Method, device and equipment for predicting carbon emission of electrolytic aluminum plant and storage medium

Abstract

The embodiment of the invention discloses a carbon emission prediction method and device for an electrolytic aluminum factory, equipment and a storage medium, and relates to the technical field of carbon emission calculation, and the method comprises the steps: obtaining a first carbon emission and an electrolytic aluminum yield of the electrolytic aluminum factory in a historical time interval, and determining a first unit carbon emission according to the first carbon emission and the electrolytic aluminum yield; inputting the first unit carbon emission into a pre-trained carbon emission prediction model to obtain a target unit carbon emission of the electrolytic aluminum plant in the target time interval; obtaining a second carbon emission amount when the upstream supplier produces the raw materials with the preset weight, and determining a second unit carbon emission amount according to the preset weight and the second carbon emission amount; and determining the sum of the target unit carbon emission and the second unit carbon emission as the total unit carbon emission of the electrolytic aluminum plant in the target time interval, so that the carbon emission condition of the electrolytic aluminum plant in a future period of time can be accurately predicted, and an effective emission reduction strategy can be formulated for the electrolytic aluminum plant in advance.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of carbon emission calculation technology, and in particular to a method, device, equipment and storage medium for predicting carbon emissions of an aluminum electrolytic plant. Background Art

[0002] As global awareness of environmental protection increases, carbon emission control in industrial production has become an important issue. As an energy-intensive industry, the accurate prediction of carbon emissions in the electrolytic aluminum industry is crucial for formulating effective emission reduction strategies.

[0003] The existing method for determining carbon emissions manually counts the carbon dioxide emissions of aluminum smelters during the production process to determine the carbon emission level of aluminum smelters. However, it is impossible to predict the carbon emissions of aluminum smelters in the future, and thus it is impossible to formulate effective emission reduction strategies for aluminum smelters in advance. Summary of the invention

[0004] The embodiments of the present application provide a method, device, equipment and storage medium for predicting carbon emissions of an aluminum smelter, which realize the carbon emissions prediction function of the aluminum smelter to solve the problem in the prior art that the carbon emissions of the aluminum smelter in the future cannot be predicted, and thus effective emission reduction strategies can be formulated for the aluminum smelter in advance.

[0005] In a first aspect, an embodiment of the present application provides a method for predicting carbon emissions of an aluminum smelter, the method comprising:

[0006] Obtain the first carbon emission and electrolytic aluminum output of the electrolytic aluminum plant in the historical time interval, and determine the first unit carbon emission according to the first carbon emission and the electrolytic aluminum output, where the first unit carbon emission is the carbon emission when the electrolytic aluminum plant produces a unit weight of electrolytic aluminum in the historical time interval;

[0007] The first unit carbon emission is input into the pre-trained carbon emission prediction model to obtain the target unit carbon emission of the electrolytic aluminum plant in the target time interval, where the target time interval is the same period of the historical time interval in the next cycle;

[0008] Obtain the second carbon emissions of the upstream supplier when producing a preset weight of raw materials, and determine the second unit carbon emissions based on the preset weight and the second carbon emissions. The preset weight of raw materials is consumed by the electrolytic aluminum plant within the target time interval to produce electrolytic aluminum. The second unit carbon emissions are the carbon emissions of the upstream supplier when producing a unit weight of raw materials;

[0009] The sum of the target unit carbon emissions and the second unit carbon emissions is determined as the total unit carbon emissions of the electrolytic aluminum plant within the target time interval.

[0010] In a second aspect, an embodiment of the present application provides a device for predicting carbon emissions of an aluminum electrolytic plant, the device comprising:

[0011] A first acquisition module is used to obtain a first carbon emission and an electrolytic aluminum output of the electrolytic aluminum plant in a historical time interval, and determine a first unit carbon emission according to the first carbon emission and the electrolytic aluminum output, where the first unit carbon emission is the carbon emission when the electrolytic aluminum plant produces a unit weight of electrolytic aluminum in the historical time interval;

[0012] A prediction module is used to input the first unit carbon emission into a pre-trained carbon emission prediction model to obtain a target unit carbon emission of the electrolytic aluminum plant within a target time interval, where the target time interval is the same period of the historical time interval in the next cycle;

[0013] A second acquisition module is used to obtain a second carbon emission amount when an upstream supplier produces a preset weight of raw materials, and determine a second unit carbon emission amount based on the preset weight and the second carbon emission amount. The preset weight of raw materials is consumed by the electrolytic aluminum plant within the target time interval and electrolytic aluminum is produced. The second unit carbon emission amount is the carbon emission amount when the upstream supplier produces a unit weight of raw materials;

[0014] A determination module is used to determine the sum of the target unit carbon emissions and the second unit carbon emissions as the total unit carbon emissions of the electrolytic aluminum plant within the target time interval.

[0015] In a third aspect, an embodiment of the present application provides an electronic device, the electronic device comprising:

[0016] at least one processor; and a memory communicatively coupled to the at least one processor;

[0017] Among them, the memory stores a computer program that can be executed by at least one processor, and the computer program is executed by at least one processor so that the at least one processor can execute the carbon emissions prediction method for the electrolytic aluminum plant of any embodiment of the present application.

[0018] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a method for predicting carbon emissions of an aluminum electrolytic plant as described in any embodiment of the present application.

[0019] In an embodiment of the present application, a first carbon emissions and electrolytic aluminum production of an aluminum smelter in a historical time period can be obtained, and a first unit carbon emissions can be determined based on the first carbon emissions and the electrolytic aluminum production; the first unit carbon emissions are input into a pre-trained carbon emissions prediction model to obtain a target unit carbon emissions of the aluminum smelter in a target time period; the second carbon emissions of an upstream supplier when producing a preset weight of raw materials are obtained, and a second unit carbon emissions is determined based on the preset weight and the second carbon emissions; the sum of the target unit carbon emissions and the second unit carbon emissions is determined as the total unit carbon emissions of the aluminum smelter in the target time period. In the above technical scheme, the carbon emissions of the aluminum smelter in the future can be accurately predicted through the pre-trained carbon emissions prediction model, and the first unit carbon emissions are used as the input value of the carbon emissions prediction model, so as to accurately predict the target unit carbon emissions of the aluminum smelter in the target time period, which effectively solves the problem that the existing technology cannot predict the carbon emissions of the aluminum smelter in the future period; and then further through the second unit carbon emissions of the upstream supplier, the total unit carbon emissions of the aluminum smelter in the target time period can be determined, which takes into account both the carbon emissions in the production process of the aluminum smelter itself and the carbon emissions in the production process of raw materials by the upstream suppliers, thereby helping the aluminum smelter to accurately and quickly complete the product carbon footprint declaration report, so that effective emission reduction strategies can be formulated for the aluminum smelter in advance, such as controlling high carbon emission process modules. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 It is a flow chart of a method for predicting carbon emissions of an aluminum electrolytic plant provided in an embodiment of the present application;

[0022] Figure 2 is another flow chart of the method for predicting carbon emissions of an aluminum electrolytic plant provided in an embodiment of the present application;

[0023] Figure 3 It is a structural schematic diagram of a carbon emission prediction device for an electrolytic aluminum plant provided in an embodiment of the present application;

[0024] Figure 4 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this application.

[0026] It should be noted that the terms "first", "second", "target", and "original" in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including", "having", and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0027] Figure 1 It is a flow chart of the method for predicting carbon emissions of an aluminum smelter provided in an embodiment of the present application. This embodiment can be applied to scenarios where it is necessary to predict the carbon emissions of an aluminum smelter in the future. The method for predicting carbon emissions of an aluminum smelter provided in this embodiment can be executed by the carbon emissions prediction device for an aluminum smelter provided in an embodiment of the present application, and the device can be implemented in software and / or hardware. In a specific embodiment, the carbon emissions prediction device for an aluminum smelter can be integrated in an electronic device, for example, the electronic device can be a computer, etc. The execution subject of this method can be an electronic device, see Figure 1 The carbon emission prediction method of the aluminum smelter in this embodiment includes but is not limited to the following steps:

[0028] S110. Obtain the first carbon emissions and electrolytic aluminum production of the electrolytic aluminum plant within a historical time period, and determine the first unit carbon emissions based on the first carbon emissions and electrolytic aluminum production.

[0029] Among them, the historical time interval is a specific time period in the past, which can be used as a reference for analyzing the carbon emissions of the electrolytic aluminum plant within the target time interval; the target time interval is the same period of the historical time interval in the next cycle, and the cycle represents the changing cycle of the carbon emissions of the electrolytic aluminum plant when producing unit weight of electrolytic aluminum; for example, if one year is a cycle, then when the historical time interval is January 2023, the target time interval is January 2024; when the historical time interval is the first quarter of 2023, the target time interval is the first quarter of 2024.

[0030] The first carbon emissions are the total amount of carbon dioxide and other greenhouse gas emissions generated by the aluminum smelter during the historical time period due to the production of electrolytic aluminum. The first carbon emissions may include all carbon emissions of the aluminum smelter itself in the process of electrolytic aluminum production, such as the carbon emissions generated by the electrolytic cell during the electrolysis process, the carbon emissions generated by electricity consumption during the operation of the electrolytic cell, and the carbon emissions generated by energy consumption (such as electricity and fuel, etc.) during the operation of other equipment.

[0031] The output of electrolytic aluminum is the weight of electrolytic aluminum produced by the electrolytic aluminum plant in the historical time interval, and the carbon emissions generated by the electrolytic aluminum plant when producing these weights of electrolytic aluminum are the first carbon emissions; the unit of electrolytic aluminum output is usually tons. The first unit carbon emissions are the carbon emissions when the electrolytic aluminum plant produces unit weight of electrolytic aluminum in the historical time interval. For example, the first unit carbon emissions are the carbon emissions generated when the electrolytic aluminum plant produces unit tons of electrolytic aluminum in the historical time interval.

[0032] Specifically, when it is necessary to predict the carbon emissions of the aluminum smelter within the target time interval, the same period of the target time interval in the previous cycle, that is, the historical time interval, can be determined, and the first carbon emissions of the aluminum smelter in the historical time interval can be obtained.

[0033] Specifically, in one implementation, the total carbon emissions generated by the electrolytic aluminum plant in the historical time interval are directly measured using monitoring equipment (such as gas analyzers and flow meters) installed in locations such as electrolytic cells and emission chimneys to obtain the first carbon emissions. In another implementation, various energy consumption data of the electrolytic aluminum plant in the historical time interval are obtained from the production management system of the electrolytic aluminum plant, including electricity, natural gas and fuel oil. For electricity consumption, if it is purchased from the power grid, the carbon emissions generated by electricity consumption can be calculated based on the carbon emission factor provided by the power grid (i.e., the carbon dioxide emissions corresponding to each kilowatt-hour of electricity); for natural gas and fuel oil, the carbon emissions generated by combustion are calculated based on the chemical equation of their combustion and their respective carbon content, thereby obtaining the total carbon emissions generated by the electrolytic aluminum plant in the historical time interval, i.e., the first carbon emissions. In another implementation, the production ledger of the electrolytic aluminum plant can be consulted to obtain production activity data directly related to carbon emissions in the historical time interval, thereby obtaining the first carbon emissions.

[0034] Then, the electrolytic aluminum production of the electrolytic aluminum plant in the historical time interval can be obtained, for example, the production report in the historical time interval is obtained from the production department of the electrolytic aluminum plant, and the total production data of electrolytic aluminum in the historical time interval of the electrolytic aluminum plant is obtained, that is, the electrolytic aluminum production. Afterwards, the first unit carbon emission can be determined according to the first carbon emission and the electrolytic aluminum production, that is, the ratio of the first carbon emission to the electrolytic aluminum production can be calculated, and the ratio can be determined as the first unit carbon emission.

[0035] S120. Input the first unit carbon emission into a pre-trained carbon emission prediction model to obtain the target unit carbon emission of the electrolytic aluminum plant within the target time interval.

[0036] The carbon emission prediction model is used to analyze and learn the past carbon emissions of the aluminum smelter to capture the law of changes in the unit carbon emissions of the aluminum smelter over time, and to predict the carbon emissions of the aluminum smelter in the future. For example, the carbon emission prediction model can be a time series analysis model or a regression model.

[0037] The target unit carbon emissions are the carbon emissions that the aluminum smelter is expected to generate when producing unit weight of electrolytic aluminum within the target time period. It can help the aluminum smelter plan emission reduction measures in advance and understand future carbon emission trends.

[0038] Specifically, after obtaining the first unit of carbon emissions, a pre-trained carbon emissions prediction model can be obtained, and the first unit of carbon emissions can be input into the carbon emissions prediction model. At this time, the carbon emissions prediction model can process the first unit of carbon emissions based on the pre-learned patterns and rules using internal algorithms and parameters, and output predicted carbon emissions; thereafter, the predicted carbon emissions output by the carbon emissions prediction model can be determined as the target unit carbon emissions of the electrolytic aluminum plant within the target time interval.

[0039] S130. Obtain a second carbon emission amount when an upstream supplier produces a preset weight of raw materials, and determine a second unit carbon emission amount based on the preset weight and the second carbon emission amount.

[0040] Among them, upstream suppliers are enterprises or units that provide the raw materials needed for the production of electrolytic aluminum to the aluminum smelter; in the production of electrolytic aluminum, upstream suppliers can provide the aluminum smelter with raw materials such as alumina, anode carbon blocks and cathode carbon blocks, and the production process of these raw materials will also produce carbon emissions, which will indirectly affect the total carbon footprint of the aluminum smelter.

[0041] The preset weight is the weight of the raw materials determined in advance according to the actual production plan of the electrolytic aluminum plant; the raw materials of the preset weight are consumed by the electrolytic aluminum plant within the target time period to produce electrolytic aluminum.

[0042] The second carbon emissions are the total amount of carbon dioxide and other greenhouse gas emissions generated by the upstream supplier when producing a preset weight of raw materials; the second carbon emissions may include all carbon emissions in the raw material production process, such as energy consumption emissions in the ore mining process and reaction emissions in the alumina refining process, or calcination and roasting emissions in the production of anode / cathode carbon blocks, etc. The second unit carbon emissions are the carbon emissions when the upstream supplier produces a unit weight of raw materials. For example, the second unit carbon emissions are the carbon emissions generated when the upstream supplier produces a unit ton of raw materials.

[0043] Specifically, the user can determine the weight of electrolytic aluminum that the aluminum smelter needs to produce within the target time period based on the actual production plan of the aluminum smelter, record it as the first weight, and enter the first weight into the electronic device through the keyboard. The electronic device can then receive the first weight sent by the user, and determine the preset weight of each raw material required to produce the first weight of electrolytic aluminum based on the actual production consumption situation, that is, there are multiple preset weights, and each raw material corresponds to a preset weight, and the value of the preset weight corresponding to each raw material may be the same or different.

[0044] Then, the second carbon emissions of the upstream supplier when producing a preset weight of raw materials can be obtained. For example, since an upstream supplier only provides one raw material to the electrolytic aluminum plant, the upstream supplier corresponding to each raw material can be determined. At this time, there are multiple upstream suppliers. Then, the carbon emissions generated in the process of producing the corresponding preset weight of raw materials can be obtained from the production records of each upstream supplier to obtain the second carbon emissions corresponding to each upstream supplier.

[0045] Afterwards, the second unit carbon emissions can be determined based on the preset weight and the second carbon emissions. That is, the ratio of the second carbon emissions corresponding to each upstream supplier to the corresponding preset weight can be calculated to obtain the unit carbon emissions corresponding to each upstream supplier. At this time, there are multiple unit carbon emissions, and then the sum of the aforementioned multiple unit carbon emissions is calculated to obtain the second unit carbon emissions.

[0046] S140. Determine the sum of the target unit carbon emissions and the second unit carbon emissions as the total unit carbon emissions of the electrolytic aluminum plant within the target time interval.

[0047] Among them, the total unit carbon emissions are the comprehensive carbon emissions of the electrolytic aluminum plant when it produces unit weight of electrolytic aluminum within the target time period, taking into account its own production process (i.e. the target unit carbon emissions) and the upstream supplier's raw material production process (i.e. the second unit carbon emissions). It is used to comprehensively evaluate the carbon emissions of the electrolytic aluminum plant when producing unit weight of electrolytic aluminum, including direct and indirect carbon emission factors.

[0048] Specifically, after obtaining the second unit carbon emissions, the sum of the target unit carbon emissions and the second unit carbon emissions can be calculated, and the sum can be determined as the total unit carbon emissions of the electrolytic aluminum plant within the target time interval.

[0049] The technical solution of the embodiment of the present application can accurately predict the carbon emissions of the aluminum smelter in the future through a pre-trained carbon emissions prediction model, and use the first unit carbon emissions as the input value of the carbon emissions prediction model to accurately predict the target unit carbon emissions of the aluminum smelter in the target time interval, effectively solving the problem that the existing technology cannot predict the carbon emissions of the aluminum smelter in the future; and then further through the second unit carbon emissions of the upstream supplier, the total unit carbon emissions of the aluminum smelter in the target time interval can be determined, which takes into account both the carbon emissions in the aluminum smelter's own production process and the carbon emissions in the upstream supplier's production process of raw materials, thereby helping the aluminum smelter to accurately and quickly complete the product carbon footprint declaration report, so that effective emission reduction strategies can be formulated for the aluminum smelter in advance, such as controlling high-carbon emission process modules.

[0050] The following further describes a method for predicting carbon emissions from an aluminum electrolytic plant provided in an embodiment of the present application. Figure 2 This is another flow chart of the carbon emission prediction method of the electrolytic aluminum plant provided in the embodiment of the present application. The embodiment of the present application is optimized on the basis of the above embodiments. Figure 2 The method of this embodiment includes but is not limited to the following steps:

[0051] S210. Obtain the first carbon emission and electrolytic aluminum output of the electrolytic aluminum plant within a historical time period.

[0052] Optionally, the first carbon emission may include carbon dioxide emission and perfluorocarbon emission, that is, on-site measurements may be conducted on the aluminum smelter in the historical time interval, including carbon dioxide and perfluorocarbon in the air, so as to obtain the carbon dioxide emission and perfluorocarbon emission generated by the aluminum smelter in the historical time interval. Among them, carbon dioxide emission refers to the carbon dioxide emission generated by the aluminum smelter in the historical time interval due to the production of electrolytic aluminum; perfluorocarbon emission refers to the perfluorocarbon emission generated by the aluminum smelter in the historical time interval due to the production of electrolytic aluminum; perfluorocarbon is a class of fluorine-containing organic compounds, such as carbon tetrafluoride and carbon hexafluoride, which are produced in some specific production links of the aluminum smelter, such as the anode / cathode effect of the electrolytic cell can produce perfluorocarbon; perfluorocarbon is a potent greenhouse gas and has a significant impact on global climate change.

[0053] S220. Convert the perfluorocarbon emissions into carbon dioxide emissions to obtain converted carbon emissions.

[0054] Among them, the converted carbon emissions are the values ​​obtained by converting perfluorocarbon emissions into carbon dioxide equivalents. The purpose is to measure perfluorocarbon emissions and carbon dioxide emissions uniformly with carbon dioxide emissions, so as to facilitate the quantification and comparison of carbon emissions of electrolytic aluminum plants; carbon dioxide equivalents are the measurement units used to compare emissions of different greenhouse gases.

[0055] Specifically, after obtaining the first carbon emission and the electrolytic aluminum output, the perfluorocarbon emission in the first carbon emission can be converted into carbon dioxide emission, that is, the global warming potential of the perfluorocarbon can be obtained, and based on the global warming potential, the perfluorocarbon emission can be converted into carbon dioxide emission to obtain the converted carbon emission. Among them, the global warming potential is used to measure the relative contribution of different greenhouse gases to global warming, and is usually used to measure the contribution of a greenhouse gas to global warming relative to carbon dioxide, that is, the global warming potential represents the multiple of the greenhouse effect generated by a certain weight of a greenhouse gas relative to the same weight of carbon dioxide within a certain time range (usually 100 years).

[0056] Specifically, one can consult authoritative data to obtain the global warming potential values ​​of perfluorocarbons at different time scales, and obtain the global warming potential value with a time scale of 100 years. Then, the product between perfluorocarbon emissions and the global warming potential value is calculated, and the product is determined as the converted carbon emissions, so as to convert perfluorocarbon emissions into carbon dioxide equivalents.

[0057] In the embodiment of the present application, the global warming potential value can be used to unify the emissions of different types of greenhouse gases into a measurement standard based on carbon dioxide, thereby improving the accuracy and efficiency of determining the converted carbon emissions and providing an accurate data basis for the subsequent determination of the first unit of carbon emissions.

[0058] Optionally, after obtaining the converted carbon emissions corresponding to the perfluorocarbon emissions, the emissions of other greenhouse gases can be obtained, and the carbon dioxide equivalents corresponding to other greenhouse gases can be determined based on the corresponding global warming potential values, and then the sum of the carbon dioxide equivalents of all greenhouse gases except carbon dioxide can be determined as the converted carbon emissions.

[0059] S230. Determine the first unit carbon emissions based on the converted carbon emissions, carbon dioxide emissions and electrolytic aluminum production.

[0060] Specifically, after obtaining the converted carbon emissions, the sum of the converted carbon emissions and the carbon dioxide emissions can be calculated, and the ratio of the sum to the electrolytic aluminum output can be calculated, and then the ratio is determined as the first unit carbon emissions.

[0061] S240: Input the first unit carbon emission into a pre-trained carbon emission prediction model to obtain the target unit carbon emission of the electrolytic aluminum plant within the target time interval.

[0062] Optionally, the training process of the carbon emission prediction model is as follows, including Sa1-Sa5:

[0063] Sa1. Get a sample dataset of an aluminum smelter.

[0064] Among them, the sample data set includes multiple historical unit carbon emissions; the historical unit carbon emissions are the carbon emissions generated by each unit weight of electrolytic aluminum produced during the production process of the electrolytic aluminum plant in the historical period, reflecting the carbon emission intensity of the electrolytic aluminum plant in different historical periods; the historical unit carbon emissions include all carbon emissions in the electrolytic aluminum plant's own (ie, the plant's) production process, and are measured based on carbon dioxide emissions.

[0065] Specifically, the carbon emissions and the corresponding electrolytic aluminum output of the electrolytic aluminum plant in different historical periods can be obtained from the production records of the electrolytic aluminum plant, and the ratio of carbon emissions to the corresponding electrolytic aluminum output is determined as the historical unit carbon emissions corresponding to each historical period, and then the historical unit carbon emissions corresponding to different historical periods are organized into a sample data set. For example, the carbon emissions generated by the electrolytic aluminum plant in January 2023 are a, and the electrolytic aluminum output is b, then the historical unit carbon emissions corresponding to January 2023 are a / b; the carbon emissions generated by the electrolytic aluminum plant in February 2023 are c, and the electrolytic aluminum output is d, then the historical unit carbon emissions corresponding to February 2023 are c / d.

[0066] Sa2. Filter out abnormal data in the sample data set to obtain the target sample data set.

[0067] Among them, the target sample data set is the data set obtained after screening out abnormal data from the sample data set of the electrolytic aluminum plant, so that the target sample data set can better represent the carbon emissions of the electrolytic aluminum plant under normal production conditions. These abnormal data may be caused by data recording errors, emergencies in the production process (such as equipment failure and process abnormalities, etc.) or errors in monitoring equipment.

[0068] Specifically, the abnormal data in the sample data set is screened out to obtain the target sample data set, which may include Sb1-Sb2:

[0069] Sb1. Determine the screening interval of the sample data set, and filter out the historical unit carbon emissions that are not within the screening interval from the sample data set to obtain an intermediate sample data set.

[0070] The screening interval is a reasonable value range for unit carbon emissions, with the purpose of removing data that is obviously inconsistent with normal production conditions, such as data during the period of equipment replacement at the electrolytic aluminum plant, or data anomalies caused by monitoring equipment failure. The intermediate sample data set is the data set obtained by removing the historical unit carbon emissions that are not within the screening interval from the sample data set.

[0071] Specifically, the screening interval of the sample data set can be determined, that is, the average value and standard deviation of the carbon emissions of multiple historical units in the sample data set can be determined, and the upper and lower limits of the screening interval can be determined based on the average value and the standard deviation. Specifically, the product between the preset multiple and the standard deviation can be calculated, and then the difference between the average value and the product can be calculated, and the difference can be determined as the lower limit of the screening interval, and then the sum of the average value and the product can be calculated, and the sum can be determined as the upper limit of the screening interval. Among them, the preset multiple is a pre-set value used to determine the screening interval. The embodiment of the present application does not specifically limit this. Exemplarily, the preset multiple can be 3.

[0072] Afterwards, the historical unit carbon emissions within the screening interval can be obtained from the sample data set to obtain an intermediate sample data set to filter out the historical unit carbon emissions that are not within the screening interval in the sample data set.

[0073] Sb2. Obtain the carbon emission baseline value of the electrolytic aluminum plant, and filter out the historical unit carbon emissions that are not within the preset normal range of the carbon emission baseline value from the intermediate sample data set to obtain the target sample data set.

[0074] Among them, the carbon emission baseline value is a reference value for measuring the normal carbon emission level of an aluminum smelter. It is a standard unit of carbon emissions in the aluminum smelter industry. It represents the carbon emissions expected to be generated by an aluminum smelter when producing unit weight of electrolytic aluminum under normal production conditions.

[0075] The preset normal interval is a reasonable range set around the carbon emission benchmark value, which is used to screen out data that does not conform to normal carbon emissions from the intermediate sample data set; if the historical unit carbon emissions are within the preset normal interval, it indicates that the historical unit carbon emissions are carbon emissions data generated within the normal production fluctuation range; otherwise, it indicates that the historical unit carbon emissions are caused by abnormal production conditions (such as equipment failure, process out of control, and sudden changes in raw material quality, etc.), and need to be eliminated. Exemplarily, the preset normal interval can be an interval in which the carbon emission benchmark value fluctuates by a certain percentage (such as ±10% or ±20%).

[0076] Specifically, although the intermediate sample data set has initially eliminated some data that are obviously inconsistent with normal production conditions, it may still contain some data that need to be further screened out, such as data that meet the screening interval in terms of numerical range, but have abnormal carbon emissions due to other factors. Therefore, after obtaining the intermediate sample data set, the industry standards can be referred to to obtain the standard unit carbon emissions of the electrolytic aluminum industry, and the carbon emission baseline value of the electrolytic aluminum plant can be obtained. Then, based on the normal production fluctuations of the electrolytic aluminum industry, the preset normal interval of the carbon emission baseline value is determined, and then the historical unit carbon emissions within the preset normal interval are obtained from the intermediate sample data set to obtain the target sample data set, thereby screening out the historical unit carbon emissions in the intermediate sample data set that are not within the preset normal interval.

[0077] In an embodiment of the present application, based on the screening interval and the preset normal interval of the carbon emission baseline value, the sample data set is screened for abnormal data twice, so that the target sample data set can more accurately reflect the carbon emission law of the electrolytic aluminum plant under normal production conditions, and provide an accurate data basis for the subsequent training of the carbon emission prediction model.

[0078] Sa3. Obtain the historical unit carbon emissions within the first preset time interval from the target sample data set to obtain the sample unit carbon emissions, and obtain the historical unit carbon emissions within the second preset time interval from the target sample data set to obtain the unit carbon emissions label corresponding to the sample unit carbon emissions.

[0079] Among them, the first preset time interval and the second preset time interval are specific time periods pre-selected from the historical period, and the second preset time interval is the same period of the first preset time interval in the next cycle, which is used to determine the sample pairs required for carbon emission prediction model training.

[0080] The sample unit carbon emissions are the historical unit carbon emissions corresponding to the first preset time interval in the target sample data set, that is, the carbon emissions generated when the electrolytic aluminum plant produces unit weight of electrolytic aluminum within the first preset time interval, and are the input value for training the carbon emissions prediction model.

[0081] The unit carbon emission label is the historical unit carbon emission corresponding to the second preset time interval in the target sample data set, that is, the carbon emissions generated when the electrolytic aluminum plant produces unit weight of electrolytic aluminum in the second preset time interval, which is used to guide the training output of the carbon emission prediction model.

[0082] Sa4. Determine a training data set based on the sample unit carbon emissions and the unit carbon emission labels corresponding to the sample unit carbon emissions.

[0083] The training data set includes multiple sample unit carbon emissions and a unit carbon emissions label corresponding to each sample unit carbon emissions.

[0084] Sa5. Input the sample unit carbon emissions in the training data set into the initial carbon emissions prediction model, use the unit carbon emissions labels corresponding to the sample unit carbon emissions to guide the training output of the initial carbon emissions prediction model, train the initial carbon emissions prediction model, and obtain a carbon emissions prediction model.

[0085] Among them, the initial carbon emissions prediction model is a model framework that has not yet been trained, which is used to learn the relationship between the sample unit carbon emissions and the unit carbon emissions label to achieve the prediction function of unit carbon emissions.

[0086] Specifically, the sample unit carbon emissions in the training data set can be input into the initial carbon emissions prediction model to obtain the training output, and then the loss between the training output and the unit carbon emissions label corresponding to the sample unit carbon emissions is calculated, and the parameters of the initial carbon emissions prediction model are updated through the back propagation algorithm to minimize the loss value and obtain the optimal initial carbon emissions prediction model, that is, the carbon emissions prediction model.

[0087] In an embodiment of the present application, by screening out abnormal data in a sample data set, the adverse effects of noise and extreme values ​​in the data on the carbon emissions prediction model are reduced, thereby improving the prediction accuracy of the carbon emissions prediction model; the unit carbon emissions of an aluminum smelter have a certain time correlation due to the influence of factors such as seasonal changes. Therefore, the unit carbon emissions of samples within a first preset time interval in a target sample data set are used as the input of the carbon emissions prediction model, and the unit carbon emissions labels within a second preset time interval are used to guide the output of the carbon emissions prediction model. This correspondence in time series can allow the carbon emissions prediction model to better adapt to the production environment and carbon emissions changes of the aluminum smelter, and thus more accurately capture the law of changes in unit carbon emissions over time, thereby improving the prediction accuracy and reliability of the carbon emissions prediction model.

[0088] S250. Obtain the input amount of the emission source of the upstream supplier when producing a preset weight of raw materials, and determine the carbon dioxide emission factor and perfluorocarbon emission factor of the emission source.

[0089] Among them, the emission source is the activities, equipment, process or substance that can produce greenhouse gases (such as carbon dioxide and perfluorocarbons, etc.) in the process of upstream suppliers producing raw materials of preset weight; exemplarily, the emission source may include alumina refining and the production of anode / cathode carbon blocks, etc.; in the alumina refining process, the Bayer process or other refining processes produce carbon emissions, and alumina is the raw material for the electrolytic aluminum production of aluminum smelters; in the production process of anode carbon blocks, processes such as petroleum coke calcination and anode roasting produce carbon emissions, and anode carbon blocks are the raw materials for the electrolytic aluminum production of aluminum smelters; in the production process of cathode carbon blocks, processes such as anthracite calcination and cathode roasting produce carbon emissions, and cathode carbon blocks are the raw materials for the electrolytic aluminum production of aluminum smelters.

[0090] The input amount is the weight of the greenhouse gas-producing substances input by the emission source in the process of producing the preset weight of raw materials; for example, when the emission source is alumina refining, the input amount includes the weight of raw materials such as bauxite used to refine alumina; when the emission source is the production of anode carbon blocks, the input amount includes the weight of raw materials such as petroleum coke used to produce anode carbon blocks; when the emission source is the production of cathode carbon blocks, the input amount includes the weight of raw materials such as anthracite used to produce cathode carbon blocks. It should be noted that the input amount can also include energy consumption.

[0091] The carbon dioxide emission factor is the amount of carbon dioxide emissions generated by a certain emission source per unit weight of raw materials, and the carbon dioxide emission factor corresponding to each emission source is different. The perfluorocarbon emission factor is the amount of perfluorocarbon emissions generated by a certain emission source per unit weight of raw materials, and the perfluorocarbon emission factor corresponding to each emission source is different.

[0092] Specifically, the user can determine the weight of electrolytic aluminum that the aluminum smelter needs to produce within the target time period based on the actual production plan of the aluminum smelter, record it as the first weight, and enter the first weight into the electronic device through the keyboard. The electronic device can then receive the first weight sent by the user, and determine the preset weight of each raw material required to produce the first weight of electrolytic aluminum based on the actual production consumption situation, that is, there are multiple preset weights, and each raw material corresponds to a preset weight, and the value of the preset weight corresponding to each raw material may be the same or different.

[0093] Since an upstream supplier only provides one raw material to the aluminum smelter, after determining the preset weight corresponding to each raw material, the upstream supplier corresponding to each raw material can be determined. At this time, if there are multiple upstream suppliers, the input amount of emission sources of each upstream supplier when producing the preset weight of raw materials can be obtained from the production records of each upstream supplier respectively; illustratively, when the raw material provided by the upstream supplier to the aluminum smelter is electrolytic aluminum, and the preset weight of the electrolytic aluminum is m tons, the input amount of raw materials such as bauxite when producing m tons of electrolytic aluminum can be obtained from the production record of the upstream supplier; when the raw material provided by the upstream supplier to the aluminum smelter is anode carbon blocks, and the preset weight of the anode carbon blocks is n tons, the input amount of raw materials such as petroleum coke when producing n tons of anode carbon blocks can be obtained from the production record of the upstream supplier.

[0094] Afterwards, the categories of emission sources can be identified, and then based on the categories of emission sources, the carbon dioxide emission factors and perfluorocarbon emission factors corresponding to each emission source can be obtained from the industry guidelines; alternatively, upstream suppliers can measure the carbon dioxide emission factors and perfluorocarbon emission factors corresponding to the emission sources by themselves or entrust a qualified third party to measure the carbon dioxide emission factors and perfluorocarbon emission factors corresponding to the emission sources, and save them in the production records, and then obtain the carbon dioxide emission factors and perfluorocarbon emission factors corresponding to each emission source directly from the production records of the upstream suppliers.

[0095] S260. Determine the second carbon emission amount based on the input amount, the carbon dioxide emission factor and the perfluorocarbon emission factor.

[0096] Specifically, when the emission source only produces carbon dioxide, the product of the input of the emission source and the carbon dioxide emission factor corresponding to the emission source can be calculated to obtain the carbon emissions corresponding to the emission source; when the emission source only produces perfluorocarbons, the product of the input of the emission source and the perfluorocarbon emission factor corresponding to the emission source can be calculated to obtain the perfluorocarbon emissions corresponding to the emission source, and then the product of the emissions and the global warming potential of the perfluorocarbons can be calculated to convert the perfluorocarbon emissions into carbon dioxide equivalents to obtain the carbon emissions corresponding to the emission source. Emissions; when an emission source produces carbon dioxide and perfluorocarbons at the same time, the product of the input of the emission source and the carbon dioxide emission factor corresponding to the emission source can be calculated (recorded as the first product), and then the product of the input of the emission source and the perfluorocarbon emission factor corresponding to the emission source can be calculated (recorded as the second product), and the product of the second product and the global warming potential of perfluorocarbons can be calculated (recorded as the third product), and then the sum of the first product and the third product is determined as the carbon emissions corresponding to the emission source; thereby, the carbon emissions corresponding to an emission source are obtained.

[0097] If there is one emission source in the process of an upstream supplier producing a preset weight of raw materials, the above method can be used to calculate the carbon emissions corresponding to the emission source to obtain the second carbon emissions of the upstream supplier; if there are multiple emission sources in the process of an upstream supplier producing a preset weight of raw materials, the above method can be used to calculate the carbon emissions corresponding to each emission source, and then the sum of the carbon emissions corresponding to the multiple emission sources can be determined as the second carbon emissions of the upstream supplier.

[0098] Optionally, after determining the second carbon emissions based on the input, carbon dioxide emission factor and perfluorocarbon emission factor, the carbon emissions reported by the upstream supplier when producing a preset weight of raw materials can be obtained; when the reported carbon emissions are not equal to the second carbon emissions, abnormal reporting information is generated and displayed. Among them, the reported carbon emissions are the greenhouse gas (mainly carbon dioxide and perfluorocarbon) emissions generated in the process of producing a preset weight of raw materials reported by the upstream supplier to the electrolytic aluminum plant or relevant regulatory authorities. The abnormal reporting information is used to remind relevant personnel (such as the purchasing department, carbon emission management department or regulatory department of the electrolytic aluminum plant) that the upstream supplier’s reported carbon emissions are abnormal. By comparing the reported carbon emissions with the second carbon emissions, it is possible to promptly discover inaccurate carbon emissions reported by upstream suppliers, and then determine whether the upstream suppliers have underreported, misreported or concealed information; if the relevant personnel are the purchasing department of the electrolytic aluminum plant, the electrolytic aluminum plant can take countermeasures in advance, such as adjusting procurement strategies and finding alternative suppliers, so as to reduce the potential risks caused by carbon emissions problems of upstream suppliers; if the relevant personnel are the carbon emission management department or the regulatory department, the reported carbon emissions of upstream suppliers can be effectively supervised to prevent upstream suppliers from evading carbon emission quota restrictions through false reporting.

[0099] S270: Determine a second unit carbon emission amount according to the preset weight and the second carbon emission amount.

[0100] Specifically, since an upstream supplier only provides one kind of raw material to the electrolytic aluminum plant, after obtaining the second carbon emissions corresponding to each upstream supplier, for the current upstream supplier among multiple upstream suppliers, the preset weight of the raw material corresponding to the current upstream supplier can be obtained, and the ratio of the second carbon emissions corresponding to the current upstream supplier to the preset weight of the raw material corresponding to the current upstream supplier can be calculated to obtain the unit carbon emissions corresponding to the current upstream supplier, thereby obtaining the unit carbon emissions corresponding to each upstream supplier among multiple upstream suppliers, and then the sum of the unit carbon emissions of multiple upstream suppliers is calculated to obtain the second unit carbon emissions.

[0101] Optionally, the unit carbon emissions generated by each of the multiple upstream suppliers in different historical periods can be obtained separately, and these unit carbon emissions can be organized into a supplier data set, and then the average and standard deviation of the multiple unit carbon emissions in the supplier data set are calculated, and the supplier screening interval is determined according to the average and standard deviation, and then the upstream suppliers are screened based on the supplier screening interval, that is, when the unit carbon emissions of the upstream supplier exceed the upper limit of the supplier screening interval, it indicates that the upstream supplier is a high-carbon emission supplier. At this time, the upstream supplier can be replaced, and raw materials are not purchased from the upstream supplier, which can reduce the total unit carbon emissions of the electrolytic aluminum plant and save the carbon emission costs of the electrolytic aluminum plant; when the reported carbon emissions of the upstream supplier are lower than the lower limit of the supplier screening interval, it indicates that the upstream supplier may have underreporting, misreporting or concealment, and at this time, the upstream supplier can be replaced, and raw materials are not purchased from the upstream supplier, which can reduce the potential risks caused by the carbon emission problems of the upstream supplier.

[0102] S280. Determine the sum of the target unit carbon emissions and the second unit carbon emissions as the total unit carbon emissions of the electrolytic aluminum plant within the target time interval.

[0103] The technical solution of the embodiment of the present application can obtain the first carbon emissions and electrolytic aluminum production of the electrolytic aluminum plant in a historical time period, and then convert the perfluorocarbon emissions into carbon dioxide emissions to obtain the converted carbon emissions, and determine the first unit carbon emissions based on the converted carbon emissions, carbon dioxide emissions and electrolytic aluminum production. The perfluorocarbon emissions of the electrolytic aluminum plant in the electrolytic aluminum production process can be considered, which effectively avoids the situation in the prior art that only carbon dioxide emissions are considered, while ignoring the perfluorocarbon emissions caused by the anode / cathode effect, etc., thereby improving the accuracy and efficiency of determining the first unit carbon emissions, and providing an accurate data basis for the subsequent prediction of the target unit carbon emissions, thereby improving the prediction accuracy; then, the first unit carbon emissions are input into a pre-trained carbon emissions prediction model to obtain the target unit carbon emissions of the electrolytic aluminum plant in the target time period, and then the input amount of the emission source of the upstream supplier when producing a preset weight of raw materials is obtained, and the emissions are determined. The carbon dioxide emission factor and perfluorocarbon emission factor of the source are taken into account, and the second carbon emissions are determined according to the input, carbon dioxide emission factor and perfluorocarbon emission factor. The second carbon emissions can be determined according to the original consumption data (i.e., input) and emission factors of the upstream supplier, and the perfluorocarbon emissions and carbon dioxide emissions of the upstream supplier when producing raw materials are comprehensively considered, thereby improving the accuracy and efficiency of determining the second carbon emissions, and providing an accurate data basis for the subsequent determination of the second unit carbon emissions; then the second unit carbon emissions are determined according to the preset weight and the second carbon emissions, and the sum of the target unit carbon emissions and the second unit carbon emissions is determined as the total unit carbon emissions of the electrolytic aluminum plant within the target time period, which takes into account both the carbon emissions in the electrolytic aluminum plant's own production process and the carbon emissions in the upstream suppliers' production of raw materials, thereby helping the electrolytic aluminum plant to accurately and quickly complete the product carbon footprint declaration report, so that an effective emission reduction strategy can be formulated for the electrolytic aluminum plant in advance.

[0104] Figure 3 This is a schematic diagram of the structure of the carbon emission prediction device of the electrolytic aluminum plant provided in the embodiment of the present application, referring to Figure 3 , the carbon emission prediction device of the electrolytic aluminum plant may include:

[0105] A first acquisition module 310 is used to acquire a first carbon emission and an electrolytic aluminum output of the electrolytic aluminum plant in a historical time interval, and determine a first unit carbon emission according to the first carbon emission and the electrolytic aluminum output, where the first unit carbon emission is the carbon emission when the electrolytic aluminum plant produces a unit weight of electrolytic aluminum in the historical time interval;

[0106] The prediction module 320 is used to input the first unit carbon emission into a pre-trained carbon emission prediction model to obtain a target unit carbon emission of the electrolytic aluminum plant in a target time interval, where the target time interval is the same period of the historical time interval in the next cycle;

[0107] The second acquisition module 330 is used to obtain the second carbon emission amount when the upstream supplier produces a preset weight of raw materials, and determine the second unit carbon emission amount according to the preset weight and the second carbon emission amount. The preset weight of raw materials is consumed by the electrolytic aluminum plant within the target time interval and electrolytic aluminum is produced. The second unit carbon emission amount is the carbon emission amount when the upstream supplier produces a unit weight of raw materials;

[0108] The determination module 340 is used to determine the sum of the target unit carbon emissions and the second unit carbon emissions as the total unit carbon emissions of the electrolytic aluminum plant within the target time interval.

[0109] In one embodiment, the first carbon emissions include carbon dioxide emissions and perfluorocarbon emissions. The first acquisition module 310 determines the first unit carbon emissions based on the first carbon emissions and the electrolytic aluminum output, including: converting the perfluorocarbon emissions into carbon dioxide emissions to obtain converted carbon emissions; determining the first unit carbon emissions based on the converted carbon emissions, carbon dioxide emissions and electrolytic aluminum output.

[0110] In one embodiment, the first acquisition module 310 converts perfluorocarbon emissions into carbon dioxide emissions to obtain converted carbon emissions, including: obtaining the global warming potential value of perfluorocarbons; based on the global warming potential value, converting perfluorocarbon emissions into carbon dioxide emissions to obtain converted carbon emissions.

[0111] In one embodiment, the second acquisition module 330 acquires the second carbon emissions when the upstream supplier produces a preset weight of raw materials, including: acquiring the input amount of the emission source when the upstream supplier produces the preset weight of raw materials, and determining the carbon dioxide emission factor and perfluorocarbon emission factor of the emission source; determining the second carbon emissions based on the input amount, the carbon dioxide emission factor and the perfluorocarbon emission factor.

[0112] In one embodiment, the carbon emissions prediction device of the electrolytic aluminum plant also includes an abnormal prompt module, which is specifically used to: after determining the second carbon emissions based on the input amount, carbon dioxide emission factor and perfluorocarbon emission factor, obtain the declared carbon emissions of the upstream supplier when producing a preset weight of raw materials; when the declared carbon emissions are not equal to the second carbon emissions, generate declared abnormality information and display the declared abnormality information.

[0113] In one embodiment, the training process of the carbon emission prediction model in the prediction module 320 is as follows: obtain a sample data set of the electrolytic aluminum plant, the sample data set including multiple historical unit carbon emissions; filter out abnormal data in the sample data set to obtain a target sample data set; obtain the historical unit carbon emissions within a first preset time interval from the target sample data set to obtain the sample unit carbon emissions, and obtain the historical unit carbon emissions within a second preset time interval from the target sample data set to obtain a unit carbon emissions label corresponding to the sample unit carbon emissions, the second preset time interval being the same period of the first preset time interval in the next cycle; determine a training data set based on the sample unit carbon emissions and the unit carbon emissions label corresponding to the sample unit carbon emissions; input the sample unit carbon emissions in the training data set into the initial carbon emissions prediction model, use the unit carbon emissions label corresponding to the sample unit carbon emissions to guide the training output of the initial carbon emissions prediction model, train the initial carbon emissions prediction model to obtain a carbon emissions prediction model.

[0114] In one embodiment, the prediction module 320 filters out abnormal data in the sample data set to obtain a target sample data set, including: determining a screening interval of the sample data set, and filtering out historical unit carbon emissions that are not within the screening interval from the sample data set to obtain an intermediate sample data set; obtaining the carbon emission baseline value of the electrolytic aluminum plant, and filtering out historical unit carbon emissions that are not within a preset normal interval of the carbon emission baseline value from the intermediate sample data set to obtain a target sample data set.

[0115] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example for illustration. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. The specific working process of the functional modules described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0116] The carbon emission prediction device for an aluminum electrolytic plant provided in this embodiment can be applied to the carbon emission prediction method for an aluminum electrolytic plant provided in any of the above embodiments, and has corresponding functions and beneficial effects.

[0117] Figure 4 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. Figure 4 A block diagram of an exemplary electronic device 11 suitable for implementing the embodiments of the present application is shown. Figure 4 The electronic device 11 shown is only an example and should not bring any limitation to the function and scope of use of the present embodiment.

[0118] like Figure 4As shown, the electronic device 11 is in the form of a general purpose computing electronic device. The components of the electronic device 11 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 connecting different system components (including the system memory 28 and the processing unit 16).

[0119] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0120] The electronic device 11 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the electronic device 11, including volatile and non-volatile media, removable and non-removable media.

[0121] The system memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The electronic device 11 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Figure 4 not shown, usually called a "hard drive"). Although Figure 4 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical medium) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The system memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present application.

[0122] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. Program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0123] The electronic device 11 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 11, and / or may communicate with any device that enables the electronic device 11 to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed through an input / output (I / O) interface 22. Furthermore, the electronic device 11 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 20.

[0124] like Figure 4 As shown, the network adapter 20 communicates with other modules of the electronic device 11 via the bus 18. It should be understood that although Figure 4 Not shown, other hardware and / or software modules may be used in conjunction with the electronic device 11, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0125] The processing unit 16 executes various functional applications and page displays by running programs stored in the system memory 28, such as implementing a carbon emission prediction method for an electrolytic aluminum plant provided in any embodiment of the present application.

[0126] An embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, it implements, for example, a method for predicting carbon emissions of an electrolytic aluminum plant provided in any embodiment of the present application.

[0127] The computer storage medium of this embodiment can adopt any combination of one or more computer-readable media. Computer-readable media can be computer-readable signal media or computer-readable storage media. Computer-readable storage media can be, for example, but not limited to: electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or devices, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: electrical connections with one or more wires, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In this document, computer-readable storage media can be any tangible medium containing or storing programs, which can be used by instruction execution systems, devices or devices or used in combination with them.

[0128] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0129] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0130] Computer program code for performing the operation of the present application can be written in one or more programming languages ​​or combinations thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer, partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., using an Internet service provider to connect through the Internet).

[0131] It should be understood by those skilled in the art that the above modules or steps of the present application can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, optionally, they can be implemented by a program code executable by a computer device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present application is not limited to any specific combination of hardware and software.

[0132] In addition, the acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws and regulations.

[0133] Note that the above are only preferred embodiments of the present application and the technical principles used. Those skilled in the art will understand that the present application is not limited to the specific embodiments herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present application. Therefore, although the present application is described in more detail through the above embodiments, the present application is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the inventive concept of the present application, and the scope of the present application is determined by the scope of the appended claims.

Claims

1. A method for predicting carbon emissions from an aluminum smelter, characterized in that: The method comprises: Obtaining a first carbon emission and an electrolytic aluminum output of an electrolytic aluminum plant in a historical time interval, and determining a first unit carbon emission according to the first carbon emission and the electrolytic aluminum output, wherein the first unit carbon emission is the carbon emission when the electrolytic aluminum plant produces a unit weight of electrolytic aluminum in the historical time interval; Inputting the first unit carbon emission into a pre-trained carbon emission prediction model to obtain the target unit carbon emission of the electrolytic aluminum plant in a target time interval, where the target time interval is the same period of the historical time interval in the next cycle; Obtaining a second carbon emission amount when an upstream supplier produces a preset weight of raw materials, and determining a second unit carbon emission amount based on the preset weight and the second carbon emission amount, wherein the preset weight of raw materials is consumed by the electrolytic aluminum plant within the target time interval and electrolytic aluminum is produced, and the second unit carbon emission amount is the carbon emission amount when the upstream supplier produces a unit weight of raw materials; The sum of the target unit carbon emissions and the second unit carbon emissions is determined as the total unit carbon emissions of the electrolytic aluminum plant within the target time interval.

2. The method for predicting carbon emissions of an aluminum smelter according to claim 1, characterized in that: The first carbon emission includes carbon dioxide emission and perfluorocarbon emission, and determining the first unit carbon emission according to the first carbon emission and the electrolytic aluminum output includes: Converting the perfluorocarbon emissions into carbon dioxide emissions to obtain converted carbon emissions; The first unit carbon emissions are determined based on the converted carbon emissions, the carbon dioxide emissions and the electrolytic aluminum output.

3. The method for predicting carbon emissions of an aluminum smelter according to claim 2, characterized in that: The converting the perfluorocarbon emissions into carbon dioxide emissions to obtain converted carbon emissions includes: Obtaining the global warming potential of perfluorocarbons; Based on the global warming potential value, the perfluorocarbon emissions are converted into carbon dioxide emissions to obtain the converted carbon emissions.

4. The method for predicting carbon emissions of an aluminum smelter according to claim 1, characterized in that: The obtaining of the second carbon emissions of the upstream supplier when producing the preset weight of raw materials includes: Obtaining the input amount of the emission source of the upstream supplier when producing a preset weight of raw materials, and determining the carbon dioxide emission factor and perfluorocarbon emission factor of the emission source; The second carbon emission is determined according to the input amount, the carbon dioxide emission factor and the perfluorocarbon emission factor.

5. The method for predicting carbon emissions of an aluminum smelter according to claim 4, characterized in that: After determining the second carbon emission amount according to the input amount, the carbon dioxide emission factor and the perfluorocarbon emission factor, the method further includes: Obtain the declared carbon emissions of the upstream supplier when producing a preset weight of raw materials; When the reported carbon emissions are not equal to the second carbon emissions, abnormal reporting information is generated and displayed.

6. The method for predicting carbon emissions of an aluminum smelter according to claim 1, characterized in that: The training process of the carbon emission prediction model is as follows: Obtaining a sample data set of the aluminum smelter, wherein the sample data set includes a plurality of historical unit carbon emissions; Screening out abnormal data in the sample data set to obtain a target sample data set; Acquire the historical unit carbon emissions within a first preset time interval from the target sample data set to obtain the sample unit carbon emissions, and acquire the historical unit carbon emissions within a second preset time interval from the target sample data set to obtain the unit carbon emissions label corresponding to the sample unit carbon emissions, wherein the second preset time interval is the same period of the first preset time interval in the next cycle; Determine a training data set based on the sample unit carbon emissions and the unit carbon emissions labels corresponding to the sample unit carbon emissions; The sample unit carbon emissions in the training data set are input into the initial carbon emissions prediction model, the unit carbon emissions labels corresponding to the sample unit carbon emissions are used to guide the training output of the initial carbon emissions prediction model, the initial carbon emissions prediction model is trained, and the carbon emissions prediction model is obtained.

7. The method for predicting carbon emissions of an aluminum smelter according to claim 6, characterized in that: The step of filtering out abnormal data in the sample data set to obtain a target sample data set includes: Determining a screening interval of the sample data set, and filtering out historical unit carbon emissions that are not within the screening interval from the sample data set to obtain an intermediate sample data set; The carbon emission baseline value of the aluminum smelter is obtained, and the historical unit carbon emissions that are not within a preset normal range of the carbon emission baseline value are screened out from the intermediate sample data set to obtain the target sample data set.

8. A device for predicting carbon emissions from an aluminum electrolytic plant, characterized in that: The device comprises: A first acquisition module is used to acquire a first carbon emission and an electrolytic aluminum output of an electrolytic aluminum plant in a historical time interval, and determine a first unit carbon emission according to the first carbon emission and the electrolytic aluminum output, wherein the first unit carbon emission is the carbon emission when the electrolytic aluminum plant produces a unit weight of electrolytic aluminum in the historical time interval; A prediction module, used for inputting the first unit carbon emission into a pre-trained carbon emission prediction model to obtain a target unit carbon emission of the electrolytic aluminum plant within a target time interval, wherein the target time interval is a corresponding period of the historical time interval in a next cycle; a second acquisition module, configured to acquire a second carbon emission amount when an upstream supplier produces a preset weight of raw materials, and determine a second unit carbon emission amount according to the preset weight and the second carbon emission amount, wherein the preset weight of raw materials is consumed by the electrolytic aluminum plant within the target time interval and electrolytic aluminum is produced, and the second unit carbon emission amount is the carbon emission amount when the upstream supplier produces a unit weight of raw materials; A determination module is used to determine the sum of the target unit carbon emissions and the second unit carbon emissions as the total unit carbon emissions of the electrolytic aluminum plant within the target time interval.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the carbon emissions prediction method for an aluminum electrolytic plant as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, it implements the carbon emission prediction method for an electrolytic aluminum plant as described in any one of claims 1 to 7.

Images