculation provided in an embodiment of this application;

[0056] Figure 5 A detailed flowchart of the evaluation indicators provided in the embodiments of this application;

[0057] Figure 6 This is a structural diagram of a system for constructing a green and low-carbon evaluation index system for the petrochemical industry, provided in an embodiment of this application.

[0058] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concepts of this application to those skilled in the art through reference to specific embodiments. Detailed Implementation

[0059] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0060] It should be noted that in the embodiments of this application, certain software, components, models and other existing solutions in the industry may be mentioned. These should be regarded as exemplary and are only intended to illustrate the feasibility of implementing the technical solution of this application. However, it does not mean that the applicant has used or necessarily used the solution.

[0061] The technical solution of this application and how it solves the above-mentioned technical problems will be described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will be described below with reference to the accompanying drawings.

[0062] This application provides a method for constructing a green and low-carbon evaluation index system for the petrochemical industry. The method works as follows: Evaluation objectives are formulated based on the green and low-carbon needs of petrochemical enterprises. These objectives include single or combined objectives such as reducing carbon emissions, improving resource utilization efficiency, reducing energy consumption, reducing waste generation, reducing environmental pollution, enhancing recyclability, and improving economic benefits. Based on whole-process management, green strategies contributing to green and low-carbon development at each stage are collected, and evaluation indicators that are related to and support the evaluation objectives are formulated. A hierarchical structure model including an objective layer, a criterion layer, and an indicator layer is constructed using the analytic hierarchy process (AHP). Expert scoring is then used to evaluate the system. A judgment matrix is ​​constructed and the weights of elements at each level are calculated. Based on different application scenarios, the green and low-carbon requirements and constraints of each scenario are identified, and the original evaluation indicators are further refined into multi-level sub-evaluation indicators. The life cycle assessment method is used to quantify the evaluation objectives, evaluation indicators, and sub-evaluation indicators to reflect the green and low-carbon performance in numerical form. The quantified evaluation objectives, evaluation indicators, and sub-evaluation indicators are combined with the weights obtained by the analytic hierarchy process to construct a complete green and low-carbon evaluation system for petrochemical enterprises. This system reflects the environmental friendliness and resource utilization efficiency in the whole process management and adapts to the needs and constraints of different application scenarios.

[0063] Based on the above overall working principle, such as Figure 1 As shown, this method can be implemented through the following steps S10-S50.

[0064] S10: Develop evaluation targets based on the green and low-carbon needs of petrochemical companies.

[0065] In step S10, specific evaluation targets need to be formulated based on the green and low-carbon needs of petrochemical enterprises. These evaluation targets should comprehensively cover the environmental impact and resource utilization efficiency of petrochemical enterprises throughout their entire management process, ensuring that the evaluation system accurately reflects the green and low-carbon performance of these enterprises.

[0066] In this embodiment, the evaluation targets may include, but are not limited to, one or more of the following categories:

[0067] Reduce carbon emissions: Reduce the total carbon emissions of petrochemical companies during operation, especially carbon emissions during stages such as fossil fuel use and process production.

[0068] Improve resource utilization efficiency: Ensure that petrochemical companies minimize the consumption of raw materials and energy during operation and maintenance.

[0069] Reduce energy consumption: Optimize design and manufacturing processes to reduce energy consumption during the operation of petrochemical enterprises.

[0070] Reduce waste generation: Reduce pollutants generated during production by optimizing design and production processes.

[0071] Reduce environmental pollution: Reduce pollutant emissions generated during the operation of petrochemical enterprises, and protect the atmosphere, surface water and water resources.

[0072] S20: For each evaluation objective, based on the whole-process management of petrochemical enterprises, formulate at least one evaluation indicator that is related to and supports the evaluation objective.

[0073] Specifically, in the steps of developing evaluation indicators based on whole-process management, whole-process management includes the site selection, design, construction, operation and maintenance phases for petrochemical companies.

[0074] In some implementations, such as Figure 2 As shown, step S20 specifically includes the following steps S21 and S22.

[0075] S21: Identify green strategies that contribute to green and low-carbon requirements at each stage of the whole process management.

[0076] In this embodiment, it is necessary to collect and analyze green strategies that petrochemical companies can use to contribute to green and low-carbon requirements at various stages of their entire process management. These green strategies include, but are not limited to:

[0077] Site selection phase: Enter a compliant industrial park, away from environmental protection targets;

[0078] Design phase: Adopting environmentally friendly raw materials, auxiliary materials and fuels, and optimizing the design to reduce the use of fossil energy and improve energy efficiency;

[0079] Construction phase: Adopting energy-saving production equipment, reducing waste generation, and improving energy efficiency, etc.

[0080] Operational phase: Improve the operational efficiency of petrochemical enterprises and reduce energy consumption and emissions during operation;

[0081] Maintenance phase: Optimize maintenance plans, extend service life, and reduce energy consumption during maintenance.

[0082] S22: Based on the green strategy, set corresponding evaluation indicators for each stage of the whole process management.

[0083] For example, the evaluation indicators set based on the green strategy at each stage include: site selection compliance indicators at the site selection stage; the proportion of environmentally friendly raw materials used, the proportion of environmentally friendly auxiliary materials used, the proportion of environmentally friendly fuels used, the comprehensive energy consumption per unit of oil refining, the comprehensive energy consumption per unit of ethylene product, crude oil processing loss rate, industrial wastewater reuse rate, comprehensive utilization rate of industrial solid waste, and whether there is an increase in coal consumption at the design stage; the scale of a single crude oil primary processing unit, the proportion of heavy oil floating roof tanks used, the proportion of carbon dioxide recovery or comprehensive utilization facilities, the proportion of clean transportation of bulk materials within the plant area, whether a coal-fired self-owned power plant is set up, whether the delayed coking unit is a closed decoking unit, the resource and energy consumption during construction, and the pollutant emissions during construction; and the operation at the operation stage. Efficiency, CO2 emissions per ton of crude oil processed, wastewater emissions per ton of crude oil processed, COD emissions per ton of crude oil processed, ammonia nitrogen emissions per ton of crude oil processed, total phosphorus emissions per ton of crude oil processed, total nitrogen emissions per ton of crude oil processed, sulfur dioxide emissions per ton of crude oil processed, nitrogen oxide emissions per ton of crude oil processed, particulate matter emissions per ton of crude oil processed, volatile organic compound emissions per ton of crude oil processed, as well as maintenance frequency during the maintenance phase, nitrogen oxide treatment technology level of heating furnace, sulfur content of fuel, exhaust gas treatment technology of catalytic reforming unit, exhaust gas treatment technology of acid gas recovery unit, level of fugitive VOC source control in storage tanks, exhaust gas treatment level of volatile organic liquid loading, energy consumption during maintenance, pollutant emissions during maintenance, and material recycling rate.

[0084] S30: Based on the green and low-carbon indicators and environmental impact indicators of petrochemical enterprises, the initial weights of all evaluation indicators are obtained using the analytic hierarchy process (AHP). The life cycle assessment method is used to quantify the evaluation indicators to obtain the actual environmental impact intensity. A correction factor is constructed based on the ratio of the actual environmental impact intensity to the initial predicted environmental impact intensity. The initial weights are then calibrated using the correction factor in a second iteration to obtain the calibrated weights.

[0085] In this embodiment, the green and low-carbon index is used to characterize the environmental friendliness and resource utilization efficiency of petrochemical enterprises in the whole process management, and the environmental impact index is used to characterize the comprehensive environmental impact of petrochemical enterprises in the whole process management.

[0086] In some implementations, such as Figure 3 As shown, based on the green and low-carbon indicators and environmental impact indicators of petrochemical enterprises, the initial weights of all evaluation indicators can be obtained using the analytic hierarchy process (AHP) through the following steps S31-S34.

[0087] S31: Construct a hierarchical structure model for the system. The hierarchical structure model includes an objective layer, a criterion layer, and an indicator layer. The objective layer is the overall objective for green and low-carbon evaluation of petrochemical enterprises. The criterion layer is the intermediate link that supports the realization of the objective layer. The indicator layer is further refined into quantifiable green and low-carbon indicators and environmental impact indicators to reflect the resource utilization efficiency and environmental friendliness of petrochemical enterprises, respectively.

[0088] In this embodiment, a hierarchical model needs to be constructed, which includes three layers: the target layer, the criterion layer, and the indicator layer.

[0089] The target layer includes the overall green and low-carbon evaluation goals for petrochemical enterprises. The criteria layer supports the intermediate steps in achieving the target layer, including but not limited to: reducing carbon emissions, improving resource utilization efficiency, reducing energy consumption, reducing waste generation, reducing environmental pollution, enhancing recyclability, and improving economic benefits. The indicator layer is refined into quantifiable green and low-carbon indicators and environmental impact indicators, specifically including: site selection compliance, use of environmentally friendly raw materials (auxiliary materials), use of environmentally friendly fuels, comprehensive energy consumption, crude oil processing loss rate, industrial water reuse rate, comprehensive utilization rate of industrial solid waste, advancement of production process equipment, waste recycling rate, comprehensive energy consumption, fresh water intake, operating efficiency, pollutant emissions during operation, carbon dioxide emissions, proportion of carbon dioxide recovery or comprehensive utilization facilities, maintenance frequency, energy consumption during maintenance, material recycling rate, and dismantling convenience.

[0090] S32: Based on expert domain knowledge in relevant fields, perform pairwise comparisons of the relative importance scores between criteria within the criterion layer and between indicators within the indicator layer, and construct at least one judgment matrix using the scaling method.

[0091] S33: Calculate the maximum eigenvalue and corresponding eigenvector of each judgment matrix using the eigenvalue method, and perform normalization to obtain the weight vector of each level element relative to the element of the previous level. Here, level represents the criterion layer or index layer, and element represents the criterion of the criterion layer or the index of the index layer.

[0092] S34: Calculate the consistency index CI of each judgment matrix, and compare the consistency index CI of each judgment matrix with the average random consistency index RI to obtain the consistency ratio CR; when the consistency ratio CR is less than the preset threshold, the judgment matrix meets the consistency condition, and the weight obtained at this time is used as the initial weight; otherwise, the judgment matrix is ​​adjusted by modifying the score of the relative importance of each element in the judgment matrix until the consistency requirement is met, and the initial weight is obtained.

[0093] In step S34, the maximum eigenvalue of each judgment matrix is ​​first calculated. Then use the consistency index formula Calculate the CI value, where To determine the order of a matrix; based on the matrix order Obtain the average random consistency index (RI) value from the table, and then calculate the consistency ratio. If the CR is less than a preset threshold of 0.1, the judgment matrix is ​​considered to have passed the consistency test, and the weight vector calculated at this time is the initial weight. If the CR is greater than or equal to 0.1, it indicates that the consistency of the judgment matrix does not meet the requirements. At this time, the feedback mechanism prompts the experts to indicate the specific location of the inconsistency, and the experts re-evaluate and modify the pairwise comparison scores of the corresponding elements in the judgment matrix. The CI and CR are calculated repeatedly until the CR is less than 0.1, thereby obtaining the initial weight that meets the consistency condition.

[0094] In some implementations, such as Figure 4 As shown, the calibrated weights are calculated through the following steps S35-S38.

[0095] S35: Collect full-process data of petrochemical enterprises through the quantitative process of life cycle assessment methods, including energy consumption data, waste gas and wastewater pollutant emission data, and resource recycling rate data at each stage.

[0096] A weight correction model is constructed by quantifying the full-process data of petrochemical enterprises collected during the life cycle assessment method. If the life cycle assessment quantification result of a certain evaluation indicator shows that its actual environmental impact intensity is higher than the initial predicted environmental impact intensity, and the initial weight of the indicator is too low, then the weight of the indicator is increased through a second iteration of hierarchical single ranking and consistency test. If the life cycle assessment quantification result of a certain evaluation indicator shows that its actual environmental impact intensity is lower than the initial predicted environmental impact intensity, and the initial weight of the indicator is too high, then the weight of the indicator is appropriately reduced. This ensures that the weight allocation conforms to the theoretical hierarchical structure of the analytic hierarchy process and is also consistent with the actual production scenario of petrochemical enterprises.

[0097] S36: Construct a weighted adjustment model, using the ratio of the actual environmental impact intensity of each indicator to the initial predicted environmental impact intensity as the adjustment factor. .

[0098] For example, using AHP, expert scoring, and pairwise comparison matrix construction, the initial weights of each indicator layer are determined as follows: Reduce carbon emissions: 0.20; Improve resource utilization efficiency: 0.15; Reduce energy consumption: 0.15; Reduce pollutant generation: 0.20; Reduce environmental impact: 0.10; Enhance recyclability: 0.10; Improve economic benefits: 0.10.

[0099] By extracting actual data collected during the LCA quantification process, a correction factor is constructed. This correction factor is the ratio of the actual environmental impact intensity of each indicator to the initial predicted intensity. The actual environmental impact intensity is determined by the LCA quantification results, while the initial predicted intensity is determined by expert scoring. The specific calculation formula is as follows:

[0100]

[0101] In the formula, is the weight adjustment factor for the i-th indicator; The actual environmental impact intensity of the i-th indicator is calculated by the LCA quantification process. The unit is determined according to the specific sub-evaluation indicator, such as the carbon dioxide emission of processing ton of crude oil is tons / ton of crude oil and the comprehensive energy consumption is kilograms of standard oil / ton of crude oil. The initial predicted environmental impact intensity for the i-th indicator is determined by experts based on their industry experience, and the unit is consistent with the actual environmental impact intensity.

[0102] S37: Set the constraint conditions for the correction factor, and take the boundary value when it is exceeded.

[0103] In this embodiment, the correction factor must satisfy the constraint: 0.5 ≤ ≤2.0. If the calculated correction factor exceeds this range, the boundary value is taken; that is, 0.5 is used when it is less than 0.5, and 2.0 is used when it is greater than 2.0. For example, if the actual environmental impact intensity of VOC emissions during the operation phase is 1.2 times the initial prediction, the corresponding correction factor for reducing pollutant generation is 1.2; if the actual environmental impact intensity of fresh water intake per ton of crude oil is consistent with the initial prediction, the correction factor is 1.0.

[0104] S38: Substitute the correction factor into the hierarchical single ranking process of the analytic hierarchy process to adjust the initial weights, and at the same time perform a consistency test to ensure that the consistency ratio CR < 0.1, and obtain the calibrated weights.

[0105] In this embodiment, the formula for calculating the calibrated weight is:

[0106]

[0107] In the formula, The weight after calibration for the i-th indicator. Let be the initial analytic hierarchy process weights for the i-th indicator. Let i be the weight adjustment factor for the i-th indicator. The total number of indicators in the sub-evaluation indicator layer.

[0108] S40: Based on the application scenarios of petrochemical industry enterprises, the current application scenario is determined by the application scenario automatic identification model, and relevant data in the scenario database is analyzed by natural language processing to extract the green and low-carbon requirements and constraints under each application scenario. Based on the requirements and constraints, the evaluation indicators are refined into multi-level sub-evaluation indicators.

[0109] In step S40, based on the application scenarios of petrochemical enterprises, a green and low-carbon evaluation scenario database for petrochemical enterprises is pre-constructed. This database obtains industry production data, monitoring data, and enterprise data from public data sources and platform interfaces through big data crawling technology, forming core feature parameters for three major categories of scenarios: enterprise applications, public applications, and management applications. A support vector machine algorithm is used to construct an automatic application scenario identification model using the feature parameters in the scenario database as training samples. The basic information of the object to be evaluated is input into the model to automatically match the current application scenario type. After identifying the application scenario, the relevant data in the scenario database is parsed through natural language processing to extract the green and low-carbon requirements and constraints under each scenario. Based on the extracted requirements and constraints, a mapping relationship between scenario requirements and evaluation indicators is established by combining association rule mining algorithms. The original evaluation indicators are adaptively refined into multi-level sub-evaluation indicators to achieve accurate matching between the evaluation indicator system and the application scenario.

[0110] In some implementations, such as Figure 5As shown, step S40 specifically includes the following steps S41 and S42.

[0111] S41: For different application scenarios of petrochemical enterprises, determine the requirements and constraints of each scenario on the green and low-carbon needs of petrochemical enterprises.

[0112] In this embodiment, it is necessary to analyze the needs and constraints of petrochemical companies under different application scenarios to determine the necessity and specific content of refining the evaluation indicators. Step S41 can be implemented through the following steps S411-S413.

[0113] S411: Construct a database of green and low-carbon evaluation scenarios for petrochemical industry enterprises.

[0114] By utilizing big data crawling and other technologies to collect information, including but not limited to industry standard data and publicly available enterprise information in the petrochemical industry; and by obtaining data from environmental management platform interfaces, including but not limited to data from the National Pollutant Discharge Permit Information Management Platform, environmental impact assessment report data, ecological and environmental law enforcement data, industrial enterprise greenhouse gas report data, and data from relevant platforms or reports such as automatic monitoring; and by obtaining data from enterprise-side interfaces, the core characteristic parameters of three major scenarios—enterprise application, public application, and management application—are aggregated to establish a green and low-carbon evaluation scenario database for petrochemical enterprises. This database includes sub-enterprises in oil refining, ethylene, and integrated refining and chemical industries, providing data support for the scenario adaptability matching of green and low-carbon evaluation for petrochemical enterprises. The database adopts a dynamic update and adjustment mechanism, with data updates and adjustments occurring monthly. By real-time crawling and aggregating pollution emission data, resource and energy consumption data, carbon emission data, energy conservation and emission reduction measure data, production process or facility data, and pollution control facility data in the petrochemical industry, the scientific validity of the data is ensured.

[0115] S412: Construction and training of application scenario automatic identification model.

[0116] Machine learning algorithms, such as Support Vector Machines, are employed to construct an automatic scene matching and recognition model using feature parameters from a scene database as training samples. The model input consists of basic information about the object to be evaluated, such as enterprise type, number of enterprises, evaluation requirements, production scale, and pollution emissions. By extracting this basic information, the model automatically and accurately matches suitable application scenario types, including enterprise applications, public applications, and management applications. Simultaneously, extended learning techniques are introduced to improve the model's matching accuracy. For different sub-sectors of the petrochemical industry, such as oil refining, ethylene, and integrated refining and chemical processing, model parameters are optimized based on the differences in various scenarios, further enhancing the accuracy of automatic scene matching and recognition and avoiding human error.

[0117] S413: Intelligent extraction and parsing of requirements and constraints.

[0118] Based on automatic identification and matching of scenario types, natural language processing is used to parse relevant data in the database and extract keywords for green and low-carbon evaluation needs under each scenario. Keywords for enterprise applications include single enterprise, pollution reduction and carbon reduction, and quality and efficiency improvement; keywords for public applications include whole-process evaluation and operation and maintenance; keywords for management applications include comprehensive dynamic control. Combining multi-source data fusion technology, production data, monitoring data, and industry standard data from industries and enterprises are integrated to extract constraint boundaries, achieving accurate and objective definition of needs and constraints.

[0119] First, the application scenarios are determined. Enterprise applications refer to industrial enterprises in the petrochemical industry, etc. Model matching identifies the evaluation subject as a production-oriented enterprise, such as crude oil processing, ethylene production, or integrated refining and chemical enterprises, matching features in the scenario database such as full production cycle control and benefit orientation. Public applications refer to environmental impact assessment units, technical consulting service units, etc. Evaluation demand keywords identify the evaluation subject as a service-oriented organization, with primary needs being environmental assessment and technical support, matching features in the application scenario database such as general assessment and technical services. Management applications refer to management departments at all levels, environmental public interest organizations, etc. Evaluation demand keywords identify the evaluation subject as a management or public interest organization, with primary needs being industry control and supervision, matching features in the scenario database such as comprehensive supervision and dynamic control.

[0120] Determine the requirements and constraints for each application scenario. Enterprise applications require personalization and guidance to more scientifically and accurately help enterprises reduce pollution and carbon emissions, improve quality and efficiency. Special consideration needs to be given to reducing carbon emissions, lowering energy consumption, and improving economic benefits during the construction and operation phases of enterprises. Requirements include high energy efficiency, high stability, and low cost, while constraints include pollution emissions, resource and energy consumption, waste management, and recycling. Public applications focus more on universality and operability, with a focus on green and low-carbon assessments throughout the entire process and chain. They need to consider carbon emissions, pollutant emissions, and energy consumption during the design and operation phases, as well as the need for simple and quick installation and maintenance to provide more scientific and precise support for enterprises. The industry provides technical support and services, with requirements including ease of installation and maintenance, and constraints including environmental impact restrictions, pollution emissions, resource and energy consumption, and the impact of daily operation and maintenance. Management applications pay more attention to scientific rigor and comprehensiveness in order to more comprehensively and dynamically grasp the green and low-carbon development level of petrochemical enterprises. It is necessary to grasp the status of various evaluation indicators for green and low-carbon assessment of petrochemical enterprises, and to scientifically evaluate the green and low-carbon level of industry enterprises throughout the entire life cycle and chain, so as to continuously improve the green and low-carbon level of the petrochemical industry and promote industry development. Requirements include scientific rigor, comprehensiveness, low pollution, and low consumption, and constraints include high requirements for green and low-carbon development and comprehensiveness.

[0121] S42: Based on the above requirements and constraints, the original evaluation indicators are refined into multi-level sub-evaluation indicators.

[0122] In this embodiment, based on the requirements and constraints identified and analyzed by the above model, and combined with the adaptive refinement technology of indicators, the original evaluation indicators are further refined into multi-level sub-evaluation indicators based on the requirements and constraints. This achieves automatic and accurate matching between sub-evaluation indicators and application scenarios, improving the pertinence and operability of the evaluation indicator system. Step S42 can be specifically achieved through the following steps S421-S424 to realize the automatic matching of multi-level sub-evaluation indicators.

[0123] S421: Construct a database of sub-evaluation indicators.

[0124] Based on the characteristics of petrochemical enterprises, and under the five evaluation objectives of reducing carbon emissions, improving resource utilization efficiency, reducing energy consumption, reducing pollutant generation and emissions, reducing environmental pollution, and improving environmental management, a database of sub-evaluation indicators for each evaluation objective is established, using industry-standard data and relevant industry and enterprise data obtained in step S10. For example, pollutant generation and emissions indicators include the amount of wastewater, COD, ammonia nitrogen, total phosphorus, and total nitrogen discharged into the environment per ton of crude oil processed, as well as related sub-evaluation indicators such as sulfur dioxide, nitrogen oxides, particulate matter, and volatile organic compounds in exhaust gases.

[0125] S422: Construct a mapping model for the indicators.

[0126] Based on the scenario requirements and constraints obtained through intelligent identification and analysis in step S41, an association rule mining algorithm is used to establish an association mapping model between scenario requirements, constraints, and evaluation indicators, clarifying the correspondence between core evaluation requirements and evaluation indicators in each scenario. For example, the high energy efficiency requirements of enterprise applications are associated with comprehensive energy consumption indicators, and the comprehensive requirements of management applications are associated with risk prevention measures indicators, providing logical support for the refinement of sub-evaluation indicators.

[0127] S423: Automatic matching and generation of multi-level sub-evaluation indicators.

[0128] A hierarchical clustering algorithm is employed to automatically decompose and generate multi-level sub-evaluation indicators based on the original evaluation objectives and the evaluation requirements of the scenario. For quantifiable requirements, such as energy consumption requirements for enterprise applications, specific quantitative sub-evaluation indicators are automatically refined, such as the comprehensive energy consumption per unit of oil refining and the comprehensive energy consumption per unit of ethylene product. For qualitative requirements, such as process advancement, sub-evaluation indicators that combine qualitative and quantitative criteria are automatically decomposed, such as the scale of a single crude oil primary processing unit and the configuration of closed decoking, ensuring that the sub-evaluation indicators are highly matched with the scenario requirements.

[0129] S424: Dynamic optimization and adjustment of multi-level sub-evaluation indicators.

[0130] A real-time data optimization and adjustment mechanism is introduced. By connecting with relevant data from regulatory platforms in the petrochemical industry, such as environmental impact assessment, pollutant discharge permit management platforms, and online monitoring, the sub-evaluation indicators are compared with actual data to automatically verify their rationality. At the same time, combined with the dynamic updates of the scenario database, when scenario requirements or constraints change, such as changes in actual application scenarios, the indicator association mapping model automatically triggers the update of sub-evaluation indicators, realizing the automatic adaptive optimization of the sub-evaluation indicator system.

[0131] The specific sub-evaluation indicators for different application scenarios are described below.

[0132] For enterprise applications, the specific sub-evaluation indicators are as follows.

[0133] The sub-evaluation indicators in the design phase include: the proportion of environmentally friendly raw materials and auxiliary materials used; the proportion of environmentally friendly fuels used; comprehensive energy consumption, where the comprehensive energy consumption per unit of oil refining refers to the ratio of the total energy consumption of oil refining to the sum of crude oil and purchased raw material processing volume during the statistical reporting period, and the comprehensive energy consumption per unit of ethylene product refers to the ratio of the energy consumption of the ethylene unit to the output of qualified ethylene products during the statistical reporting period; crude oil processing loss rate, which is the percentage of crude oil loss during the processing of the production unit to the total amount of raw material processed; industrial wastewater reuse rate, which is the ratio of industrial water reuse to the total industrial water consumption; comprehensive utilization rate of industrial solid waste, which is the proportion of comprehensive utilization of industrial solid waste to the total amount of solid waste generated by the entire plant; and whether there is any increase in coal consumption, i.e., whether the enterprise has increased its coal consumption.

[0134] The sub-evaluation indicators during the construction phase include: the advancement of production technology and equipment, specifically covering the scale of a single crude oil primary processing unit, the proportion of heavy oil floating roof tanks used, the proportion of carbon dioxide recovery or comprehensive utilization facilities, the proportion of clean transportation of bulk materials within the plant area, whether a coal-fired self-owned power plant or boiler is set up, and whether the delayed coking unit is a closed decoking unit; the amount of resources and energy consumed during construction, i.e., the amount of energy consumed during construction; and the amount of pollutants emitted during construction, i.e., the amount of wastewater, waste gas, and solid waste pollutants emitted during the project construction process.

[0135] The sub-evaluation indicators for the operation phase include: operation efficiency, i.e. the efficiency of petrochemical enterprises during operation; carbon dioxide emissions per ton of crude oil processed during the operation period, i.e. the amount of carbon dioxide emitted into the environment per ton of crude oil processed; and pollutant emissions per ton of crude oil processed during the operation period, i.e. the amount of wastewater, COD, ammonia nitrogen, total phosphorus, and total nitrogen emitted into the environment per ton of crude oil processed, as well as the amount of sulfur dioxide, nitrogen oxides, particulate matter, and volatile organic compounds in the exhaust gas.

[0136] The sub-evaluation indicators for the maintenance phase include: maintenance frequency, i.e., the maintenance frequency of petrochemical enterprises; pollution prevention and control technology level, specifically including the level of nitrogen oxide treatment technology for heating furnaces, sulfur content of fuel (fuel being refinery dry gas or natural gas), waste gas treatment technology for catalytic reforming units, waste gas treatment technology for acid gas recovery units, level of source control of fugitive VOCs in storage tanks, and level of waste gas treatment for volatile organic liquid loading; energy consumption during maintenance; pollutant emissions during maintenance; and material recycling rate, i.e., the recycling rate of materials during maintenance.

[0137] For public applications, the specific sub-evaluation indicators are as follows.

[0138] The sub-evaluation indicators in the site selection phase include: site selection compliance, i.e., whether the project is located in a compliant industrial park and the environmental protection objectives around the project.

[0139] The sub-evaluation indicators for the construction phase are the same as those for the corresponding phase of enterprise application, including the advancement of production processes and equipment, resource and energy consumption during construction, and pollutant emissions during construction.

[0140] The sub-evaluation indicators for the operation phase are the same as those for the corresponding phase of enterprise application, including operation efficiency, carbon dioxide emissions per ton of crude oil processed during the operation period, and pollutant emissions per ton of crude oil processed during the operation period.

[0141] The sub-evaluation indicators for the maintenance phase are the same as those for the corresponding phase of enterprise application, including maintenance frequency, pollution prevention and control technology level, energy consumption during maintenance, pollutant emissions during maintenance, and material recycling rate.

[0142] For management applications, the specific sub-evaluation indicators are as follows.

[0143] The sub-evaluation indicators in the site selection phase include: site selection compliance, namely the ecological environment zoning control, whether the project is located in a compliant industrial park, and the environmental protection targets around the project.

[0144] The sub-evaluation indicators for the construction phase are the same as those for the corresponding phase of enterprise application, including the advancement of production processes and equipment, resource and energy consumption during construction, and pollutant emissions during construction.

[0145] The sub-evaluation indicators for the operation phase include not only operating efficiency, carbon dioxide emissions per ton of crude oil processed, and pollutant emissions per ton of crude oil processed, but also risk prevention measures, namely risk control measures and emergency plans; as well as changes in pollutant emissions after the project is in stable operation, namely whether new pollutants are added, whether the environmental quality of the project site meets the standards, whether regional reduction measures are implemented, and the status of regional reduction measures.

[0146] The sub-evaluation indicators for the maintenance phase are the same as those for the corresponding phase of public application, including maintenance frequency, pollution prevention and control technology level, energy consumption during maintenance, pollutant emissions during maintenance, and material recycling rate.

[0147] S50: The life cycle assessment method is used to quantify the assessment objectives, assessment indicators and sub-assessment indicators, and the quantified assessment objectives, assessment indicators and sub-assessment indicators are combined with the calibrated weights to construct the assessment system.

[0148] In an exemplary embodiment, for industrial enterprise applications, the following evaluation indicators and sub-evaluation indicators have been quantified based on LCA, and the specific calculation details are shown in Tables 1 to 4. The final total score is 9.675.

[0149] Table 1. Accounting details during the design phase of an enterprise's evaluation index system.

[0150]

[0151] Table 2. Accounting for the Construction Phase in an Enterprise's Evaluation Index System

[0152]

[0153] Table 3. Accounting Status of the Operation Phase in the Evaluation Index System of a Certain Enterprise

[0154]

[0155] Table 4. Accounting details for the maintenance phase in an enterprise's evaluation indicator system.

[0156]

[0157] This application also provides a system for constructing a green and low-carbon evaluation index system for the petrochemical industry, such as... Figure 6 As shown, the construction system of the green and low-carbon evaluation index system for the petrochemical industry includes:

[0158] The evaluation target setting module 601 is configured to set evaluation targets based on the green and low-carbon needs of petrochemical enterprises. The evaluation targets include one or more combinations of reducing carbon emissions, improving resource utilization efficiency, reducing energy consumption, reducing pollutant generation and emissions, reducing environmental pollution, and improving environmental management level.

[0159] The evaluation index formulation module 602 is configured to formulate at least one evaluation index that is associated with and supports the evaluation target for each evaluation target, based on the whole process management of the petrochemical industry enterprise. The whole process management includes the site selection stage, design stage, construction stage, operation and maintenance stage.

[0160] The weight determination module 603 is configured to obtain the initial weights of all evaluation indicators based on the green and low-carbon indicators and environmental impact indicators of the petrochemical industry enterprises using the analytic hierarchy process (AHP). The green and low-carbon indicators characterize the environmental friendliness and resource utilization efficiency of the petrochemical industry enterprises in their whole-process management, while the environmental impact indicators characterize the comprehensive environmental impact of the petrochemical industry enterprises in their whole-process management. The evaluation indicators are quantitatively analyzed using a life cycle assessment method to obtain the actual environmental impact intensity. A correction factor is constructed based on the ratio of the actual environmental impact intensity to the initially predicted environmental impact intensity. The initial weights are then iteratively calibrated using the correction factor to obtain the calibrated weights.

[0161] The refined evaluation index module 604 is configured to determine the current application scenario based on the application scenario of the petrochemical industry enterprise using an application scenario automatic identification model, and to extract the green and low-carbon requirements and constraints under each application scenario by parsing relevant data in the scenario database through natural language processing, and to refine the evaluation index into multi-level sub-evaluation indexes based on the requirements and constraints.

[0162] The system construction module 605 is configured to use a life cycle assessment method to quantify the evaluation target, the evaluation index and the sub-evaluation index, and combine the quantified evaluation target, the evaluation index and the sub-evaluation index with the calibrated weights to construct an evaluation system.

[0163] It should be noted that the construction system of the green and low-carbon evaluation index system for the petrochemical industry mentioned above belongs to the same technical concept as the prior method, and can achieve the same technical effect, so it will not be elaborated here.

[0164] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A method for constructing a green and low-carbon evaluation index system for the petrochemical industry, characterized in that... The method includes: Evaluation targets are formulated based on the green and low-carbon needs of petrochemical enterprises. These evaluation targets include one or more combinations of reducing carbon emissions, improving resource utilization efficiency, reducing energy consumption, reducing pollutant generation and emissions, reducing environmental pollution, and improving environmental management. For each evaluation objective, based on the full-process management of the petrochemical industry enterprise, at least one evaluation indicator is formulated to be associated with and support the evaluation objective. The full-process management includes the site selection stage, design stage, construction stage, and operation and maintenance stage. Based on the green and low-carbon indicators and environmental impact indicators of the petrochemical industry enterprises, the initial weights of all evaluation indicators are obtained using the analytic hierarchy process (AHP). The green and low-carbon indicators characterize the environmental friendliness and resource utilization efficiency of the petrochemical industry enterprises in their whole-process management, while the environmental impact indicators characterize the comprehensive environmental impact of the petrochemical industry enterprises in their whole-process management. The life cycle assessment method is used to quantitatively analyze the evaluation indicators to obtain the actual environmental impact intensity. A correction factor is constructed based on the ratio of the actual environmental impact intensity to the initially predicted environmental impact intensity. The initial weights are then iteratively calibrated using the correction factor to obtain the calibrated weights. Based on the application scenarios of the petrochemical industry enterprises, the current application scenario is determined by the application scenario automatic identification model, and the relevant data in the scenario database is analyzed by natural language processing to extract the green and low-carbon requirements and constraints under each application scenario. Based on the requirements and constraints, the evaluation index is refined into multi-level sub-evaluation indexes. The evaluation objectives, evaluation indicators, and sub-evaluation indicators are quantified using a life cycle assessment method. The quantified evaluation objectives, evaluation indicators, and sub-evaluation indicators are then combined with the calibrated weights to construct an evaluation system.

2. The method for constructing a green and low-carbon evaluation index system for the petrochemical industry according to claim 1, characterized in that, For each evaluation objective, based on the full-process management of the petrochemical industry enterprise, at least one evaluation indicator is formulated that is related to and supports the evaluation objective, including: Identify green strategies that contribute to green and low-carbon requirements at each stage of the entire process management; Based on the green strategy, corresponding evaluation indicators are set for each stage of the whole process management; The green strategies for the site selection phase include entering compliant industrial parks and staying away from environmental protection targets; for the design phase, green strategies include using environmentally friendly raw materials, auxiliary materials and fuels, optimizing designs to reduce fossil fuel use and improve energy efficiency; for the construction phase, green strategies include using energy-saving production equipment, reducing waste generation, and improving energy utilization efficiency; for the operation phase, green strategies include improving the operational efficiency of petrochemical companies and reducing energy consumption and emissions during operation; and for the maintenance phase, green strategies include optimizing maintenance plans, extending service life, and reducing energy consumption during maintenance.

3. The method for constructing a green and low-carbon evaluation index system for the petrochemical industry according to claim 1, characterized in that, Based on the green and low-carbon indicators and environmental impact indicators of the petrochemical industry enterprises, the initial weights of all evaluation indicators are obtained using the analytic hierarchy process (AHP), including: A hierarchical model is constructed, which includes a target layer, a criterion layer, and an indicator layer. The target layer is the overall target for green and low-carbon evaluation of petrochemical enterprises, the criterion layer is the intermediate link supporting the realization of the target layer, and the indicator layer is refined into quantifiable green and low-carbon indicators and environmental impact indicators. Based on expert knowledge, pairwise comparisons are made between the relative importance of each criterion within the criterion layer and between each indicator within the indicator layer, and a judgment matrix is ​​constructed using the scaling method. The maximum eigenvalue and corresponding eigenvector of each judgment matrix are calculated using the eigenvalue method, and then normalized to obtain the weight vector of each level element relative to the previous level element. Calculate the consistency index CI for each judgment matrix, and compare the consistency index CI of each judgment matrix with the average random consistency index RI to obtain the consistency ratio CR. When the consistency ratio CR is less than a preset threshold, the judgment matrix meets the consistency condition, and the weight obtained at this time is used as the initial weight. Otherwise, the judgment matrix is ​​adjusted by modifying the score of the relative importance of each element in the judgment matrix until the consistency requirement is met, and the initial weight is obtained.

4. The method for constructing a green and low-carbon evaluation index system for the petrochemical industry according to claim 1, characterized in that, A correction factor is constructed based on the ratio of the actual environmental impact intensity to the initial predicted environmental impact intensity. The initial weights are then iteratively calibrated using this correction factor to obtain the calibrated weights, including: The life cycle assessment method is used to collect data on the entire process of petrochemical enterprises, including energy consumption data, waste gas and wastewater pollutant emission data, and resource recycling rate data at each stage. A weighted adjustment model is constructed, using the ratio of the actual environmental impact intensity to the initial predicted environmental impact intensity of each indicator as the adjustment factor. ; The constraint condition for setting the correction factor is 0.5 ≤ ≤2.0, if exceeded, the boundary value is used; Substituting the correction factor into the hierarchical single ranking process of the analytic hierarchy process, the initial weights are adjusted, and a consistency check is performed to ensure that the consistency ratio CR < 0.1, resulting in the calibrated weights. The formula for calculating the calibrated weights is as follows: In the formula, The weight after calibration for the i-th indicator. Let be the initial analytic hierarchy process weights for the i-th indicator. Let i be the weight adjustment factor for the i-th indicator. The total number of indicators in the sub-evaluation indicator layer.

5. The method for constructing a green and low-carbon evaluation index system for the petrochemical industry according to claim 1, characterized in that, Based on the application scenarios of the petrochemical industry enterprises, an automatic application scenario identification model is used to determine the current application scenario. Natural language processing is then used to parse relevant data from the scenario database to extract the green and low-carbon requirements and constraints for each scenario, including: A database of green and low-carbon evaluation scenarios for petrochemical enterprises will be constructed. Industry standard data, enterprise information disclosure data, environmental management platform data and enterprise-side data will be captured from public data sources and platform interfaces to form characteristic parameters for three major categories of scenarios: enterprise application, public application and management application. A support vector machine learning algorithm is used to construct an automatic scene matching and recognition model using the feature parameters in the scene database as training samples. The input of the automatic scene matching and recognition model is the basic information of the object to be evaluated, and the output is the matching application scene type. Based on the automatic identification and matching of scenario types, natural language processing is used to parse relevant data in the scenario database, extract keywords for green and low-carbon evaluation requirements under each scenario, and multi-source data fusion technology is used to integrate industry production data, monitoring data and industry standard data to extract constraint boundaries and obtain the requirements and constraints of each scenario.

6. The method for constructing a green and low-carbon evaluation index system for the petrochemical industry according to claim 5, characterized in that, Based on the aforementioned requirements and constraints, the evaluation indicators are refined into multi-level sub-evaluation indicators, including: A sub-evaluation index database is constructed, and sub-evaluation indicators for each evaluation objective are formed based on industry standard data of the petrochemical industry and relevant industry and enterprise data captured under the evaluation objectives. By using association rule mining algorithms, an association mapping model of scenario requirements, constraints, and evaluation indicators is established. A hierarchical clustering algorithm is used to automatically decompose and generate multi-level sub-evaluation indicators based on the original evaluation objectives and combined with the evaluation requirements of the scenario. A real-time data optimization and adjustment mechanism is introduced, which connects to the regulatory platform data and industry standard data of the petrochemical industry to automatically verify the rationality of the sub-evaluation indicators. When the scenario requirements or constraints change, the associated mapping model is triggered to automatically update the sub-evaluation indicators.

7. The method for constructing a green and low-carbon evaluation index system for the petrochemical industry according to claim 1, characterized in that, The application scenarios include enterprise applications, public applications, and management applications; Among them, the requirements for enterprise applications include high energy efficiency, high stability, and low cost, while the constraints include pollution emissions, resource and energy consumption, waste management, and recycling. Requirements for public applications include ease of installation and maintenance, while constraints include environmental impact limits, pollution emissions, resource and energy consumption, and the impact of daily operation and maintenance. The requirements for management applications include scientific rigor, comprehensiveness, low pollution, and low consumption, while the constraints include high requirements for green and low-carbon practices and comprehensiveness. Furthermore, the content of the multi-level sub-evaluation indicators differs for different application scenarios: the sub-evaluation indicators for enterprise applications focus on energy efficiency and carbon emission indicators in the design, construction, operation, and maintenance phases; the sub-evaluation indicators for public applications focus on general indicators in the site selection, construction, operation, and maintenance phases; and the sub-evaluation indicators for management applications, in addition to those for public applications, further include risk prevention measures and changes in pollutant emissions after the project has been operating stably.

8. The method for constructing a green and low-carbon evaluation index system for the petrochemical industry according to claim 1, characterized in that, When using the life cycle assessment method to quantify the assessment objectives, assessment indicators, and sub-assessment indicators, for indicators whose weight percentage in the calibrated weights is higher than a preset threshold, the data collection accuracy and time span of their sub-assessment indicators are improved during the life cycle assessment quantification process; for indicators whose weight percentage in the calibrated weights is lower than a preset threshold, the life cycle assessment quantification process is optimized while ensuring data accuracy.

9. The method for constructing a green and low-carbon evaluation index system for the petrochemical industry according to claim 1, characterized in that, The multi-level sub-evaluation indicators include at least the following quantitative indicators: carbon dioxide emissions per ton of crude oil processed, comprehensive energy consumption per unit of oil refining, comprehensive energy consumption per unit of ethylene product, crude oil processing loss rate, industrial wastewater reuse rate, comprehensive utilization rate of industrial solid waste, proportion of clean transportation of bulk materials within the plant area, level of nitrogen oxide treatment technology in heating furnaces, and level of source control of fugitive VOCs in storage tanks.

10. A system for constructing a green and low-carbon evaluation index system for the petrochemical industry, used to implement the method as described in any one of claims 1 to 9, characterized in that, The system includes: The evaluation target setting module is configured to set evaluation targets based on the green and low-carbon needs of petrochemical enterprises. The evaluation targets include one or more combinations of reducing carbon emissions, improving resource utilization efficiency, reducing energy consumption, reducing pollutant generation and emissions, reducing environmental pollution, and improving environmental management level. The evaluation indicator formulation module is configured to formulate at least one evaluation indicator that is related to and supports the evaluation target for each evaluation target, based on the whole process management of the petrochemical industry enterprise. The whole process management includes the site selection stage, design stage, construction stage, operation and maintenance stage. The weight determination module is configured to obtain the initial weights of all evaluation indicators based on the green and low-carbon indicators and environmental impact indicators of the petrochemical industry enterprises using the analytic hierarchy process (AHP). The green and low-carbon indicators characterize the environmental friendliness and resource utilization efficiency of the petrochemical industry enterprises in their whole-process management, while the environmental impact indicators characterize the comprehensive environmental impact of the petrochemical industry enterprises in their whole-process management. The evaluation indicators are quantitatively analyzed using a life cycle assessment method to obtain the actual environmental impact intensity. A correction factor is constructed based on the ratio of the actual environmental impact intensity to the initially predicted environmental impact intensity. The initial weights are then iteratively calibrated using the correction factor to obtain the calibrated weights. The refined evaluation index module is configured to determine the current application scenario based on the application scenario of the petrochemical industry enterprise using an application scenario automatic identification model, and to extract the green and low-carbon requirements and constraints under each application scenario by parsing relevant data in the scenario database through natural language processing, and to refine the evaluation index into multi-level sub-evaluation indexes based on the requirements and constraints. The system construction module is configured to use a life cycle assessment method to quantify the evaluation objectives, evaluation indicators and sub-evaluation indicators, and combine the quantified evaluation objectives, evaluation indicators and sub-evaluation indicators with the calibrated weights to construct an evaluation system.

Images