Method for rapidly measuring, calculating, analyzing and correcting carbon footprint of product

Abstract

The invention discloses a rapid measurement and calculation and analysis and correction method for a carbon footprint of a product, relates to the technical field of measurement and calculation of the carbon footprint of the product, and solves the technical problem of inaccurate measurement and calculation of the carbon footprint of the product due to the fact that aging of production equipment of the product is not considered in the prior art. The method comprises the steps of obtaining production link data and correction data of a target product; calculating the initial carbon emission of the target product based on the production link data; a correction model is constructed based on the correction data to correct the initial carbon emission, and target carbon emission is obtained; training an artificial intelligence model based on historical production link data to obtain a product carbon footprint prediction model; predicting the real-time production link data based on the product carbon footprint prediction model to obtain a prediction result; calculating the predicted carbon emission of the target product based on the prediction result; and judging whether the target carbon emission and the predicted carbon emission of the target product perform early warning or not. The technical problem is solved.

Description

Technical Field

[0001] The present invention belongs to the field of product carbon footprint measurement, and specifically is a method for rapid measurement and analysis and correction of product carbon footprint. Background Art

[0002] As global attention to climate change continues to increase, reducing greenhouse gas emissions has become a common responsibility of enterprises and society. Product carbon footprint, as an important indicator to measure the greenhouse gas emissions directly or indirectly generated by a product throughout its life cycle, is of great significance to the formulation of corporate sustainable development strategies, consumer choices, and policy and regulatory formulation.

[0003] The prior art (invention application with application number 2024102283511) discloses a method, device, electronic device and storage medium for measuring carbon footprint data. The method and device are applied to electronic equipment to measure the carbon footprint data in the product production process, specifically to determine the production links involved in the production process of the product to be measured; decompose the material composition involved in each production link of the product to be measured to obtain multiple material varieties for producing the product to be measured; calculate the material parameters of each material variety based on the carbon emission calculation model to obtain multiple material emission data, and summarize the multiple material emission data to obtain the carbon footprint data of the product to be measured; the carbon footprint data is the carbon footprint data in the product manufacturing process, thereby providing a data basis for enterprises to reduce carbon emissions. However, the existing technology for measuring the carbon footprint of products is based on the ideal state of production equipment, and does not take into account the impact of equipment aging on carbon emissions. As the equipment is used for a longer time, its efficiency gradually decreases, and energy consumption and maintenance requirements increase accordingly, which in turn leads to an increase in carbon emissions. The mechanical parts of aging equipment wear more severely, the lubrication effect weakens, and the performance of electrical components declines, all of which will increase friction and energy loss during operation, making the energy consumption per unit of product production higher. This makes the existing technology's measurement results of the product's carbon footprint different from the actual situation, resulting in inaccurate measurement of the product's carbon footprint.

[0004] Therefore, the present invention solves the above-mentioned problem by proposing a method for rapid measurement and analysis and correction of product carbon footprint. Summary of the invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art; to this end, the present invention proposes a method for rapid measurement and analysis and correction of the carbon footprint of a product, which is used to solve the problem that the prior art measurement of the carbon footprint of a product is based on an ideal state of the production equipment, and does not take into account the impact of equipment aging on carbon emissions. As the equipment is used for an extended period of time, its efficiency gradually decreases, and energy consumption and maintenance requirements increase accordingly, which in turn leads to an increase in carbon emissions. The mechanical parts of the aging equipment wear more severely, the lubrication effect weakens, and the performance of electrical components declines, all of which increase friction and energy loss during operation, making the energy consumption per unit of product production higher. This causes the prior art measurement results of the carbon footprint of the product to differ from the actual situation, resulting in inaccurate measurement of the carbon footprint of the product.

[0006] To achieve the above objectives, the first aspect of the present invention provides a method for rapid measurement and analysis and correction of a product carbon footprint, comprising:

[0007] Obtaining production process data and correction data of the target product; wherein the correction data includes: transportation data, water resource consumption data and aging data;

[0008] Calculate the initial carbon emissions of the target product based on production data;

[0009] Based on the correction data, a correction model is constructed to correct the initial carbon emissions and obtain the target carbon emissions;

[0010] Train the artificial intelligence model based on historical production data to obtain a product carbon footprint prediction model; predict the real-time production data based on the product carbon footprint prediction model to obtain prediction results; calculate the predicted carbon emissions of the target product based on the prediction results;

[0011] Determine whether to issue an early warning based on the target carbon emissions and predicted carbon emissions of the target product.

[0012] Preferably, the obtaining of the production process data and correction data of the target product includes:

[0013] Determine the production links designed for the target product; the target product refers to the product whose carbon footprint is to be measured; the production links include: raw material processing, product production, product transportation and distribution, product use, maintenance and waste treatment;

[0014] Obtain the production link data, water resource consumption data and aging data of the target product's production equipment in the production link through the enterprise's database; among them, the production link data refers to the energy consumed by the target product in each production link, including: raw material processing energy consumption, production energy consumption, transportation and distribution energy consumption, use and maintenance energy consumption and waste treatment energy consumption; water resource consumption data refers to the water resource consumption of the target product in the production link; aging data includes: the cumulative operating time of the equipment, the current output power of the equipment and the current vibration amplitude of the equipment;

[0015] The transportation data of the target product is obtained through the positioning device; the transportation data includes: the total distance from the production site of the raw materials of the product to the product processing plant and the total transportation distance of the recycled waste products.

[0016] It should be noted that the energy consumption refers to the various energy types and their usage involved in the processing, production, transportation and distribution, use and maintenance, and waste disposal of raw materials, where the energy types include: electricity or fuel (such as coal, natural gas, gasoline, etc.);

[0017] An enterprise's database generally refers to an information system used by the enterprise to store, manage and maintain various data generated during its business operations; these databases contain various types of information, including but not limited to customer information, product information, production data, production equipment data, human resources data, etc.

[0018] Preferably, the initial carbon emissions of the target product calculated based on the production process data include:

[0019] Extract the energy consumption of each link in the production link data and mark it as Ni; where i = {1, 2, 3, ..., n}, n is the total number of production links of the target product;

[0020] The initial carbon emissions calculation formula is: The initial carbon emissions of the target product are calculated; among them, CT is the initial carbon emissions of the target product, and αi is the carbon emission factor corresponding to the energy consumption of the i-th production link.

[0021] It should be noted that the carbon emission factor refers to the carbon dioxide emissions generated by unit energy or material, that is, carbon emission factor = carbon dioxide emissions per unit energy or material / unit energy or material usage.

[0022] Preferably, the correction model is constructed based on the correction data to correct the initial carbon emissions, including:

[0023] constructing a first revised model based on the aging data;

[0024] constructing a second revised model based on transportation data and water consumption data;

[0025] The initial carbon emissions are corrected based on the first correction model and the second correction model to obtain the target carbon emissions.

[0026] Preferably, the constructing of the first correction model based on the aging data comprises:

[0027] The accumulated running time of the equipment is marked as T, the current output power of the equipment is marked as W, and the current vibration amplitude of the equipment is marked as F;

[0028] By formula:

[0029] P=A1×ln^[(T / ZT)+1]+A2×ln^[((EW-W) / EW)+1]+A3×

[0030] ln^[((F-ZF) / ZF)+1];

[0031] The aging degree assessment coefficient of the equipment is calculated; wherein P is the aging degree assessment coefficient of the equipment, A1, A2, and A3 are weight coefficients, and A1+A2+A3=1, ZT refers to the design life of the equipment, EW is the rated output power of the equipment, and ZF is the initial vibration amplitude of the equipment;

[0032] The aging evaluation coefficient of the equipment is used as the independent variable, and the result obtained by correction is used as the dependent variable, and is marked as the first correction factor f1;

[0033] The independent variables and dependent variables are fitted by polynomial fitting to establish the first correction model; the first correction model is specifically: f1=CT×e^(k×P); wherein CT is the initial carbon emission of the target product, and k is the proportional coefficient, which represents the influence of each unit aging degree assessment coefficient on carbon emissions.

[0034] It should be noted that the design life is the expected service life given by the equipment manufacturer; when the cumulative operating time approaches or exceeds the design life, the aging degree of the equipment will increase significantly, and the risk of failure will also increase;

[0035] The rated output power is the maximum output power of the device under design conditions. When the current output power is significantly lower than the rated output power, it means that the performance of the device has been significantly reduced.

[0036] The initial vibration amplitude refers to the normal vibration level of the equipment when it is newly installed or in optimal working condition. When the current vibration amplitude is higher than the initial vibration amplitude, it means that the mechanical condition of the equipment has deteriorated and there may be serious wear or looseness problems.

[0037] The aging of equipment will lead to a lower carbon emission result of the product calculated by collecting the energy consumption of production equipment. This is because in most cases, the carbon emission calculation model is estimated based on the energy efficiency of the equipment under ideal or designed conditions, and the actual energy efficiency of aging equipment is usually lower than its design value; for example, aging combustion equipment (such as boilers, engines, etc.) may have incomplete combustion, resulting in insufficient combustion of fuel. Unburned hydrocarbons will be further oxidized into carbon dioxide during subsequent processing, increasing the total carbon emissions. Therefore, even if the total energy consumption remains unchanged, the actual carbon emissions will increase due to the decrease in combustion efficiency. Therefore, the carbon emission calculation results based on fixed energy consumption will underestimate the actual carbon emissions;

[0038] The present invention calculates an aging degree assessment coefficient of the equipment based on aging data, and the coefficient can dynamically reflect the aging condition of the equipment in actual use; a first correction model is constructed through the aging degree assessment coefficient of the equipment to correct the initial carbon emissions of the product, thereby avoiding the problem of underestimated carbon emissions due to equipment aging.

[0039] Preferably, the constructing of the second correction model based on the transportation data and the water resource consumption data comprises:

[0040] The transport data and water consumption data are used as independent variables, and the correction result is used as the dependent variable, which is marked as the second correction factor f2;

[0041] The total distance from the raw material production site to the product processing plant is marked as Y, the total transportation distance of recycled waste products is marked as H, and the water consumption of the product during the production process is marked as S; the total transportation distance of recycled waste products is the sum of the distance from the recycling plant to the recycled products and the distance from the recycled products to the recycling plant;

[0042] The independent variables and dependent variables are fitted by polynomial fitting to establish the second revised model; the second revised model is specifically:

[0043] f2=β1×ln(Y+1)^θ1+β2×ln(H+1)^θ2+S×γ×β3;

[0044] Among them, β1, β2, and β3 are carbon emission factors, θ1 and θ2 are proportional coefficients; γ refers to the energy consumption required for one cubic meter of water.

[0045] It should be noted that the proportionality coefficients θ1 and θ2 are set by experts in this field based on experience according to the energy consumption of actual transport vehicles;

[0046] The carbon footprint of a product refers to the total carbon emissions generated by all activities related to greenhouse gas emissions throughout the product's entire life cycle (from raw material acquisition, production, transportation, use to final disposal); carbon footprint includes not only direct carbon emissions (such as energy consumption of production equipment), but also indirect carbon emissions (such as transportation of raw materials, water treatment and transportation, etc.); for example, the foundry industry consumes water resources in smelting, molding, cooling and post-processing. In the process of water extraction, purification and transportation, a large amount of energy is consumed, which in turn generates carbon emissions. Although these carbon emissions are not directly generated by production equipment, they are the environmental price that must be paid to support product production, and therefore are part of the product's life cycle carbon emissions.

[0047] Preferably, the correction of the initial carbon emissions based on the first correction model and the second correction model includes:

[0048] Inputting the initial carbon emissions into the first correction model to obtain a first correction factor;

[0049] Inputting the transportation data and the water resource consumption data into the second correction model to obtain the second correction factor;

[0050] The first correction factor is added to the second correction factor to obtain the target carbon emissions.

[0051] Preferably, the training of the artificial intelligence model based on historical production link data includes:

[0052] Integrate historical production link data into standard input data; integrate historical production link data within a preset forecast period into standard output data;

[0053] An artificial intelligence model is trained based on standard input data and standard output data to obtain a product carbon footprint prediction model; wherein the artificial intelligence model includes: a convolutional neural network or a deep belief network.

[0054] It should be noted that the historical production link data refers to the historical data of obtaining production link data; the preset prediction time period is set according to the actual needs of the enterprise or factory to predict the carbon emissions of products in a certain time period in the future.

[0055] Preferably, the step of calculating the predicted carbon emissions of the target product based on the prediction results includes:

[0056] Input the production data of the product into the product carbon footprint prediction model to obtain the prediction result; wherein the prediction result refers to the production data of the product within the preset prediction time period;

[0057] The predicted initial carbon emissions of the product are calculated using the initial carbon emissions calculation formula;

[0058] The initial carbon emissions predicted by the product are corrected by the first correction model and the second correction model to obtain the predicted carbon emissions.

[0059] Preferably, the step of determining whether to issue an early warning for the target carbon emission amount and the predicted carbon emission amount of the target product includes:

[0060] Determine whether the target carbon emissions are greater than the preset carbon emissions threshold; if yes, generate an early warning message of product carbon emissions exceeding the standard and send it to the client; if no, continue to detect and judge;

[0061] Determine whether the predicted carbon emissions are greater than the preset carbon emissions threshold; if yes, generate warning information that the product's predicted carbon emissions exceed the standard and send it to the client; if no, continue to detect and judge.

[0062] It should be noted that the preset carbon emission threshold is set by experts in this field based on the actual carbon emission safety standards.

[0063] Compared with the prior art, the present invention has the following beneficial effects:

[0064] 1. The existing technology calculates the carbon footprint of products based on the ideal state of production equipment, and does not take into account the impact of equipment aging on carbon emissions. As the equipment is used for a longer time, its efficiency gradually decreases, and energy consumption and maintenance requirements increase accordingly, which in turn leads to an increase in carbon emissions. The mechanical parts of the aging equipment wear more severely, the lubrication effect weakens, and the performance of electrical components declines, all of which increase friction and energy loss during operation, making the energy consumption per unit of product production higher. This makes the calculation results of the carbon footprint of products in the existing technology different from the actual situation, resulting in the technical problem of inaccurate carbon footprint calculation of products. The present invention obtains production link data and correction data of the target product; calculates the initial carbon emissions of the target product based on the production link data; calculates the aging degree assessment coefficient of the equipment based on the aging data, and the coefficient can dynamically reflect the aging status of the equipment in actual use; constructs a first correction model through the aging degree assessment coefficient of the equipment to correct the initial carbon emissions of the product, thereby solving the above problems.

[0065] 2. The present invention constructs a second correction model, takes transportation data and water resource consumption data as independent variables, and combines corresponding carbon emission factors, proportional coefficients, water treatment energy consumption and other parameters to accurately correct the initial carbon emissions of the product, thereby significantly improving the accuracy and comprehensiveness of the product carbon footprint measurement; specifically, the present invention not only takes into account the transportation distance of raw materials from the place of production to the processing plant and the waste product recycling process, but also incorporates the water resource consumption in the production process, ensuring the effective evaluation of indirect carbon emission sources. By fitting these factors with polynomials, it can more realistically reflect the carbon emission changes under different transportation distances and water resource usage conditions, making up for the shortcomings of existing measurement methods that ignore the impact of transportation and water consumption. At the same time, considering the carbon emissions caused by energy consumption in the water treatment process, it can more accurately evaluate the contribution of transportation and water resource consumption to the product carbon footprint, avoiding the underestimation problem caused by ignoring indirect emissions in existing measurement methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0067] Figure 1 A schematic diagram of the method steps of an embodiment of the present invention;

[0068] Figure 2 A correction schematic diagram of a correction model according to an embodiment of the present invention;

[0069] Figure 3 Schematic diagram of early warning judgment of target carbon emissions according to an embodiment of the present invention. DETAILED DESCRIPTION

[0070] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0071] See also Figure 1 The first embodiment of the present invention provides a method for rapid measurement and analysis of a product's carbon footprint, including:

[0072] Obtaining production process data and correction data of the target product; wherein the correction data includes: transportation data, water resource consumption data and aging data;

[0073] Calculate the initial carbon emissions of the target product based on production data;

[0074] Based on the correction data, a correction model is constructed to correct the initial carbon emissions and obtain the target carbon emissions;

[0075] Train the artificial intelligence model based on historical production data to obtain a product carbon footprint prediction model; predict the real-time production data based on the product carbon footprint prediction model to obtain prediction results; calculate the predicted carbon emissions of the target product based on the prediction results;

[0076] Determine whether to issue an early warning based on the target carbon emissions and predicted carbon emissions of the target product.

[0077] Obtain production process data and correction data of the target product, including:

[0078] Determine the production links designed for the target product; the target product refers to the product whose carbon footprint is to be measured; the production links include: raw material processing, product production, product transportation and distribution, product use, maintenance and waste treatment;

[0079] Obtain the production link data, water resource consumption data and aging data of the target product's production equipment in the production link through the enterprise's database; among them, the production link data refers to the energy consumed by the target product in each production link, including: raw material processing energy consumption, production energy consumption, transportation and distribution energy consumption, use and maintenance energy consumption and waste treatment energy consumption; water resource consumption data refers to the water resource consumption of the target product in the production link; aging data includes: the cumulative operating time of the equipment, the current output power of the equipment and the current vibration amplitude of the equipment;

[0080] The transportation data of the target product is obtained through the positioning device; the transportation data includes: the total distance from the production site of the raw materials of the product to the product processing plant and the total transportation distance of the recycled waste products.

[0081] The initial carbon emissions of the target product are calculated based on the production data, including:

[0082] Extract the energy consumption of each link in the production link data and mark it as Ni; where i = {1, 2, 3, ..., n}, n is the total number of production links of the target product;

[0083] The initial carbon emissions calculation formula is: The initial carbon emissions of the target product are calculated; among them, CT is the initial carbon emissions of the target product, and αi is the carbon emission factor corresponding to the energy consumption of the i-th production link.

[0084] Based on the revised data, a revised model is constructed to revise the initial carbon emissions, including:

[0085] constructing a first revised model based on the aging data;

[0086] constructing a second revised model based on transportation data and water consumption data;

[0087] The initial carbon emissions are corrected based on the first correction model and the second correction model to obtain the target carbon emissions.

[0088] A first correction model is constructed based on the aging data, including:

[0089] The accumulated running time of the equipment is marked as T, the current output power of the equipment is marked as W, and the current vibration amplitude of the equipment is marked as F;

[0090] By formula:

[0091] P=A1×ln^[(T / ZT)+1]+A2×ln^[((EW-W) / EW)+1]+A3×

[0092] ln^[((F-ZF) / ZF)+1];

[0093] The aging degree assessment coefficient of the equipment is calculated; wherein P is the aging degree assessment coefficient of the equipment, A1, A2, and A3 are weight coefficients, and A1+A2+A3=1, ZT refers to the design life of the equipment, EW is the rated output power of the equipment, and ZF is the initial vibration amplitude of the equipment;

[0094] The aging evaluation coefficient of the equipment is used as the independent variable, and the correction result is used as the dependent variable, which is marked as the first correction factor f1;

[0095] The independent variables and dependent variables are fitted by polynomial fitting to establish the first correction model; the first correction model is specifically: f1=CT×e^(k×P); wherein CT is the initial carbon emission of the target product, and k is the proportional coefficient, which represents the influence of each unit aging degree assessment coefficient on carbon emissions.

[0096] The second revised model is constructed based on transportation data and water consumption data, including:

[0097] The transport data and water consumption data are used as independent variables, and the correction result is used as the dependent variable, which is marked as the second correction factor f2;

[0098] The total distance from the raw material production site to the product processing plant is marked as Y, the total transportation distance of recycled waste products is marked as H, and the water consumption of the product during the production process is marked as S; the total transportation distance of recycled waste products is the sum of the distance from the recycling plant to the recycled products and the distance from the recycled products to the recycling plant;

[0099] The independent variables and dependent variables are fitted by polynomial fitting to establish the second revised model; the second revised model is specifically:

[0100] f2=β1×ln(Y+1)^θ1+β2×ln(H+1)^θ2+S×γ×β3;

[0101] Among them, β1, β2, and β3 are carbon emission factors, θ1 and θ2 are proportional coefficients; γ refers to the energy consumption required for one cubic meter of water.

[0102] The initial carbon emissions are corrected based on the first correction model and the second correction model, including:

[0103] Inputting the initial carbon emissions into the first correction model to obtain a first correction factor;

[0104] Inputting the transportation data and the water resource consumption data into the second correction model to obtain the second correction factor;

[0105] The first correction factor is added to the second correction factor to obtain the target carbon emissions.

[0106] Training AI models based on historical production data, including:

[0107] Integrate historical production link data into standard input data; integrate historical production link data within a preset forecast period into standard output data;

[0108] An artificial intelligence model is trained based on standard input data and standard output data to obtain a product carbon footprint prediction model; wherein the artificial intelligence model includes: a convolutional neural network or a deep belief network.

[0109] The predicted carbon emissions of the target product are calculated based on the prediction results, including:

[0110] Input the production data of the product into the product carbon footprint prediction model to obtain the prediction result; wherein the prediction result refers to the production data of the product within the preset prediction time period;

[0111] The predicted initial carbon emissions of the product are calculated using the initial carbon emissions calculation formula;

[0112] The initial carbon emissions predicted by the product are corrected by the first correction model and the second correction model to obtain the predicted carbon emissions.

[0113] Determine whether to issue an early warning for the target carbon emissions and predicted carbon emissions of the target product, including:

[0114] Determine whether the target carbon emissions are greater than the preset carbon emissions threshold; if yes, generate an early warning message of product carbon emissions exceeding the standard and send it to the client; if no, continue to detect and judge;

[0115] Determine whether the predicted carbon emissions are greater than the preset carbon emissions threshold; if yes, generate warning information that the product's predicted carbon emissions exceed the standard and send it to the client; if no, continue to detect and judge.

[0116] For example, suppose you want to measure the carbon footprint of an automobile part. The production process of this part includes raw material processing, production, transportation and distribution, use and maintenance, and waste disposal. The specific process is as follows:

[0117] 1. Obtain the production process data and correction data of the target product;

[0118] 1.1 Production data:

[0119] Electricity consumption for raw material processing: 30kWh;

[0120] Electricity consumption for production: 60kWh;

[0121] Gasoline consumption for transportation and distribution: 20L;

[0122] Power consumption for maintenance: 15kWh;

[0123] Waste disposal is coal consumption: 2kg;

[0124] 1.2 Corrected data:

[0125] Shipping data:

[0126] The total distance from the raw material production site to the product processing plant is Y = 500km;

[0127] The total transportation distance for recycling waste products is H = 300km;

[0128] 1.3 Water consumption data:

[0129] The consumption of water resources in the production process is S = 100 cubic meters;

[0130] 1.4 Aging data:

[0131] The cumulative operating time of the equipment is T = 8000 hours;

[0132] The current output power of the equipment is W = 80kW (rated output power EW = 100kW);

[0133] The current vibration amplitude of the equipment F = 0.5 mm / s (initial vibration amplitude ZF = 0.3 mm / s);

[0134] The design life of the equipment is ZT = 10,000 hours;

[0135] 2. Calculate the initial carbon emissions of the target product based on production data;

[0136] Assume that the final calculated initial carbon emissions are 217.5kgCO2;

[0137] 3. Construct a correction model based on the correction data to correct the initial carbon emissions;

[0138] 3.1 Construct the first correction model based on aging data;

[0139] The aging evaluation coefficient of the equipment is calculated by the formula: P = A1 × ln^[(T / ZT)+1]+A2 × ln^[((EW-W) / EW)+1]+A3 × ln^[((F-ZF) / ZF)+1];

[0140] Assume that weight coefficients A1 = 0.5, A2 = 0.3, A3 = 0.2;

[0141] Substituting the data into the data, we obtain P = 0.4508;

[0142] The initial carbon emissions are corrected by using the first correction model: f1 = CT×e^(k×P).

[0143] Assume the proportionality factor k = 0.5:

[0144] Substituting the data into the equation, we get: f1 = 272.36 kg CO2;

[0145] 3.2 Construction of the second revised model based on transportation data and water consumption data

[0146] Based on the second correction model: f2 = β1 × ln(Y+1)^θ1 + β2 × ln(H+1)^θ2 + S × γ × β3; calculate the second correction factor;

[0147] Assuming carbon emission factors β1 = 0.2, β2 = 0.3, β3 = 0.3, proportionality coefficients θ1 = 0.5, θ2 = 0.6, the energy consumption required for one cubic meter of water γ = 0.2 kWh / cubic meter;

[0148] Substituting the data into the equation, we get: f2 = 22.6 kg CO2;

[0149] 3.3 Add the first correction factor and the second correction factor to obtain the target carbon emissions;

[0150] Target carbon emissions = f1 + f2 = 294.96 kg CO2;

[0151] Therefore, the final carbon emission of the target product is 294.96kgCO2.

[0152] 4. Train the artificial intelligence model based on historical production data to obtain the product carbon footprint prediction model;

[0153] Assume that the predicted initial carbon emissions are 317.5kgCO2.

[0154] 5. Determine whether to issue an early warning based on the target carbon emissions and predicted carbon emissions of the target product;

[0155] Assuming the preset carbon emission threshold is 250kgCO2, then:

[0156] The target carbon emissions are 294.96 kg CO2, which exceeds the preset threshold. Therefore, the system will generate an early warning message that the product’s carbon emissions exceed the standard and send it to the client.

[0157] The predicted carbon emissions of 317.5kgCO2 also exceed the preset threshold, so the system will also generate an early warning message that the product's predicted carbon emissions exceed the standard, reminding companies to take measures in advance to reduce carbon emissions.

[0158] The present invention successfully corrects the problem of underestimating carbon emissions due to equipment aging and indirect emissions in traditional carbon emission calculation methods by introducing aging data and transportation and water resource consumption data. Specifically, the present invention not only takes into account the actual operating status of production equipment, but also comprehensively considers the impact of transportation and water resource consumption on carbon emissions, ensuring the accuracy and comprehensiveness of the carbon footprint calculation results. In addition, through the predictive function of the artificial intelligence model, companies can identify potential high-carbon emission risks in advance and take corresponding emission reduction measures to achieve more refined carbon emission management. At the same time, the specific energy types of each production link are clearly listed, making carbon emission calculations more transparent and accurate, which helps companies better understand and optimize their carbon emission structure.

[0159] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0160] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A method for rapid measurement and analysis of product carbon footprint, characterized in that: include: Obtaining production process data and correction data of the target product; wherein the correction data includes: transportation data, water resource consumption data and aging data; Calculate the initial carbon emissions of the target product based on production data; Based on the correction data, a correction model is constructed to correct the initial carbon emissions and obtain the target carbon emissions; Train the artificial intelligence model based on historical production data to obtain a product carbon footprint prediction model; predict the real-time production data based on the product carbon footprint prediction model to obtain prediction results; calculate the predicted carbon emissions of the target product based on the prediction results; Determine whether to issue an early warning based on the target carbon emissions and predicted carbon emissions of the target product.

2. The method for rapid measurement and analysis and correction of product carbon footprint according to claim 1, characterized in that: The obtaining of the production process data and correction data of the target product includes: Determine the production links designed for the target product; the target product refers to the product whose carbon footprint is to be measured; the production links include: raw material processing, product production, product transportation and distribution, product use, maintenance and waste treatment; Obtain the production link data, water resource consumption data and aging data of the target product's production equipment in the production link through the enterprise's database; among them, the production link data refers to the energy consumed by the target product in each production link, including: raw material processing energy consumption, production energy consumption, transportation and distribution energy consumption, use and maintenance energy consumption and waste treatment energy consumption; water resource consumption data refers to the water resource consumption of the target product in the production link; aging data includes: the cumulative operating time of the equipment, the current output power of the equipment and the current vibration amplitude of the equipment; The transportation data of the target product is obtained through the positioning device; the transportation data includes: the total distance from the production site of the raw materials of the product to the product processing plant and the total transportation distance of the recycled waste products.

3. The method for rapid measurement and analysis of product carbon footprint according to claim 1, characterized in that: The initial carbon emissions of the target product calculated based on the production process data include: Extract the energy consumption of each link in the production link data and mark it as Ni; where i = {1, 2, 3, ..., n}, n is the total number of production links of the target product; The initial carbon emissions calculation formula is: The initial carbon emissions of the target product are calculated; among them, CT is the initial carbon emissions of the target product, and αi is the carbon emission factor corresponding to the energy consumption of the i-th production link.

4. The method for rapid measurement and analysis of product carbon footprint according to claim 1, characterized in that: The method of constructing a correction model based on the correction data to correct the initial carbon emissions includes: constructing a first revised model based on the aging data; constructing a second revised model based on transportation data and water consumption data; The initial carbon emissions are corrected based on the first correction model and the second correction model to obtain the target carbon emissions.

5. The method for rapid measurement and analysis and correction of product carbon footprint according to claim 4, characterized in that: The step of constructing a first correction model based on aging data includes: The accumulated running time of the equipment is marked as T, the current output power of the equipment is marked as W, and the current vibration amplitude of the equipment is marked as F; By formula: P=A1×ln^[(T / ZT)+1]+A2×ln^[((EW-W) / EW)+1]+A3× ln^[((F-ZF) / ZF)+1]; The aging degree assessment coefficient of the equipment is calculated; wherein P is the aging degree assessment coefficient of the equipment, A1, A2, and A3 are weight coefficients, and A1+A2+A3=1, ZT refers to the design life of the equipment, EW is the rated output power of the equipment, and ZF is the initial vibration amplitude of the equipment; The aging evaluation coefficient of the equipment is used as the independent variable, and the result obtained by correction is used as the dependent variable, and is marked as the first correction factor f1; The independent variables and dependent variables are fitted by polynomial fitting to establish the first correction model; the first correction model is specifically: f1=CT×e^(k×P); wherein CT is the initial carbon emission of the target product, and k is the proportional coefficient, which represents the influence of each unit aging degree assessment coefficient on carbon emissions.

6. The method for rapid measurement and analysis and correction of product carbon footprint according to claim 4, characterized in that: The second correction model is constructed based on the transportation data and the water resource consumption data, comprising: The transport data and water consumption data are used as independent variables, and the correction result is used as the dependent variable, which is marked as the second correction factor f2; The total distance from the raw material production site to the product processing plant is marked as Y, the total transportation distance for recycling waste products is marked as H, and the water consumption during the production process of the product is marked as S; The independent variables and dependent variables are fitted by polynomial fitting to establish the second revised model; the second revised model is specifically: f2=β1×ln(Y+1)^θ1+β2×ln(H+1)^θ2+S×γ×β3; Among them, β1, β2, and β3 are carbon emission factors, θ1 and θ2 are proportional coefficients; γ refers to the energy consumption required for one cubic meter of water.

7. The method for rapid measurement and analysis and correction of product carbon footprint according to claim 4, characterized in that: The correcting of the initial carbon emissions based on the first correction model and the second correction model includes: Inputting the initial carbon emissions into the first correction model to obtain a first correction factor; Inputting the transportation data and the water resource consumption data into the second correction model to obtain the second correction factor; The first correction factor is added to the second correction factor to obtain the target carbon emissions.

8. The method for rapid measurement and analysis and correction of product carbon footprint according to claim 1, characterized in that: The training of the artificial intelligence model based on historical production link data includes: Integrate historical production link data into standard input data; integrate historical production link data within a preset forecast period into standard output data; An artificial intelligence model is trained based on standard input data and standard output data to obtain a product carbon footprint prediction model; wherein the artificial intelligence model includes: a convolutional neural network or a deep belief network.

9. The method for rapid measurement and analysis and correction of product carbon footprint according to claim 1, characterized in that: The method of calculating the predicted carbon emissions of the target product based on the prediction results includes: Input the production data of the product into the product carbon footprint prediction model to obtain the prediction result; wherein the prediction result refers to the production data of the product within the preset prediction time period; The predicted initial carbon emissions of the product are calculated using the initial carbon emissions calculation formula; The initial carbon emissions predicted by the product are corrected by the first correction model and the second correction model to obtain the predicted carbon emissions.

10. The method for rapid measurement and analysis and correction of product carbon footprint according to claim 1, characterized in that: The determining whether to issue an early warning for the target carbon emission amount and the predicted carbon emission amount of the target product includes: Determine whether the target carbon emissions are greater than the preset carbon emissions threshold; if yes, generate an early warning message of product carbon emissions exceeding the standard and send it to the client; if no, continue to detect and judge; Determine whether the predicted carbon emissions are greater than the preset carbon emissions threshold; if yes, generate an early warning message that the product's predicted carbon emissions exceed the standard and send it to the client; if no, continue to detect and judge.

Images