A method and system for evaluating the carbon reduction effect of technical transformation of power generation equipment

Abstract

The application discloses a kind of carbon reduction effect evaluation method and system for power generation equipment technical reformation, belong to electric power engineering and carbon emission assessment technical field.The application is through systematization collection and pretreatment before, after multiple source operation data of power generation equipment technical reformation;Build the multistage evaluation index system including equipment energy efficiency, carbon emission, economy and environmental benefit four dimensions;Adopt analytic hierarchy process to determine index weight, and based on weighted comprehensive score model calculation comprehensive evaluation score;According to the score, divide carbon reduction effect grade, and establish periodic dynamic tracking and feedback mechanism.The application guarantees the accuracy of evaluation basis by standardizing data processing;Rely on dynamic monitoring realizes long-term tracking and closed-loop management to reformation effect, provides reliable tool for benefit evaluation and optimization operation of power generation equipment technical reformation.The application solves the technical problems of single evaluation index, insufficient data accuracy and lack of dynamic tracking capability in the prior art.

Description

Technical Field

[0001] This invention belongs to the field of power engineering and carbon emission assessment technology, specifically a method and system for evaluating the carbon reduction effect of technical transformation of power generation equipment. Background Technology

[0002] The power generation industry is a major sector of energy consumption and greenhouse gas emissions, accounting for a significant proportion of global carbon emissions. Promoting energy-saving and carbon-reducing technological upgrades for power generation equipment is a crucial path for the power industry to achieve a green and low-carbon transformation and reach its "dual-carbon" strategic goals. A scientific, accurate, and comprehensive evaluation of the carbon reduction effects of technological upgrade projects is not only related to assessing the investment benefits of the projects themselves, but also an important basis for industry carbon emission statistics and accounting, emission reduction potential analysis, and the formulation and assessment of relevant policies.

[0003] Currently, there are still several prominent issues that urgently need to be addressed in evaluating the carbon reduction effects of technological upgrades to power generation equipment, both in terms of theoretical methods and practical applications: The evaluation dimensions are one-sided, and the indicator system is incomplete. Many existing evaluation methods often focus on a direct comparison of total carbon emissions before and after the transformation, or only examine a single core indicator such as carbon emission intensity per unit of electricity generation. Such methods ignore the fact that technological transformation is a systemic project, and its effects are not only reflected in direct carbon emission reduction, but also profoundly affect the operational energy efficiency, long-term economics, and comprehensive benefits to the surrounding environment of the equipment.

[0004] The weak data foundation leads to insufficient reliability of evaluation results. Accurate evaluation relies on high-quality data support. Currently, the data sources required for evaluation are diverse, including distributed control systems, plant-level monitoring information systems, electricity metering systems, and environmental online monitoring systems, resulting in issues such as inconsistent data formats, different sampling frequencies, and asynchronous timestamps. In the data acquisition and processing stages, effective cleaning, alignment, and outlier handling mechanisms are often lacking, leading to data quality problems due to sensor errors, communication interruptions, or human recording bias.

[0005] There is a lack of dynamic tracking and feedback mechanisms. Most existing evaluations are "post-hoc" or "one-off" static assessments, meaning the effectiveness is verified at a specific time after the upgrade is completed. As a complex, continuously operating system, power generation equipment's performance and emission characteristics dynamically evolve with equipment aging, fuel characteristic fluctuations, operational mode adjustments, and changes in environmental conditions. One-off static evaluations cannot capture the long-term decline trends, seasonal fluctuations, or operational parameter drift of the technological upgrade's effects.

[0006] In summary, existing technologies for evaluating the carbon reduction effects of technological upgrades to power generation equipment generally suffer from problems such as a single evaluation perspective, insufficient data quality control, and a static and isolated evaluation process. Therefore, there is an urgent need to propose a new evaluation method and system that can ensure the accuracy and standardization of data processing and achieve long-term dynamic tracking and intelligent feedback of carbon reduction effects. Summary of the Invention

[0007] To address the above problems, this invention provides a method and system for evaluating the carbon reduction effect of technological upgrades to power generation equipment, which solves the problems of a single price perspective, insufficient data quality control, and a static and isolated evaluation process.

[0008] To achieve the above objectives, the present invention adopts the following technical solution: A carbon reduction effect evaluation system for technological transformation of power generation equipment includes a data acquisition and preprocessing module, an indicator system construction module, a weight determination module, a comprehensive evaluation model module, a grade classification and evaluation module, and a dynamic tracking and feedback module. The output of the data acquisition and preprocessing module is connected to the input of the indicator system construction module, and is used to provide it with preprocessed periodic operation data of the power generation equipment before, during and after the technical transformation. The output of the indicator system construction module is connected to the input of the weight determination module and the comprehensive evaluation model module, and is used to provide the constructed multi-level evaluation indicator system; The output of the weight determination module is connected to the input of the comprehensive evaluation model module, and is used to provide the calculated weights of each evaluation indicator. The output of the comprehensive evaluation model module is connected to the input of the grading and evaluation module, and is used to provide a comprehensive evaluation score of the carbon reduction effect of power generation equipment technical transformation. The output of the grading and evaluation module is connected to the input of the dynamic tracking and feedback module, and is used to provide the carbon reduction effect grading results based on the comprehensive evaluation score. The dynamic tracking and feedback module receives periodic operation data from the data acquisition and preprocessing module, and performs dynamic evaluation and feedback adjustments based on the current and historical evaluation results of the level classification and evaluation module.

[0009] A further improvement of this invention is that the data acquisition and preprocessing module is specifically used for: acquiring static basic data before the technical transformation of the power generation equipment. Including equipment model and rated power Fuel type and historical running dataset ; Data collection of renovation plans during the renovation process Technical parameters adopted and renovation costs ; Collect real-time operational data after the upgrade Including real-time power generation Real-time fuel consumption Real-time pollutant emissions and equipment operating status parameters ; The collected static basic data before the modification Data on renovation plans Technical parameters Cost of renovation and real-time operation data after the modification Perform preprocessing operations such as data cleaning, outlier removal, and missing value interpolation.

[0010] A further improvement of this invention is that the indicator system construction module constructs a multi-level evaluation indicator system containing four primary indicators based on the preprocessed data: This refers to equipment energy efficiency indicators, with secondary indicators including the rate of change in power generation efficiency. thermal efficiency change rate and the rate of change of plant power consumption ; The carbon emission indicator has two sub-indicators, including the rate of change in carbon emissions per unit of electricity generated. Total carbon emission reduction and carbon emission intensity reduction rate ; As an economic indicator, its sub-indicators include the investment payback period for renovation. Unit carbon emission reduction cost and internal rate of return (IRR); As an environmental benefit indicator, its sub-indicators include reductions in other pollutants. and ecological environment impact index .

[0011] A further improvement of this invention is that the weight determination module uses the analytic hierarchy process (AHP) to determine the weights of each indicator, specifically including: constructing a three-layer hierarchical structure model: the target layer is the evaluation of the carbon reduction effect of the technical transformation of the target power generation equipment, and the criterion layer is the four primary indicators. The solution layer consists of secondary indicators under each primary indicator; the criterion layer constructs a judgment matrix for the target layer using expert scoring. And the judgment matrix of each scheme layer to its corresponding criterion layer; calculate the eigenvector of each judgment matrix and normalize it to obtain the first-level index weight vector. The weights of each secondary indicator and its local weight vector under its primary indicator are calculated; by combining the weights, the global weight of each secondary indicator relative to the target layer is obtained. .

[0012] A further improvement of the present invention is that the comprehensive evaluation model module includes: Data standardization units are established by using either range standardization or Z-score standardization to normalize the raw values ​​of each secondary indicator. The data is processed to obtain standardized scores. ; The weighted comprehensive scoring unit, based on the global weights and the corresponding standardized score Calculate the overall evaluation score E using the following formula: , where n is the total number of secondary indicators.

[0013] A further improvement of this invention is that the grading and evaluation module has a preset threshold for carbon reduction effect levels: when When the carbon reduction effect was rated as "excellent", when When the carbon reduction effect is rated as "good"; when At that time, the carbon reduction effect was rated as "moderate"; when At that time, the carbon reduction effect was rated as "poor"; among them, , , .

[0014] A further improvement of the present invention is that the dynamic tracking and feedback module includes: The dynamic monitoring unit collects the real-time operating data after the modification at a fixed period T. ; The trend analysis unit is based on a comprehensive evaluation score over multiple consecutive periods T. For the sequence, calculate its slope k. If k is less than a preset negative trend threshold... If so, a warning signal will be triggered; The feedback execution unit generates a feedback report containing specific indicator degradation analysis and adjustment suggestions based on the warning signal and the current level evaluation result, and sends it to the equipment management system.

[0015] A further improvement of this invention is that it also includes a machine learning optimization module, the input of which is connected to the output of the dynamic tracking and feedback module, for receiving historical operating data, historical evaluation results, and feedback adjustment records; the machine learning optimization module dynamically optimizes the indicator weight vector in the weight determination module by training a prediction model. The rating thresholds in the rating classification and evaluation module enable the evaluation system to adapt to the specific type of power generation equipment and its operating environment.

[0016] A method for evaluating the carbon reduction effect of technological upgrades to power generation equipment includes the following steps: S1: Collect and preprocess data, including: static basic data of power generation equipment before technical transformation, including equipment model, rated power, fuel type and historical operating data; transformation scheme data, technical parameters adopted and transformation investment cost during the transformation process; and real-time operating data of power generation equipment after transformation, including real-time power generation, real-time fuel consumption, real-time pollutant emissions and equipment operating status parameters. S2: Based on the data preprocessed in step S1, construct a multi-level evaluation index system containing four primary indicators. The primary indicator is the equipment energy efficiency indicator, and its secondary indicators include the rate of change in power generation efficiency. thermal efficiency change rate and the rate of change of plant power consumption The second-level indicator is the carbon emission indicator, and its sub-sub-indicators include the rate of change in carbon emissions per unit of electricity generated. Total carbon emission reduction and carbon emission intensity reduction rate The third-level indicators are economic indicators, and their sub-secondary indicators include the payback period for renovation investment. Unit carbon emission reduction cost And the internal rate of return (IRR); the fourth level indicator is the environmental benefit indicator, whose sub-secondary indicators include the reduction of other pollutants. and ecological environment impact index ; S3: Use the Analytic Hierarchy Process (AHP) to determine the global weight of each second-level indicator in the multi-level evaluation index system described in step S2. The analytic hierarchy process includes: constructing a hierarchical structure model with three layers: target layer, criterion layer, and scheme layer; constructing a judgment matrix using expert scoring; calculating and normalizing the eigenvectors of each judgment matrix to obtain the weights of each level of indicators; S4: The original values ​​of each second-level indicator collected and preprocessed in step S1. Standardization is performed to obtain standardized scores. The weighted comprehensive scoring method is adopted, based on the formula. Calculate the comprehensive evaluation score E for the carbon reduction effect of the technical transformation of the power generation equipment, where n is the total number of second-level indicators; S5: Compare the comprehensive evaluation score E obtained in step S4 with the preset level threshold: if E≥85, the carbon reduction effect is rated as excellent; if 70≤E<85, it is rated as good; if 55≤E<70, it is rated as medium; if E<55, it is rated as poor.

[0017] A further improvement of this invention is that it also includes step S6, dynamic evaluation and adjustment, by repeatedly executing steps S1 to S5 at a fixed period T to generate a time series. ;analyze The trend, if the slope k of the change is less than a preset negative trend threshold. Then, the key indicators that cause the degradation are identified; based on the historical data and current status of the key indicators, targeted suggestions for adjusting equipment operating parameters or maintenance strategies are generated, and the effects of the adjustments are verified.

[0018] Compared with the prior art, the present invention has at least the following beneficial technical effects: This invention provides a method and system for evaluating the carbon reduction effect of technological upgrades to power generation equipment. Through modular system design, it achieves a complete automated process from data acquisition, indicator construction, weight allocation, comprehensive evaluation to dynamic tracking, ensuring the comprehensiveness, scientific rigor, and continuity of the evaluation process. This effectively solves the problems of single evaluation dimensions, static assessment, and delayed feedback in existing technologies. The dynamic tracking and feedback mechanism of this technology involves continuously collecting data at a fixed period T and repeating the evaluation process to form a time series of carbon reduction effects. Through trend analysis, the system automatically and promptly detects whether the carbon reduction effect shows a decline trend and triggers an early warning. This overcomes the shortcomings of traditional "one-time" evaluations that cannot reflect long-term operational effects, achieving full life-cycle monitoring and proactive early warning of the benefits of technological upgrades. Attached Figure Description

[0019] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0020] Figure 1 This is a structural block diagram of a carbon reduction effect evaluation system for technological upgrades of power generation equipment; Figure 2 This is a flowchart of a method for evaluating the carbon reduction effect of technological upgrades to power generation equipment. Detailed Implementation

[0021] In the following description, only certain exemplary embodiments are briefly described. As those skilled in the art will recognize, the described embodiments can be modified in various ways without departing from the spirit or scope of the invention. Therefore, the drawings and description are considered to be exemplary in nature and not restrictive.

[0022] In the description of this invention, it should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0023] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0024] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0025] The accompanying drawings illustrate various structural schematic diagrams according to embodiments disclosed in this invention. These drawings are not to scale, and some details have been enlarged for clarity, and some details may have been omitted. The shapes of the various regions and layers shown in the drawings, as well as their relative sizes and positional relationships, are merely exemplary and may deviate from reality due to manufacturing tolerances or technical limitations. Furthermore, those skilled in the art can design regions / layers with different shapes, sizes, and relative positions as needed.

[0026] The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0027] Example 1 The system is deployed in the power plant data center or cloud server, and its hardware infrastructure includes data acquisition servers, application servers, database servers and network equipment.

[0028] See attached document Figure 1 A carbon reduction effect evaluation system for technological transformation of power generation equipment includes a data acquisition and preprocessing module, an indicator system construction module, a weight determination module, a comprehensive evaluation model module, a grade classification and evaluation module, and a dynamic tracking and feedback module.

[0029] The output of the data acquisition and preprocessing module is connected to the input of the indicator system construction module to provide it with preprocessed periodic operation data of the power generation equipment before, during and after the technical transformation.

[0030] The output of the indicator system construction module is connected to the input of the weight determination module and the comprehensive evaluation model module. It is used to provide the constructed multi-level evaluation indicator system. The system adopts a two-level hierarchical structure, covering four dimensions: energy efficiency, carbon emissions, economic efficiency, and environmental benefits, providing a quantitative basis for evaluating carbon reduction effects. The weight determination module outputs the global weights of each indicator.

[0031] The output of the weight determination module is connected to the input of the comprehensive evaluation model module. It is used to provide the calculation weights of each evaluation indicator and is the core basic parameter for calculating the comprehensive evaluation score and conducting the grade assessment.

[0032] The output of the comprehensive evaluation model module is connected to the input of the grading and evaluation module to provide a comprehensive evaluation score E for the carbon reduction effect of power generation equipment technical transformation.

[0033] The output of the grading and evaluation module is connected to the input of the dynamic tracking and feedback module to provide carbon reduction effect grading results based on the comprehensive evaluation score E.

[0034] The dynamic tracking and feedback module receives periodic operational data from the data acquisition and preprocessing module, and performs dynamic evaluation and feedback adjustments based on the current and historical evaluation results from the grading and evaluation module.

[0035] Data Acquisition and Preprocessing Module: This module includes standardized data interfaces with the power plant's Distributed Control System (DCS), System-on-System (SIS), and Management Information System (MIS). It incorporates a data validation rule library and interpolation algorithm library, enabling it to automatically perform data cleaning, filtering, and completion tasks, outputting structured standard data packets. Specifically, the Data Acquisition and Preprocessing module is used to collect static basic data prior to the technical upgrade of power generation equipment. Including equipment model and rated power Fuel type and historical running dataset Collect data on the renovation plan during the renovation process. Technical parameters adopted and renovation costs Collect real-time operational data after the upgrade. Including real-time power generation Real-time fuel consumption Real-time pollutant emissions and equipment operating status parameters The collected static basic data before the modification Data on renovation plans Technical parameters Cost of renovation and real-time operation data after the modification Perform preprocessing operations such as data cleaning, outlier removal, and missing value interpolation.

[0036] The indicator system construction module builds four primary indicators based on the preprocessed data. Multi-level evaluation index system: This refers to equipment energy efficiency indicators, with secondary indicators including the rate of change in power generation efficiency. thermal efficiency change rate and the rate of change of plant power consumption ; The carbon emission indicator has two sub-indicators, including the rate of change in carbon emissions per unit of electricity generated. Total carbon emission reduction and carbon emission intensity reduction rate ; As an economic indicator, its sub-indicators include the investment payback period for renovation. Unit carbon emission reduction cost and internal rate of return (IRR); As an environmental benefit indicator, its sub-indicators include reductions in other pollutants. and ecological environment impact index .

[0037] The weight determination module uses the analytic hierarchy process (AHP) to determine the weights of each indicator. Specifically, it includes constructing a three-layer hierarchical model: the target layer is for evaluating the carbon reduction effect of technical upgrades to target power generation equipment, and the criterion layer consists of the four primary indicators. The solution layer consists of secondary indicators under each primary indicator; the criterion layer constructs a judgment matrix for the target layer using expert scoring. And the judgment matrix of each scheme layer for its corresponding criterion layer. Calculate and normalize the eigenvectors of each judgment matrix to obtain the first-level indicator weight vector. The weights of each secondary indicator and its local weight vector under its primary indicator are calculated; by combining the weights, the global weight of each secondary indicator relative to the target layer is obtained. .

[0038] The comprehensive evaluation model module specifically executes the following: Data standardization unit, using either range standardization or Z-score standardization to standardize the raw values ​​of each secondary indicator. The data is processed to obtain standardized scores. The weighted comprehensive scoring unit, based on the global weights... and the corresponding standardized score Calculate the overall evaluation score E using the following formula: , where n is the total number of secondary indicators.

[0039] The grading and evaluation module has preset carbon reduction effect grading thresholds L1~L4: when When the carbon reduction effect was rated as "excellent", when When the carbon reduction effect is rated as "good"; when At that time, the carbon reduction effect was rated as "moderate"; when At that time, the carbon reduction effect was rated as "poor"; among them, , , .

[0040] The dynamic tracking and feedback module includes a dynamic monitoring unit that collects real-time operational data after the modification at a fixed period T. Trend analysis unit, based on the comprehensive evaluation score of multiple consecutive periods T. For the sequence, calculate its slope k. If k is less than a preset negative trend threshold... If the warning signal is triggered, the feedback execution unit generates a feedback report containing specific indicator degradation analysis and adjustment suggestions based on the warning signal and the current level evaluation result, and sends it to the equipment management system.

[0041] It also includes a machine learning optimization module, whose input is connected to the output of the dynamic tracking and feedback module, for receiving historical operating data, historical evaluation results, and feedback adjustment records; the machine learning optimization module dynamically optimizes the indicator weight vector in the weight determination module by training a prediction model. The grade thresholds L1 to L3 in the grade classification and evaluation module enable the evaluation system to adapt to the specific type of power generation equipment and the operating environment.

[0042] Example 2 This embodiment uses a comprehensive renovation project of a 600MW coal-fired boiler for low-NOx combustion and flue gas purification system as an example to explain in detail the implementation process of the evaluation method of this invention, with reference to the appendix. Figure 2 .

[0043] A method for evaluating the carbon reduction effect of technological upgrades to power generation equipment includes the following steps: S1: Collect and preprocess data, including: static basic data of power generation equipment before technical transformation, including equipment model, rated power, fuel type and historical operating data; transformation scheme data, technical parameters adopted and transformation investment cost during the transformation process; and real-time operating data of power generation equipment after transformation, including real-time power generation, real-time fuel consumption, real-time pollutant emissions and equipment operating status parameters. S2: Based on the data preprocessed in step S1, construct a multi-level evaluation index system containing four primary indicators. The primary indicator is the equipment energy efficiency indicator, and its secondary indicators include the rate of change in power generation efficiency. thermal efficiency change rate and the rate of change of plant power consumption The second-level indicator is the carbon emission indicator, and its sub-sub-indicators include the rate of change in carbon emissions per unit of electricity generated. Total carbon emission reduction and carbon emission intensity reduction rate The third-level indicators are economic indicators, and their sub-secondary indicators include the payback period for renovation investment. Unit carbon emission reduction cost And the internal rate of return (IRR); the fourth level indicator is the environmental benefit indicator, whose sub-secondary indicators include the reduction of other pollutants. and ecological environment impact index ; S3: Use the Analytic Hierarchy Process (AHP) to determine the global weight of each second-level indicator in the multi-level evaluation index system described in step S2. The analytic hierarchy process includes: constructing a hierarchical structure model with three layers: target layer, criterion layer, and scheme layer; constructing a judgment matrix using expert scoring; calculating and normalizing the eigenvectors of each judgment matrix to obtain the weights of each level of indicators; S4: The original values ​​of each second-level indicator collected and preprocessed in step S1. Standardization is performed to obtain standardized scores. The weighted comprehensive scoring method is adopted, based on the formula. Calculate the comprehensive evaluation score E for the carbon reduction effect of the technical transformation of the power generation equipment, where n is the total number of second-level indicators; S5: Compare the comprehensive evaluation score E obtained in step S4 with the preset level threshold: if E≥85, the carbon reduction effect is rated as excellent; if 70≤E<85, it is rated as good; if 55≤E<70, it is rated as moderate; if E<55, it is rated as poor. S6: Repeat steps S1 to S5 at a fixed period T to obtain the comprehensive evaluation score of the time series. Analysis of the above If the slope k of the change trend is less than the preset negative trend threshold, then... Then, a feedback report containing specific indicator degradation analysis and adjustment suggestions is generated and sent to the equipment management system.

[0044] Step S1 includes at least steps S110 to S130: S110. Collect multi-source operation and static data of power generation equipment before, during and after technical transformation, and perform data cleaning and screening to obtain clean data. The data collected included static baseline data and historical operating data of the power generation equipment before the technical upgrade, data on the upgrade plan and costs, and real-time operating data after the upgrade. Specifically, for a 600 MW subcritical coal-fired power generating unit, the static baseline data before the technical upgrade included equipment model N600-16.7 / 538 / 538, rated power 600 MW, and fuel type bituminous coal. The historical operating data before the technical upgrade covered the 24 months prior to the upgrade, including total power generation of 7.2 × 10^9 kWh, total fuel consumption of 2.4 × 10^6 tons, total carbon emissions of 6.0 × 10^6 tons, average power generation efficiency of 35.5%, average thermal efficiency of 87.5%, and average plant power consumption rate of 7.8%. The data on the technical upgrade process included the upgrade plan of upgrading the turbine flow path and the total cost of the upgrade, amounting to 180 million yuan. The real-time operation data collection period after the technical upgrade is twelve months. The data includes total power generation of 3.9×10^9 kWh, total fuel consumption of 1.26×10^6 tons, total carbon emissions of 3.15×10^6 tons, average power generation efficiency of 37.2%, average thermal efficiency of 89.0%, average plant power consumption rate of 7.2%, total sulfur dioxide emission reduction of 2,800 tons, and total nitrogen oxide emission reduction of 2,200 tons.

[0045] The multi-source operational and static data enters the data cleaning and filtering process after collection. Specifically, the historical operational data undergoes integrity verification, and three days of missing plant power consumption rate records are identified. These are then interpolated using the arithmetic mean of the same load conditions over ten consecutive days. The real-time operational data after the upgrade undergoes outlier detection and removal. The rule is set as follows: if the generator's active power is less than 20% of its rated power and this condition persists for more than two hours, it is considered an abnormal condition, and all data for that period is removed. Five abnormal records were removed according to this rule. Static data such as upgrade investment costs undergo unit standardization and format normalization. After cleaning and filtering, clean data is output, which has had outliers removed, missing data filled, and has consistent time sequence identifiers and data formats.

[0046] S120. Perform dimension unification and interpolation completion processing on the cleaning data to obtain regularized data; The clean data is read, and all continuous variables are standardized in terms of units. Specifically, power generation is standardized to kilowatt-hours, fuel consumption to tons, carbon emissions to tons, efficiency and ratios to percentage values, and monetary costs to yuan. For the plant power consumption rate data completed by S110 interpolation, a second verification is performed to ensure that the data trend before and after the interpolation point is smooth and that no abrupt changes are introduced. For other time-series data that may have slight discontinuities, linear interpolation is used for final completion to ensure that all time series are continuous and uninterrupted. After processing, a well-organized dataset is formed, in which all variables have consistent units, the time series is continuous and complete, and it can be directly used for subsequent indicator calculations.

[0047] S130. The regularized data is partitioned and indexed according to the time periods before and after the transformation to generate a standardized data sequence. The standardized data is stored in partitions according to the time period from which it originates. Specifically, it is divided into three data zones: Zone 1 stores historical standardized data for the 24 months prior to the renovation; Zone 2 stores static standardized data during the renovation process; and Zone 3 stores real-time standardized data for the 12 months following the renovation. Independent time-series indexes and data field indexes are established for each data zone. The time-series index is accurate to the day, supporting rapid data extraction by time range. The data field index clearly labels the name, unit, and attributes of each field. Simultaneously, key performance parameters, such as power generation efficiency and carbon emissions per unit of power generation, are pre-calculated and cached according to their respective time periods (before / after renovation) to accelerate subsequent indicator calculation processes. Finally, a standardized data sequence is generated, which is a structured data set with time-series and field indexes, for direct use in step S200. After the above-mentioned standardized data sequence is generated, explicit references are established: First, the pre-calculated results of performance parameters before and after the modification are provided to S210 to calculate the relative change rate of equipment energy efficiency indicators and carbon emission indicators; Second, the cost data of the modification process and the operation data after the modification are provided to S220 to calculate economic indicators; Third, the index of all standardized data sequences is provided to S600 to support rapid data retrieval during periodic dynamic evaluation.

[0048] Step S2 includes at least steps S210 to S230: S210. Based on the standardized data sequence, calculate the original values ​​of the secondary indicators of equipment energy efficiency index and carbon emission index; Read the pre-calculated performance parameters before and after the modification from the standardized data sequence. Calculate the secondary indicator under the equipment energy efficiency index: the rate of change in power generation efficiency. =(Average power generation efficiency after renovation - Average power generation efficiency before renovation) / Average power generation efficiency before renovation × 100% = (37.2% - 35.5%) / 35.5% × 100% = 4.79%; Thermal efficiency change rate =(89.0%-87.5%) / 87.5%×100%=1.71%; Plant power consumption rate change rate =Average plant power consumption rate after renovation - Average plant power consumption rate before renovation = 7.2% - 7.8% = -0.6%. Calculate the secondary indicators under the carbon emission index: Carbon emissions per unit of electricity generated before renovation Cpre = Total carbon emissions before renovation / Total electricity generated before renovation = 6.0 × 10^6 tons / 7.2 × 10^9 kWh = 0.833 kg / kWh; Carbon emissions per unit of electricity generated after renovation Cpost = Total carbon emissions after renovation / Total electricity generated after renovation = 3.15 × 10^6 tons / 3.9 × 10^9 kWh = 0.808 kg / kWh; Rate of change of carbon emissions per unit of electricity generated. =(Cpost-Cpre) / Cpre×100%=(0.808-0.833) / 0.833×100%=-3.00%; Total carbon emission reduction =Annualized carbon emissions before renovation - Annualized carbon emissions after renovation = (6.0 × 10^6 tons / 2) - 3.15 × 10^6 tons = -1.5 × 10^5 tons; The industry benchmark carbon emission intensity is set at 0.85 kg / kWh, and the carbon emission intensity reduction rate... =(Industry Benchmark Value - Cpost) / Industry Benchmark Value × 100% = (0.85 - 0.808) / 0.85 × 100% = 4.94%. Record the calculation result as part of the original set of indicator values.

[0049] S220. Based on the standardized data sequence, calculate the original values ​​of the secondary indicators of economic indicators and environmental benefit indicators; Read the transformation process cost data, post-transformation operation data, and preset parameters from the standardized data sequence. Calculate the secondary indicators under the economic indicators: Set the carbon price Pcarbon to 60 yuan / ton, and the annualized carbon emission reduction benefit R = annualized total carbon emission reduction. ×Pcarbon = (-1.5 × 10^5 tons) × 60 yuan / ton = -9.0 × 10^6 yuan; Investment recovery period for renovation =Total cost of retrofitting / Annualized carbon emission reduction benefit = 1.8 × 10^8 yuan / (-9.0 × 10^6 yuan / year) = -20.0 years; Unit carbon emission reduction cost =Total cost of retrofitting / Total annual carbon emission reduction =1.8 × 10^8 yuan / (-1.5 × 10^5 tons) = -1200 yuan / ton; Based on the cash flow composed of the transformation cost and carbon emission reduction benefits, the internal rate of return (IRR) is calculated to be -2.1% using a financial calculation function. The secondary indicator under the environmental benefit indicators is calculated as: emission reduction of other pollutants. It consists of a reduction of 2,800 tons of sulfur dioxide emissions and a reduction of 2,200 tons of nitrogen oxide emissions; Ecological and environmental impact index The PM2.5 annual average concentration decreased by 3% according to the reports from the air quality monitoring stations around the factory area after the renovation. A score of 70 was assigned based on this 3% decrease. The calculation results were then added to the original set of indicator values.

[0050] S230. Integrate the original values ​​of all secondary indicators to form a set of original values ​​of the indicators to be evaluated; The raw values ​​of all secondary indicators calculated in steps S210 and S220 are integrated to form a complete set to be evaluated. This set includes: =4.79%, =1.71%, =-0.6%, =-3.00%, = -1.5 × 10^5 tons, =4.94%, =-20.0 years, =-1200 yuan / ton, IRR=-2.1%, ={2800 tons, 2200 tons}, =70. This set serves as the direct input to step S4. Simultaneously, the logic for constructing this set is provided to S310 for building the judgment matrix in the analytic hierarchy process, ensuring that weight allocation is based on actual existing indicators.

[0051] Step S3 includes at least steps S310 to S330: S310. Construct a hierarchical model comprising an objective layer, a criterion layer, and a solution layer, and build a judgment matrix using expert scoring; construct a three-layer hierarchical model. The objective layer is defined as a comprehensive evaluation of the carbon reduction effect of power generation equipment technological transformation. The criterion layer includes four primary indicators: equipment energy efficiency indicators. Carbon emission indicators Economic indicators Environmental benefit indicators The scheme layer comprises eleven secondary indicators under the four primary indicators mentioned above. Experts from the power industry and carbon assessment were invited, and the definitions of each indicator and the original numerical values ​​for this example were clarified with them. Based on their experience, the experts compared the importance of the four indicators in the criterion layer relative to the target layer pairwise, using a 1-9 scale to score them. All expert scores were aggregated and a geometric mean was calculated to form an aggregated judgment matrix A. Similarly, the experts compared the secondary indicators under each primary indicator pairwise, forming four aggregated judgment matrices A1, A2, A3, and A4.

[0052] S320. Calculate the eigenvectors and consistency ratios of each judgment matrix. After verification, determine the weights of each level of indicators. Calculate the eigenvectors of the criterion-level judgment matrix A and perform normalization to obtain the first-level indicator weight vectors. The consistency ratio (CR) of matrix A is calculated to be 0.03, which is less than 0.10, thus passing the consistency test. The eigenvectors of matrices A1, A2, A3, and A4 are calculated respectively to obtain the local weight vectors of each secondary indicator under its respective primary indicator. For example, for carbon emission indicator I2, the local weight vectors of its three subordinate secondary indicators are (0.55, 0.30, 0.15). The CR values ​​of all secondary judgment matrices are less than 0.10.

[0053] S330. Perform combined weight calculation to obtain the global weight of each secondary indicator relative to the target layer. ; According to the formula Calculate the global weight for each secondary indicator. Among them, The weight of the primary indicator to which this secondary indicator belongs. This refers to the local weight of the secondary indicator under its primary indicator. For example, the rate of change in carbon emissions per unit of electricity generated. global weight = *0.55=0.42*0.55=0.231. Calculate the global weights of all secondary indicators to form a global weight set { This set will be provided to S410 for weighted composite score calculation.

[0054] Step S4 includes at least S410 to S430: S410. Standardize each value in the original set of indicator values ​​to obtain the standardized score Ri for each indicator; read the original set of indicator values. For each secondary indicator, select an appropriate standardization method based on its attributes (positive indicator, negative indicator, moderate indicator). This example uses the range standardization method. Set a theoretical optimal value (the value corresponding to a full score of 100) and a theoretical worst value (the value corresponding to 0) for each indicator. The original values ​​of each indicator... Substitute into the standardized formula: =( -Worst value) / (Best value - Worst value). After calculation, the standardized score set for each indicator is obtained { }

[0055] S420, Based on the global weight Standardized score The weighted comprehensive scoring method is used to calculate the comprehensive evaluation score E; Perform a weighted composite score calculation. The formula is: , where i iterates through all eleven secondary indicators. Multiply the global weight set { } obtained in step S330 and the standardized score set { } obtained in step S410 one by one according to the indicators and then sum them. After calculation, the comprehensive evaluation score E of the carbon reduction effect in this example is 71.3 points.

[0056] S430. Output the comprehensive evaluation score E; Output the calculated comprehensive evaluation score E = 71.3 points. This score will be directly passed to step S510 for grade classification. At the same time, this score is stored together with the metadata of this evaluation (such as the evaluation object and evaluation period) and provided to step S610 as a historical record for trend analysis.

[0057] Step S5 at least includes steps S510 - S520: S510. Compare the comprehensive evaluation score E with the preset grade thresholds; Read the preset grade thresholds for carbon reduction effect: excellent threshold L1 = 85 points, good threshold L2 = 70 points, medium threshold L3 = 55 points. Compare the input comprehensive evaluation score E = 71.3 points with the thresholds. The comparison logic is: if E ≥ L1, then enter the excellent branch; if L2 ≤ E < L1, then enter the good branch; if L3 ≤ E < L2, then enter the medium branch; if E < L3, then enter the poor branch.

[0058] S520. According to the comparison result, classify and output the carbon reduction effect grade; According to the comparison result in step S510, E = 71.3 points meets the condition L2 ≤ E < L1. Therefore, the carbon reduction effect grade is classified as "good". Output this grade conclusion. This grade conclusion will be used as the final result of this static evaluation and provided to step S620 together with score E for generating a feedback report containing grade information.

[0059] Step S6 at least includes steps S610 - S630: S610. Establish a dynamic monitoring mechanism and repeat steps S100 to S500 at a fixed period T to generate a time series of comprehensive evaluation scores ; Set the fixed evaluation period T to three months. At the end of each period, automatically trigger a complete evaluation process from S100 to S500 to generate the comprehensive evaluation score of this period . Continuously execute four periods, collect the scores and form a time series . In this example, the scores for four consecutive quarters are {71.3, 70.5, 69.8, 68.2}. Store this sequence and its corresponding timestamps.

[0060] S620, for the time series Perform trend analysis, calculate the slope k of its change, and compare it with the negative trend threshold. Compare; Time series A univariate linear regression analysis was performed on the period index {71.3, 70.5, 69.8, 68.2}, with the period index as the independent variable and the score as the dependent variable. The slope k of the regression line was calculated. The calculated k = -1.0 points / period. A negative trend threshold was set. = -0.8 minutes / cycle. Compare k with Since k = -1.0 < =-0.8, triggering the warning condition.

[0061] S630, If k is less than Then, key degradation indicators are located and feedback reports are generated; When warning conditions are triggered, the system identifies the key indicators that led to the recent decline in scores. The specific method involves comparing the standardized scores of each secondary indicator across the two most recent evaluation periods. The two indicators with the largest decreases in score are identified. In this example, the analysis result is the rate of change in plant power consumption rate. and rate of change of thermal efficiency The score drop was most significant for [specific category]. The system generates a feedback report based on predefined rules in the knowledge base. The report includes: early warning (carbon reduction effect shows a diminishing trend), analysis of key deterioration indicators (increased plant power consumption, decreased thermal efficiency), and targeted adjustment suggestions (recommendation to check the circulating water system, turbine cylinder insulation, and leaks in the thermal system). The report is automatically pushed to the power plant equipment management work order system.

[0062] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered illustrative and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the scope of the invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

[0063] Furthermore, it should be understood that although this specification describes embodiments, not every embodiment contains only one independent technical solution. This narrative style is merely for clarity. Those skilled in the art should consider the specification as a whole, and the technical solutions in each embodiment can be appropriately combined to form other embodiments that can be understood by those skilled in the art. The above content is only for illustrating the technical concept of the present invention and should not be construed as limiting the scope of protection of the present invention. Any modifications made based on the technical concept proposed in this invention shall fall within the scope of protection of the claims of this invention.

Claims

1. A carbon reduction effect evaluation system for technological upgrades of power generation equipment, characterized in that, It includes modules for data acquisition and preprocessing, indicator system construction, weight determination, comprehensive evaluation model, grade classification and evaluation, and dynamic tracking and feedback. The output of the data acquisition and preprocessing module is connected to the input of the indicator system construction module, and is used to provide it with preprocessed periodic operation data of the power generation equipment before, during and after the technical transformation. The output of the indicator system construction module is connected to the input of the weight determination module and the comprehensive evaluation model module, and is used to provide the constructed multi-level evaluation indicator system; The output of the weight determination module is connected to the input of the comprehensive evaluation model module, and is used to provide the calculated weights of each evaluation indicator. The output of the comprehensive evaluation model module is connected to the input of the grading and evaluation module, and is used to provide a comprehensive evaluation score of the carbon reduction effect of power generation equipment technical transformation. The output of the grading and evaluation module is connected to the input of the dynamic tracking and feedback module, and is used to provide the carbon reduction effect grading results based on the comprehensive evaluation score. The dynamic tracking and feedback module receives periodic operation data from the data acquisition and preprocessing module, and performs dynamic evaluation and feedback adjustments based on the current and historical evaluation results of the level classification and evaluation module.

2. The carbon reduction effect evaluation system for technical transformation of power generation equipment according to claim 1, characterized in that, The data acquisition and preprocessing module is specifically used for: acquiring static basic data before the technical transformation of power generation equipment. Including equipment model and rated power Fuel type and historical running dataset ; Data collection of renovation plans during the renovation process Technical parameters adopted and renovation costs ; Collect real-time operational data after the upgrade Including real-time power generation Real-time fuel consumption Real-time pollutant emissions and equipment operating status parameters ; The collected static basic data before the modification Data on renovation plans Technical parameters Cost of renovation and real-time operation data after the modification Perform preprocessing operations such as data cleaning, outlier removal, and missing value interpolation.

3. The carbon reduction effect evaluation system for technical transformation of power generation equipment according to claim 2, characterized in that, The indicator system construction module constructs a multi-level evaluation indicator system containing four primary indicators based on the preprocessed data: This refers to equipment energy efficiency indicators, with secondary indicators including the rate of change in power generation efficiency. thermal efficiency change rate and the rate of change of plant power consumption ; The carbon emission indicator has two sub-indicators, including the rate of change in carbon emissions per unit of electricity generated. Total carbon emission reduction and carbon emission intensity reduction rate ; As an economic indicator, its sub-indicators include the investment payback period for renovation. Unit carbon emission reduction cost and internal rate of return (IRR); As an environmental benefit indicator, its sub-indicators include reductions in other pollutants. and ecological environment impact index .

4. The carbon reduction effect evaluation system for technical transformation of power generation equipment according to claim 3, characterized in that, The weight determination module uses the analytic hierarchy process (AHP) to determine the weights of each indicator, specifically including: constructing a three-layer hierarchical structure model: the target layer is for evaluating the carbon reduction effect of technical upgrades to target power generation equipment, and the criterion layer is the four primary indicators. The solution layer consists of secondary indicators under each primary indicator; the criterion layer constructs a judgment matrix for the target layer using expert scoring. And the judgment matrix of each scheme layer to its corresponding criterion layer; calculate the eigenvector of each judgment matrix and normalize it to obtain the first-level index weight vector. The weights of each secondary indicator and its local weight vector under its primary indicator are calculated; by combining the weights, the global weight of each secondary indicator relative to the target layer is obtained. .

5. The carbon reduction effect evaluation system for technical transformation of power generation equipment according to claim 4, characterized in that, The comprehensive evaluation model module includes: Data standardization units are established by using either range standardization or Z-score standardization to normalize the raw values ​​of each secondary indicator. The data is processed to obtain standardized scores. ; The weighted comprehensive scoring unit, based on the global weights and the corresponding standardized score Calculate the overall evaluation score E using the following formula: , where n is the total number of secondary indicators.

6. The carbon reduction effect evaluation system for technical transformation of power generation equipment according to claim 5, characterized in that, The grading and evaluation module has preset threshold values ​​for carbon reduction effect levels: when... When the carbon reduction effect was rated as "excellent"; when When the carbon reduction effect is rated as "good"; when At that time, the carbon reduction effect was rated as "moderate"; when At that time, the carbon reduction effect was rated as "poor"; among them, , , .

7. The carbon reduction effect evaluation system for technical transformation of power generation equipment according to claim 6, characterized in that, The dynamic tracking and feedback module includes: The dynamic monitoring unit collects the real-time operating data after the modification at a fixed period T. ; The trend analysis unit is based on a comprehensive evaluation score over multiple consecutive periods T. For the sequence, calculate its slope k. If k is less than a preset negative trend threshold... If so, a warning signal will be triggered; The feedback execution unit generates a feedback report containing specific indicator degradation analysis and adjustment suggestions based on the warning signal and the current level evaluation result, and sends it to the equipment management system.

8. The carbon reduction effect evaluation system for technical transformation of power generation equipment according to claim 7, characterized in that, It also includes a machine learning optimization module, whose input is connected to the output of the dynamic tracking and feedback module, for receiving historical operating data, historical evaluation results, and feedback adjustment records; the machine learning optimization module dynamically optimizes the indicator weight vector in the weight determination module by training a prediction model. The rating thresholds in the rating classification and evaluation module enable the evaluation system to adapt to the specific type of power generation equipment and its operating environment.

9. A method for evaluating the carbon reduction effect of technological upgrades to power generation equipment, characterized in that, Includes the following steps: S1: Collect and preprocess data, including: static basic data of power generation equipment before technical transformation, including equipment model, rated power, fuel type and historical operating data; transformation scheme data, technical parameters adopted and transformation investment cost during the transformation process; and real-time operating data of power generation equipment after transformation, including real-time power generation, real-time fuel consumption, real-time pollutant emissions and equipment operating status parameters. S2: Based on the data preprocessed in step S1, construct a multi-level evaluation index system containing four primary indicators. The primary indicator is the equipment energy efficiency indicator, and its secondary indicators include the rate of change in power generation efficiency. thermal efficiency change rate and the rate of change of plant power consumption The second-level indicator is the carbon emission indicator, and its sub-sub-indicators include the rate of change in carbon emissions per unit of electricity generated. Total carbon emission reduction and carbon emission intensity reduction rate The third-level indicators are economic indicators, and their sub-secondary indicators include the payback period for renovation investment. Unit carbon emission reduction cost And the internal rate of return (IRR); the fourth level indicator is the environmental benefit indicator, whose sub-secondary indicators include the reduction of other pollutants. and ecological environment impact index ; S3: Use the Analytic Hierarchy Process (AHP) to determine the global weight of each second-level indicator in the multi-level evaluation index system described in step S2. The analytic hierarchy process includes: constructing a hierarchical structure model with three layers: target layer, criterion layer, and scheme layer; constructing a judgment matrix using expert scoring; calculating and normalizing the eigenvectors of each judgment matrix to obtain the weights of each level of indicators; S4: The original values ​​of each second-level indicator collected and preprocessed in step S1. Standardization is performed to obtain standardized scores. The weighted comprehensive scoring method is adopted, based on the formula. Calculate the comprehensive evaluation score E for the carbon reduction effect of the technical transformation of the power generation equipment, where n is the total number of second-level indicators; S5: Compare the comprehensive evaluation score E obtained in step S4 with the preset level threshold: if E≥85, the carbon reduction effect is rated as excellent; if 70≤E<85, it is rated as good; if 55≤E<70, it is rated as medium; if E<55, it is rated as poor.

10. The method for evaluating the carbon reduction effect of technical retrofitting of power generation equipment according to claim 9, characterized in that, It also includes step S6, dynamic evaluation and adjustment, which involves repeating steps S1 to S5 at a fixed period T to generate a time series. ;analyze The trend, if the slope k of the change is less than a preset negative trend threshold. Then, the key indicators that cause the degradation are identified; based on the historical data and current status of the key indicators, targeted suggestions for adjusting equipment operating parameters or maintenance strategies are generated, and the effects of the adjustments are verified.

Images