Electro-galvanized product carbon footprint measuring and calculating method and system based on electric power big data

Abstract

The embodiment of the invention provides a method and a system for measuring and calculating a carbon footprint of an electrogalvanizing product based on electric power big data, and belongs to the technical field of carbon footprint measurement and calculation. The method comprises the following steps: acquiring the number of electrogalvanizing products and basic information of each flow section in a life cycle; according to the quantity and the basic information, the carbon dioxide emission of the electrogalvanizing product is determined; correcting the carbon dioxide emission by adopting a preset carbon footprint prediction model; and describing a carbon footprint trend diagram of the transformer according to the corrected carbon dioxide emission. According to the carbon footprint measuring and calculating method and system, measuring and calculating of the carbon footprint of the electro-galvanized product can be achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of carbon footprint calculation, and in particular to a carbon footprint calculation method and system for electro-galvanized products based on electric power big data. Background Art

[0002] As global climate change issues are gaining more and more attention, the carbon footprint of key industrial products, as an important indicator to measure the impact of products or activities on climate change, has become particularly important to measure and manage. Key industrial products occupy an important position in the fields of public safety, ecological and environmental safety, and the national economy. They have a significant impact on economic development, technological progress, and national security, and are crucial to improving national competitiveness and meeting social development needs. Galvanizing plays a vital role in preventing rust and corrosion, and electrogalvanized products are typical key products in the industrial sector.

[0003] The commonly used carbon footprint measurement method is generally through simple cost and emission measurement. However, in the production process, due to the influence of human factors, it is difficult for conventional measurement methods to achieve relatively accurate accuracy. At present, to achieve accurate measurement, it is necessary to have perfect measurement facilities. However, under actual production conditions, it is difficult to equip perfect measurement facilities. Summary of the invention

[0004] The purpose of the embodiments of the present invention is to provide a carbon footprint calculation method and system for electrogalvanized products based on electric power big data, which can realize the calculation of the carbon footprint of electrogalvanized products.

[0005] In order to achieve the above object, an embodiment of the present invention provides a method for calculating the carbon footprint of electro-galvanized products based on power big data, comprising: Obtain basic information on the quantity of electrogalvanized products and each process stage in their life cycle; Determine the carbon dioxide emissions of the electro-galvanized product based on the quantity and basic information; Correcting the carbon dioxide emissions using a preset carbon footprint prediction model; The carbon footprint trend of the electro-galvanized product is depicted according to the corrected carbon dioxide emissions.

[0006] Optionally, the process segments include a raw material acquisition period, a raw material transportation period, a product production period, a product transportation period, a product use period and a product recovery period.

[0007] Optionally, determining the carbon dioxide emissions of the electrogalvanized product according to the quantity and basic information includes: During the raw material acquisition period, when the electro-galvanized product is a 200kVA oil-immersed distribution transformer, the following formulas (1) to (5) are used to calculate the carbon dioxide emissions: , (1) in, The carbon dioxide emissions of the iron core of a single transformer during the period of raw material acquisition; , (2) in, The carbon dioxide emissions of the copper wire of a single transformer during the period of raw material acquisition; , (3) in, The carbon dioxide emissions from the insulation components of a single transformer during the period of raw material acquisition; , (4) in, The carbon dioxide emissions from transformer oil of a single transformer during the period of raw material acquisition; , (5) in, The carbon dioxide emissions from the oil tank of a single transformer during the period of raw material acquisition; During the raw material transportation period, when the electro-galvanized product is a 200kVA oil-immersed distribution transformer, the following formulas (6) to (9) are used to calculate the carbon dioxide emissions: , (6) in, is the carbon dioxide emission of the iron core of a single transformer during the transportation period of raw materials, The transportation mileage of the raw materials of the iron core during the raw materials transportation period; , (7) in, is the carbon dioxide emission of the copper wire of a single transformer during the transportation period of raw materials, The transportation mileage of the raw materials of the copper wire during the raw materials transportation period; , (8) in, is the carbon dioxide emission of the insulation components of a single transformer during the transportation period of raw materials, The transportation mileage of the raw materials of the insulation parts during the raw materials transportation period; , (9) in, is the carbon dioxide emission of the insulation components of a single transformer during the transportation period of raw materials, The transportation mileage of the raw materials of the insulation parts during the raw materials transportation period; During the product production period, when the electro-galvanized product is a 200kVA oil-immersed distribution transformer, the following formulas (10) to (14) are used to calculate the carbon dioxide emissions: , (10) in, The carbon dioxide emissions generated by the coil production of a single transformer during the production period of the product; , (11) in, The carbon dioxide emissions generated by the insulation assembly of a single transformer during the production period of the product; , (12) in, The carbon dioxide emissions generated by the production of the oil tank of a single transformer during the production period of the product; , (13) in, The carbon dioxide emissions generated by the final assembly of a single transformer during the production period of the product; , (14) in, The carbon dioxide emissions generated by the test of a single transformer during the production period of the product; During the product transportation period, when the electro-galvanized product is a 200kVA oil-immersed distribution transformer, the following formula (15) is used to calculate the carbon dioxide emissions: , (15) in, The carbon dioxide emissions of a single transformer during the product transportation period; During the product life, when the electro-galvanized product is a 200kVA oil-immersed distribution transformer, the carbon dioxide emissions are calculated using the following formula (16): , (16) in, is the carbon dioxide emissions of a single transformer during the product life, is the accumulated working power of the transformer; During the product recovery period, when the electro-galvanized product is a 200kVA oil-immersed distribution transformer, the carbon dioxide emissions are calculated using the following formulas (17) and (18): , (17) in, The carbon dioxide emissions of a single transformer during the product payback period; , (18) in, It is the carbon dioxide emission of a single transformer during the product recovery period.

[0008] Optionally, the carbon dioxide emissions are corrected using a preset carbon footprint prediction model, including: Obtain the electricity meter ledger, electricity carbon meter ledger, energy consumption ledger, and product input and output ledger information of electrogalvanized products during the production stage; Preprocessing the electric energy meter ledger, electric carbon meter ledger, energy consumption ledger, and product input and output ledger information to obtain corresponding ledger features; Combining each of the ledger features to obtain a fused feature; Inputting the fused features into the carbon footprint prediction model to obtain predicted carbon dioxide emissions; The predicted carbon dioxide emission amount is added to the carbon dioxide emission amount to obtain the corrected carbon dioxide emission amount.

[0009] Optionally, the electric energy meter ledger, the electric carbon meter ledger, the energy consumption ledger, and the product input and output ledger information are preprocessed to obtain corresponding ledger features, including: Perform data cleaning operations on the electricity meter ledger, electricity carbon meter ledger, energy consumption ledger, and product input and output ledger information; Perform data completion operations on the missing information of the electric energy meter ledger, electric carbon meter ledger, energy consumption ledger, and product input and output ledger information after the data cleaning operation; The data point values ​​of the electric energy meter ledger, electric carbon meter ledger, energy consumption ledger and product input and output ledger information after the sampling data of the preset sampling points in the time series are completed to obtain multiple ledger matrices; The ledger matrices are combined to obtain the ledger features.

[0010] Optionally, the carbon footprint prediction model includes an ARDL model, an XGBoost model, a linear regression model, a DNN model and a DS output layer.

[0011] Optionally, the method comprises: The ARDL model is expressed using formula (1): , (1) in, is the output of the ARDL model, is a constant term, Output The autoregressive order of Output The autoregression coefficient of is the output of the previous layer, is the input of the previous layer, For input The lag order of For input The lag term coefficient of is the autoregressive coefficient of the first layer, is the initial input, is the error term; Formula (2) is used to represent the XGBoost model: , (2) in, is the prediction output of the XGBoost model, is the calculated value of the basis function, is the number of decision trees, is a set of decision trees, For the A decision tree.

[0012] Optionally, the method comprises: The linear regression model is expressed by formula (3): , (3) in, is the output of the linear regression model, is the intercept, , , is the independent variable, , , is the regression coefficient, is the error term; The softmax function is used as the classification function of the output layer of the DNN model.

[0013] Optionally, the DS output layer is used to: The final output is determined according to the outputs of the ARDL model, XGBoost model, linear regression model, and DNN model in accordance with the DS evidence theory.

[0014] On the other hand, the present invention also provides a carbon footprint calculation system for electro-galvanized products based on electric power big data, the system comprising a processor, and the processor is configured to execute any of the methods described above.

[0015] Through the above technical solution, the present invention provides a method and system for calculating the carbon footprint of electrogalvanized products based on power big data. The method and system use numerical calculation methods to determine the numerical range of carbon dioxide emissions, thereby avoiding the defect of numerical overflow of subsequent prediction models. On this basis, the method and system further use the predicted value of the prediction model to correct the calculation results, thereby overcoming the influence of human factors and realizing accurate calculation of carbon dioxide emissions.

[0016] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings: Figure 1 is a flow chart of a method for calculating the carbon footprint of electro-galvanized products based on power big data according to one embodiment of the present invention; Figure 2 is a flow chart of a method for correcting carbon dioxide emissions using a preset carbon footprint prediction model according to one embodiment of the present invention; Figure 3 is a schematic diagram of a lagged 1-order line training result according to an example of the present invention; Figure 4 is a schematic diagram of a lagged 2nd order line training result according to an example of the present invention; Figure 5 is a schematic diagram of an XGBoost model according to one embodiment of the present invention; Figure 6 is a result diagram of training a linear regression model according to one embodiment of the present invention. DETAILED DESCRIPTION

[0018] The specific implementation of the embodiment of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the embodiment of the present invention, and is not used to limit the embodiment of the present invention.

[0019] It should be noted that the acquisition, transmission, storage, use, and processing of data in the technical solution of this application are in compliance with the relevant provisions of national laws and regulations. In the embodiments of this application, some existing solutions in the industry such as certain software, components, and models may be mentioned, which should be considered as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of this application, but it does not mean that the applicant has or will necessarily use the solution.

[0020] Figure 1 The present invention is a flowchart of a method for calculating the carbon footprint of electro-galvanized products based on power big data according to an embodiment of the present invention. Figure 1 In the method, the method may include the following steps: In step S10, the quantity of electrogalvanized products and basic information of each process stage in the life cycle are obtained; In step S11, the carbon dioxide emission of the electrogalvanized product is determined based on the quantity and basic information; In step S12, the carbon dioxide emissions are corrected using a preset carbon footprint prediction model; In step S13, a carbon footprint trend diagram of the electro-galvanized product is drawn according to the corrected carbon dioxide emission.

[0021] In such Figure 1 In the method shown, step S10 can be used to obtain the quantity of electrogalvanized products and basic information of each process segment in the life cycle. Among them, the multiple process segments included in the life cycle can be a variety known to those skilled in the art. In one example of the present invention, the process segment can be a raw material acquisition period, a raw material transportation period, a product production period, a product transportation period, a product use period, and a product recycling period.

[0022] Specifically, in this example, during the raw material acquisition period, when the electro-galvanized product is a 200kVA oil-immersed distribution transformer, the following formulas (1) to (5) are used to calculate the carbon dioxide emissions: , (1) in, The carbon dioxide emissions of the iron core of a single transformer during the period of raw material acquisition; , (2) in, The CO2 emissions of the copper wire of a single transformer during the period of raw material acquisition; , (3) in, The carbon dioxide emissions of the insulation components of a single transformer during the period of raw material acquisition; , (4) in, The carbon dioxide emissions from transformer oil of a single transformer during the period of raw material acquisition; , (5) in, The carbon dioxide emissions from the oil tank of a single transformer during the period of raw material acquisition; During the raw material transportation period, when the electro-galvanized product is a 200kVA oil-immersed distribution transformer, the following formulas (6) to (9) are used to calculate the carbon dioxide emissions: , (6) in, is the carbon dioxide emission of a single transformer core during the transportation period of raw materials, The transportation mileage of the raw materials of the iron core during the raw materials transportation period; , (7) in, is the carbon dioxide emission of the copper wire of a single transformer during the transportation period of raw materials, The transportation mileage of the raw materials of the copper wire during the raw materials transportation period; , (8) in, is the carbon dioxide emission of the insulation parts of a single transformer during the transportation period of raw materials, The transportation mileage of the raw materials of the insulation parts during the raw materials transportation period; , (9) in, is the carbon dioxide emission of the insulation parts of a single transformer during the transportation period of raw materials, The transportation mileage of the raw materials of the insulation parts during the raw materials transportation period; During the production period, when the electro-galvanized product is a 200kVA oil-immersed distribution transformer, the following formulas (10) to (14) are used to calculate the carbon dioxide emissions: , (10) in, The carbon dioxide emissions generated by the coil production of a single transformer during the product production period; , (11) in, The carbon dioxide emissions generated by the insulation assembly of a single transformer during the production period of the product; , (12) in, The carbon dioxide emissions generated by the production of a single transformer oil tank during the production period; , (13) in, The CO2 emissions generated by the final assembly of a single transformer during the product production period; , (14) in, The carbon dioxide emissions generated by the testing of a single transformer during the production period of the product; During the product transportation period, when the electro-galvanized product is a 200kVA oil-immersed distribution transformer, the following formula (15) is used to calculate the carbon dioxide emissions: , (15) in, The carbon dioxide emissions of a single transformer during the product transportation period; During the product life, when the electro-galvanized product is a 200kVA oil-immersed distribution transformer, the following formula (16) is used to calculate the carbon dioxide emissions: , (16) in, is the carbon dioxide emissions of a single transformer during the product life, is the cumulative working power of the transformer; During the product recovery period, when the electro-galvanized product is a 200kVA oil-immersed distribution transformer, the following formula (17) and formula (18) are used to calculate the carbon dioxide emissions: , (17) in, The carbon dioxide emissions of a single transformer during the product payback period; , (18) in, It is the carbon dioxide emission of a single transformer during the product payback period.

[0023] Step S12 may be used to correct the carbon dioxide emissions using a preset carbon footprint prediction model. The specific method for correcting the carbon dioxide emissions using the carbon footprint prediction model may be in various forms known to those skilled in the art. In one example of the present invention, the specific method for correcting the carbon dioxide emissions using the carbon footprint prediction model may include: Figure 2 In the steps shown in Figure 2 In the method, the specific method of correcting carbon dioxide emissions using the carbon footprint prediction model may include the following steps: In step S20, the electric energy meter account, electric carbon meter account, energy consumption account, and product input and output account information of the electro-galvanized product in the production stage are obtained; In step S21, the information of the electricity meter ledger, the electricity carbon meter ledger, the energy consumption ledger, and the product input and output ledger is preprocessed to obtain the corresponding ledger features. Specifically, in this example, the preprocessing method can be to first perform a data cleaning operation on the electricity meter ledger, the electricity carbon meter ledger, the energy consumption ledger, and the product input and output ledger information, and then perform a data completion operation on the missing information of the electricity meter ledger, the electricity carbon meter ledger, the energy consumption ledger, and the product input and output ledger information after the data cleaning operation, and then sample the data point values ​​of the electricity meter ledger, the electricity carbon meter ledger, the energy consumption ledger, and the product input and output ledger information after the data completion operation according to the preset sampling points in the time series to obtain multiple ledger matrices, and finally, combine the ledger matrices to obtain the ledger features.

[0024] In step S22, each ledger feature is combined to obtain a fused feature; In step S23, the fused features are input into the carbon footprint prediction model to obtain the predicted carbon dioxide emissions. The specific structure of the carbon footprint prediction model can be in various forms known to those skilled in the art. In this example, considering the distribution characteristics of the ledger data, the carbon footprint prediction model can include an ARDL model (AutoRegressiveDistributed Lag), an XGBoost model, a linear regression model, a DNN model, and a DS output layer.

[0025] Among them, the ARDL model, XGBoost model, linear regression model, and DNN model are used to output the corresponding classification results according to the ledger characteristics, while the DS output layer can use the DS evidence theory to determine the final prediction result for each classification result. More specifically, in this example, the ARDL model is a statistical model for time series data analysis, which combines the characteristics of the AutoRegressive (AR) model and the Distributed Lag (DL) model. The ARDL model can capture the dynamic relationship between variables and can simultaneously estimate the short-term and long-term equilibrium relationship between variables.

[0026] In the ARDL model, the autoregressive part describes the relationship between the current value of a variable and its historical value, while the distributed lag part considers that the impact of one or more explanatory variables on the explained variable may occur at different time points. Since the distribution of ledger characteristics is statistically calculated based on a single month or a single reporting cycle, the ARDL model can obviously adapt to this feature well. As for the representation of the ARDL model, in this example, the following formula (1) can be used to determine the ARDL model: , (1) in, is the output of the ARDL model, is a constant term, Output The autoregressive order of Output The autoregression coefficient of is the output of the previous layer, is the input of the previous layer, For input The lag order of For input The lag term coefficient of is the autoregressive coefficient of the first layer, is the initial input, is the error term.

[0027] In addition, the ARDL model is a statistical model for time series data analysis that can capture the dynamic relationship between variables and simultaneously estimate the short-term and long-term equilibrium relationship between variables. In the ARDL model, the autoregressive part describes the relationship between the current value of a variable and its historical value, while the distributed lag part takes into account that the impact of one or more explanatory variables on the explained variable may occur at different time points. In this example, the independent variables and dependent variables that can be used are electricity consumption data and electrogalvanizing process electricity data (ledger characteristics), and training is carried out according to lag 1 and lag 2 respectively. Specifically: The training results of the lagged 1-order line are as follows Figure 3 As shown. Figure 3 In the study, the standardized coefficient (Beta) calculated by the ARDL model was 0.358, reflecting the relative importance of electricity consumption in the electrogalvanizing process, but it did not reach statistical significance (t=1.151, P=079). The overall fit of the model was evaluated by R² and adjusted R², which were 0.128 and 0.031 respectively, and F statistic (F=1.324, P=0.279).

[0028] The training results of the lagged 2-order line are as follows Figure 4 As shown. Figure 4In the analysis, the standardized coefficient (Beta) calculated by the ARDL model is 0.063, reflecting the low importance of electricity consumption in the electrogalvanizing process. The overall fit R² and adjusted R² of the model are extremely low, 0.004 and -0.121 respectively, and the value of the F statistic is very small (F=0.032), with a corresponding P value of 0.862, indicating a poor overall fit.

[0029] Therefore, in this example, the ARDL model may be trained by using a lagged 1-order line training method.

[0030] The XGBoost model is a regression model based on gradient boosting trees and is one of the most widely used machine learning models in various regression tasks. Its full name is Extreme Gradient Boosting Regressor. It is an efficient, flexible and scalable machine learning method that can process various types of data, including numerical and categorical data, which is obviously a data form that can well adapt to the characteristics of ledgers.

[0031] The basic principle of the XGBoost model is to build a more powerful and complex model by combining multiple simple decision trees. The gradient boosting tree gradually optimizes each decision tree, making the model's prediction results more and more accurate, thereby achieving the final prediction goal.

[0032] In this example, in order to determine the XGBoost model and the best loss function, the same training samples (8 training sets and 4 test sets) can be used to train the XGBoost model to determine the best loss function. The training results are shown in Table 1 below: Table 1

[0033] From the training results shown in Table 1, it can be seen that the mean square error (MSE) and root mean square error (RMSE) increase significantly on the test set, indicating that the model has obvious prediction errors on unseen data, and there may be overfitting or the data characteristics of the test set are quite different from those of the training set. The MSE and RMSE values ​​on the training set are relatively low, indicating that the model fits the training data well, but the sharp increase on the test set (especially the RMSE jump from 4546.065 to 165060.801) warns of the lack of generalization ability of the model. The mean absolute error (MAE) also increases significantly on the test set, and the coefficient of determination (R²) decreases significantly, further indicating that the model training effect is not good. Therefore, in this example, the loss function of the XGBoost model can be set to the mean square error function. With this setting, the training process of the gradient boosting tree becomes a step-by-step iterative process. Each step builds a new decision tree based on the previous step and optimizes the prediction effect of the model according to the loss function. In each iteration, the gradient boosting tree calculates the prediction error of the current model for each sample, and then uses these errors as new target variables to train the next decision tree. In this example, the XGBoost model can also be Figure 5 Correspondingly, the XGBoost model is also expressed by the following formula (2): , (2) in, is the prediction output of the XGBoost model, is the calculated value of the basis function, is the number of decision trees, is a set of decision trees, For the A decision tree.

[0034] Linear regression is a statistical method used to establish the relationship between one or more independent variables (also called predictor variables or explanatory variables) and a dependent variable (also called response variable or outcome variable). The goal of linear regression is to find the best fit line to predict the value of the dependent variable based on the values ​​of the independent variables. Its advantages include its simplicity and interpretability, while its disadvantages include the linear assumption and sensitivity to outliers. In this example, the linear regression model can also be expressed as the following formula (3), , (3) in, is the output of the linear regression model, is the intercept, , , is the independent variable, , , is the regression coefficient, is the error term.

[0035] In this example, the results of training the linear regression model are shown in the figure below. Figure 6 As shown. Figure 6 It can be seen that the linear regression model has a high degree of fit, specifically R² and adjusted R² are 0.716 and 0.688 respectively, indicating that the independent variable of electricity can explain most of the variability of the dependent variable electricity (about 69%). The F statistic is significant (F=25.264, P=0.001***). It reflects the relative impact of electricity on electricity when considering the standard deviation of all variables, indicating that electricity is one of the main explanatory variables for the change in electricity in the electrogalvanizing process, and the model fitting effect is good. In summary, the linear regression algorithm model has a good fitting effect, with R² and adjusted R² of 0.716 and 0.688 respectively. Therefore, the linear regression algorithm model algorithm is selected to realize the function of calculating the production situation of the electrogalvanizing process based on the electricity consumption of Bengang plate.

[0036] The DNN model is a fully connected neural network, also known as a deep neural network. Each neuron node has an operational relationship with each node in the next layer, so it is called a fully connected neural network. DNN is generally composed of an input layer, a hidden layer, and an output layer. The more hidden layers there are, the more complex the calculation is, and the better the fit with the training set is, but it is prone to overfitting. The training of a fully connected neural network is divided into two processes: forward propagation and backward propagation. The forward propagation data is transferred from the input to the output and then the loss function value is calculated. The backward propagation is an optimization process that uses the gradient descent method to reduce the loss function value generated by the forward propagation, thereby optimizing and updating the parameters. The DNN model can be as follows: Figure 4 In the structure shown in FIG. 1 , in this example, the softmax function can be used as the classification function of the output layer of the DNN model.

[0037] In step S24, the predicted carbon dioxide emission amount is added to the carbon dioxide emission amount to obtain a corrected carbon dioxide emission amount.

[0038] On the other hand, the present invention also provides a carbon footprint calculation system for electro-galvanized products based on electric power big data, the system comprising a processor, and the processor is configured to execute any of the methods described above.

[0039] Through the above technical solution, the present invention provides a method and system for calculating the carbon footprint of electrogalvanized products based on power big data. The method and system use numerical calculation methods to determine the numerical range of carbon dioxide emissions, thereby avoiding the defect of numerical overflow of subsequent prediction models. On this basis, the method and system further use the predicted value of the prediction model to correct the calculation results, thereby overcoming the influence of human factors and realizing accurate calculation of carbon dioxide emissions.

[0040] Those skilled in the art should understand that the embodiments of the present application can provide methods, systems, and computer program products. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0041] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0042] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0043] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0044] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0045] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0046] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0047] It should also be noted that the terms "comprises", "includes" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device that includes a series of elements includes not only those elements, but also other elements that are not explicitly listed, including elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device that includes the elements.

[0048] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for calculating the carbon footprint of electro-galvanized products based on power big data, characterized in that: The method comprises: Obtain basic information on the quantity of electrogalvanized products and each process stage in their life cycle; Determine the carbon dioxide emissions of the electro-galvanized product based on the quantity and basic information; Correcting the carbon dioxide emissions using a preset carbon footprint prediction model; The carbon footprint trend of the electro-galvanized product is depicted according to the corrected carbon dioxide emissions.

2. The method according to claim 1, characterized in that The process stages include raw material acquisition period, raw material transportation period, product production period, product transportation period, product use period and product recovery period.

3. The method according to claim 2, characterized in that Determine the carbon dioxide emissions of the electro-galvanized product based on the quantity and basic information, including: During the raw material acquisition period, when the electro-galvanized product is a 200kVA oil-immersed distribution transformer, the following formulas (1) to (5) are used to calculate the carbon dioxide emissions: ，（1） in, The carbon dioxide emissions of the iron core of a single transformer during the period of raw material acquisition; ，（2） in, The carbon dioxide emissions of the copper wire of a single transformer during the period of raw material acquisition; ，（3） in, The carbon dioxide emissions from the insulation components of a single transformer during the period of raw material acquisition; ，（4） in, The carbon dioxide emissions from transformer oil of a single transformer during the period of raw material acquisition; ，（5） in, The carbon dioxide emissions from the oil tank of a single transformer during the period of raw material acquisition; During the raw material transportation period, when the electro-galvanized product is a 200kVA oil-immersed distribution transformer, the following formulas (6) to (9) are used to calculate the carbon dioxide emissions: ，（6） in, is the carbon dioxide emission of the iron core of a single transformer during the transportation period of raw materials, The transportation mileage of the raw materials of the iron core during the raw materials transportation period; ，（7） in, is the carbon dioxide emission of the copper wire of a single transformer during the transportation period of raw materials, The transportation mileage of the raw materials of the copper wire during the raw materials transportation period; ，（8） in, is the carbon dioxide emission of the insulation components of a single transformer during the transportation period of raw materials, The transportation mileage of the raw materials of the insulation parts during the raw materials transportation period; ，（9） in, is the carbon dioxide emission of the insulation components of a single transformer during the transportation period of raw materials, The transportation mileage of the raw materials of the insulation parts during the raw materials transportation period; During the product production period, when the electro-galvanized product is a 200kVA oil-immersed distribution transformer, the following formulas (10) to (14) are used to calculate the carbon dioxide emissions: ，（10） in, The carbon dioxide emissions generated by the coil production of a single transformer during the production period of the product; ，（11） in, The carbon dioxide emissions generated by the insulation assembly of a single transformer during the production period of the product; ，（12） in, The carbon dioxide emissions generated by the production of the oil tank of a single transformer during the production period of the product; ，（13） in, The carbon dioxide emissions generated by the final assembly of a single transformer during the production period of the product; ，（14） in, The carbon dioxide emissions generated by the test of a single transformer during the production period of the product; During the product transportation period, when the electro-galvanized product is a 200kVA oil-immersed distribution transformer, the following formula (15) is used to calculate the carbon dioxide emissions: ，（15） in, The carbon dioxide emissions of a single transformer during the product transportation period; During the product life, when the electro-galvanized product is a 200kVA oil-immersed distribution transformer, the carbon dioxide emissions are calculated using the following formula (16): ，（16） in, is the carbon dioxide emissions of a single transformer during the product life, is the accumulated working power of the transformer; During the product recovery period, when the electro-galvanized product is a 200kVA oil-immersed distribution transformer, the carbon dioxide emissions are calculated using the following formulas (17) and (18): ，（17） in, The carbon dioxide emissions of a single transformer during the product payback period; ，（18） in, It is the carbon dioxide emission of a single transformer during the product recovery period.

4. The method according to claim 2, characterized in that: The carbon dioxide emissions are corrected using a preset carbon footprint prediction model, including: Obtain the electricity meter ledger, electricity carbon meter ledger, energy consumption ledger, and product input and output ledger information of electrogalvanized products during the production stage; Preprocessing the electric energy meter ledger, electric carbon meter ledger, energy consumption ledger, and product input and output ledger information to obtain corresponding ledger features; Combining each of the ledger features to obtain a fused feature; Inputting the fused features into the carbon footprint prediction model to obtain predicted carbon dioxide emissions; The predicted carbon dioxide emission amount is added to the carbon dioxide emission amount to obtain the corrected carbon dioxide emission amount.

5. The method according to claim 4, characterized in that The electric energy meter ledger, electric carbon meter ledger, energy consumption ledger and product input and output ledger information are preprocessed to obtain corresponding ledger features, including: Perform data cleaning operations on the electricity meter ledger, electricity carbon meter ledger, energy consumption ledger, and product input and output ledger information; Perform data completion operations on the missing information of the electric energy meter ledger, electric carbon meter ledger, energy consumption ledger, and product input and output ledger information after the data cleaning operation; The data point values ​​of the electric energy meter ledger, electric carbon meter ledger, energy consumption ledger and product input and output ledger information after the sampling data of the preset sampling points in the time series are completed to obtain multiple ledger matrices; The ledger matrices are combined to obtain the ledger features.

6. The method according to claim 4, characterized in that The carbon footprint prediction model includes an ARDL model, an XGBoost model, a linear regression model, a DNN model and a DS output layer.

7. The method according to claim 6, characterized in that The method comprises: The ARDL model is expressed using formula (1): ，（1） in, is the output of the ARDL model, is a constant term, Output The autoregressive order of Output The autoregression coefficient of is the output of the previous layer, is the input of the previous layer, For input The lag order of For input The lag term coefficient of is the autoregressive coefficient of the first layer, is the initial input, is the error term; Formula (2) is used to represent the XGBoost model: ，（2） in, is the prediction output of the XGBoost model, is the calculated value of the basis function, is the number of decision trees, is a set of decision trees, For the A decision tree.

8. The method according to claim 6, characterized in that The method comprises: The linear regression model is expressed by formula (3): ，（3） in, is the output of the linear regression model, is the intercept, , , is the independent variable, , , is the regression coefficient, is the error term; The softmax function is used as the classification function of the output layer of the DNN model.

9. The method according to claim 6, characterized in that The DS output layer is used to: The final output is determined according to the outputs of the ARDL model, XGBoost model, linear regression model, and DNN model in accordance with the DS evidence theory.

10. A carbon footprint calculation system for electrogalvanized products based on power big data, characterized in that: The system comprises a processor configured to execute the method according to any one of claims 1 to 9.

Images