Zero-carbon factory management method based on big data and medium

Abstract

The invention provides a zero-carbon factory management method based on big data and a medium, and relates to the technical field of zero-carbon factory management, and the method comprises the steps: building and updating a zero-carbon factory environment model through environment data; training a zero-carbon factory environment model: inputting the energy input quantity and the raw material input quantity into corresponding nodes of a process topological structure, and determining a predicted product quantity through a yield function; correcting the yield function through the product output quantity and the predicted product quantity to obtain a yield correction coefficient; correcting the predicted product amount of the node through the yield correction coefficient to obtain a corrected product amount; determining a raw material input quantity and an energy input quantity; obtaining a trained zero-carbon factory environment model until all nodes of the process topological structure are corrected; and determining an energy scheduling strategy of each process through the trained zero-carbon factory environment model. The energy input of each working procedure during multi-working-procedure combined operation is predicted in advance, so that preparation energy supply is realized, and the occurrence probability of energy waste and energy shortage is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of zero-carbon factory management, and in particular to a zero-carbon factory management method and medium based on big data. Background Art

[0002] Under the traditional factory management model, energy scheduling in multi-process joint operations mainly relies on pre-set flowcharts and operating procedures. Traditional energy scheduling usually adopts a fixed, static solution based on historical experience and best practices to optimize a single workshop or specific process; static solutions cannot respond to changes in the production process in real time (such as equipment failures, fluctuations in raw material input, etc.). When a process changes during the production process, if energy is supplied to the process according to the static solution, if the raw material input increases and the energy supply remains unchanged, it will lead to energy shortages, thereby affecting productivity; if the raw material input decreases and the energy supply remains unchanged, it will cause energy waste.

[0003] The joint operation of multiple processes requires the effective connection of materials and energy, but in the traditional model, this connection mainly relies on pre-set flow charts and operating procedures, and lacks an automated scheduling system. When a problem occurs in a certain process, it is easy to form a bottleneck, affecting the smooth operation of the entire production chain and increasing time and resource costs. Summary of the invention

[0004] The purpose of the present invention is to provide a zero-carbon factory management method and medium based on big data. The technical problem to be solved is how to predict in advance the energy input of each process when multiple processes are operated together, realize the preparatory energy supply, and reduce the probability of energy waste and energy shortage.

[0005] The present invention is achieved through the following technical solutions:

[0006] A first aspect provides a zero-carbon factory management method based on big data, comprising the following steps:

[0007] S100, obtaining environmental data and historical data of the zero-carbon factory, and preprocessing the environmental data and historical data;

[0008] S200, building a zero-carbon factory environmental model through the above environmental data, and updating the zero-carbon factory environmental model according to the environmental data at each time point; wherein the above zero-carbon factory environmental model includes a process topology structure; each node in the above process topology structure is configured with a yield function;

[0009] The steps of training the above zero-carbon factory environment model include:

[0010] S300, extracting the energy input, raw material input and product output of a process from the above historical data;

[0011] S400, inputting the energy input amount and the raw material input amount into the corresponding node of the process topology structure, and determining the expected product amount through the yield function of the node;

[0012] The yield function of the node is corrected by the above product output and the expected product amount to obtain the yield correction coefficient;

[0013] S500, correcting the estimated product amount of the node by the yield correction coefficient to obtain a corrected product amount; wherein the product of the node is used as a raw material for the next node;

[0014] S600, configuring the ingredient list, and determining the auxiliary material input amount of the next node through the ingredient list and the corrected product amount;

[0015] Determine the raw material input amount of the next node through the above-mentioned correction product amount and auxiliary material input amount;

[0016] Configure an energy scheduling table, and determine the energy input amount of the next node through the above energy scheduling table and the raw material input amount of the next node;

[0017] S700, return to S400 and continue to execute until all nodes of the process topology structure are corrected, and the zero-carbon factory environment model after training is obtained;

[0018] S800. Input energy data and raw material data into the process topology structure after training to determine the energy scheduling strategy for each process of the zero-carbon factory; wherein the energy data includes energy input, and the raw material data includes raw material input.

[0019] The yield correction coefficient is trained based on historical data to correct the yield function, so that the energy input required for each process can be predicted before actual production, and the appropriate amount of energy can be prepared to reduce energy waste caused by excessive preparation, while also reducing the risk of energy shortage caused by insufficient estimation; since the production of a product requires multiple processes, there is a time difference between processes, and they are usually not carried out at the same time; in order to ensure the energy supply of each process when producing the product, the energy used to produce the product must be prepared in advance, and the pre-prepared energy is called when the process produces the product, so as to realize the energy supply operation. In the process from S400 to S700, by continuously correcting the yield function, adapting to production changes under different conditions, the energy demand is dynamically adjusted to ensure that even in the face of uncertain factors (such as raw material fluctuations), a better energy efficiency can be maintained. The energy scheduling strategy for determining each process of the zero-carbon factory mentioned in step S800 is based on a comprehensive consideration of the entire process topology, which means that it not only focuses on the optimal state of a single process, but also takes into account the mutual influence between each process to achieve a global optimal solution. Therefore, when performing multi-process joint operations, this holistic perspective can help better coordinate the energy distribution among different processes and improve the operating efficiency of the entire system.

[0020] Furthermore, after S800, a carbon capture operation needs to be performed, and the steps for determining the carbon capture time are as follows:

[0021] S910, determining the total carbon absorption amount of the zero-carbon factory environmental model in time period t through the above environmental data;

[0022] S920, determining the total carbon emissions of the zero-carbon factory environment model in time period t by inputting the energy data and raw material data of the modified process topology structure;

[0023] S930, determining the carbon capture time of the zero-carbon factory environment model in time period t through the above-mentioned total carbon absorption and total carbon emission;

[0024] According to the above carbon capture time, a control signal is generated to control the energy input of the carbon capture equipment.

[0025] Time period t refers to the time from the start of the first process to the end of the last process of a product; adding carbon capture operations to the zero-carbon factory management method can further improve the factory's environmental friendliness and carbon neutrality. First, evaluate the amount of carbon dioxide that can be absorbed by natural or technical carbon sinks (such as greening, algae cultivation, etc.) in the factory within a specific time period; second, predict the amount of carbon dioxide emissions generated during the production process; third, in order to ensure the carbon balance of the zero-carbon factory and reduce energy waste, it is necessary to plan the length of time for carbon capture operations so that carbon emissions and carbon absorption offset each other; finally, generate control signals to control the energy input of carbon capture equipment, optimize the energy efficiency in the carbon capture process, and avoid waste.

[0026] Through the above methods, zero-carbon factories can more flexibly respond to possible fluctuations in carbon emissions during the production process and take timely measures to compensate, thereby better achieving the goal of carbon neutrality. In addition, intelligent regulation of the operation of carbon capture equipment can also reduce unnecessary energy consumption and enhance the overall economic benefits and environmental performance of the factory.

[0027] Furthermore, the specific steps of S910 include:

[0028] S911, obtaining environmental data for building the above-mentioned zero-carbon factory environmental model within a time period t, and extracting the vegetation type at each time point, the quantity of each vegetation type, and the carbon absorption and carbon emission of each vegetation type per unit time from the environmental data;

[0029] S912. Determine the total carbon absorption of the zero-carbon factory environment model in time period t using the following formula:

[0030] ,

[0031] in, represents the total carbon absorption of the zero-carbon factory environment model in time period t; Indicates the number of vegetation types; Indicates The amount of carbon absorbed by vegetation types per unit time; Indicates Carbon emissions per unit time by vegetation type; Indicates the start time of period t; represents the end time of period t; Represents the total number of vegetation types.

[0032] Collect necessary ecological data to quantify the impact of vegetation on the carbon cycle. By calculating the net amount of carbon absorbed by each vegetation type per unit time, the net carbon absorbed by all vegetation types is accumulated, and combined with the absorption time, the total carbon absorption of the entire zero-carbon factory environmental model within a specified period of time is obtained. This method not only helps to understand how the internal ecosystem of the factory participates in the carbon cycle, but also can be used as part of optimizing factory design, such as adding more efficient carbon-absorbing vegetation types, or adjusting the existing vegetation layout to improve the overall carbon absorption efficiency. In addition, the calculation of carbon absorption is an important basis for evaluating and managing the carbon footprint of the factory, and supports the formulation of more scientific and reasonable carbon capture and emission reduction strategies.

[0033] Furthermore, the specific steps of S920 include:

[0034] S921. Obtain energy data and raw material data of the input process topology structure within time period t; wherein the energy data also includes energy type and carbon emission coefficient of each energy type, and the raw material data also includes raw material type and carbon emission coefficient of each raw material type;

[0035] S922. Determine the total carbon emissions of the zero-carbon factory environment model in time period t using the following formula:

[0036] ,

[0037] in, represents the total carbon emissions of the zero-carbon factory environment model in time period t; Indicates Node Energy input by energy type; Indicates Carbon emission coefficient of each energy type; represents the conversion factor between carbon and carbon dioxide; Indicates Node Raw material input quantity of each raw material type; Indicates Carbon emission coefficient of each raw material type; The total number of nodes representing the process topology; Indicates the total number of energy types; Indicates the total number of raw material types; Indicates the carbon capture equipment Energy input by energy type; It represents the carbon capture duration in time period t, that is, the startup duration of the carbon capture equipment.

[0038] Collect necessary production activity data to quantify carbon emissions. Considering that the carbon capture process itself consumes energy, this additional energy demand also needs to be included in the total carbon emissions. A comprehensive assessment of carbon emissions within a zero-carbon factory not only covers the energy and raw material consumption in the main production processes, but also takes into account the carbon footprint of the carbon capture operation itself. By quantifying these factors, the factory can formulate emission reduction strategies more scientifically, optimize resource allocation, and ensure that the predetermined carbon neutrality goals are achieved or even exceeded.

[0039] Furthermore, the following formula is used to determine the carbon capture time of the zero-carbon plant environmental model in time period t:

[0040] ,

[0041] in, It represents the amount of carbon captured per unit time; Represents the carbon capture duration in time period t.

[0042] The length of time the carbon capture equipment needs to work to offset net carbon emissions is calculated. If the carbon capture time is negative or zero, it means that the plant's natural carbon sinks (such as vegetation) are sufficient to compensate for its carbon emissions and no additional carbon capture activities are required; conversely, if the carbon capture time is positive, it indicates that the carbon capture equipment needs to be activated, and the value indicates how long it needs to run. This method allows the plant management system to dynamically adjust the carbon capture strategy to ensure a balance between carbon emissions and carbon absorption, thereby achieving carbon neutrality goals. By calculating the carbon capture time, the plant can not only effectively reduce the concentration of carbon dioxide in the atmosphere when necessary, but also optimize energy use and reduce operating costs.

[0043] Furthermore, S400 further includes the following steps:

[0044] Each node in the above process topology is configured with a material loss function;

[0045] Determine the estimated intermediate amount through the above material loss function, raw material input amount and estimated product amount;

[0046] The intermediate output of the corresponding process is extracted from the above historical data; the material loss function of the node is corrected through the above intermediate output and the expected intermediate quantity to obtain the material loss correction coefficient.

[0047] In addition to the yield function, each node is also configured with a material loss function. The material loss function is used to describe the inevitable material losses (such as evaporation, leakage, side reactions, etc.) in the production process, which will affect the final product quantity. Using the raw material input and the expected product quantity as input parameters, combined with the node's material loss function, the expected intermediate quantity is calculated. This step aims to consider the impact of material loss on the production process and ensure that the prediction is closer to the actual production situation. The intermediate output of the corresponding process is extracted from the historical data, which is the data recorded in the actual production process in the past and used as a comparison benchmark; the actual intermediate output is compared with the expected intermediate quantity. If there is a difference between the two, the material loss function is adjusted to better reflect the actual situation. According to the obtained material loss correction coefficient, the material loss function of the node is updated so that more accurate parameters can be used in subsequent simulations and predictions. After considering material loss, the model can simulate the production process more realistically and improve the prediction accuracy of the material quantity at each stage. Since the energy input is related to the product output, when the prediction accuracy of the product output is improved, the prediction accuracy of the energy input is also improved accordingly.

[0048] Furthermore, each node in the above process topology is configured with a recycling times threshold;

[0049] Recycling the intermediates of each node, and counting the number of times the intermediates are recycled;

[0050] The intermediate whose recycling times are less than the recycling threshold is used as the raw material of the node that recycles the intermediate;

[0051] The intermediates whose recycling times are equal to or greater than the recycling threshold are regarded as waste.

[0052] Introducing an intermediate recycling mechanism into the process topology of a zero-carbon factory and configuring a recycling threshold for each node can further optimize resource utilization efficiency and reduce waste generation. Limit the number of times intermediates are recycled to ensure the quality of the materials; track the number of times each batch of intermediates is recycled to determine their subsequent treatment. If the number of recycling times is less than the recycling threshold, the batch of intermediates is regarded as qualified reusable raw materials and can be re-entered into the corresponding production node for continued use, which helps to save raw materials and reduce production costs, while reducing the demand for new materials and reducing raw material consumption; if the number of recycling times is equal to or greater than the recycling threshold, it is considered that the batch of intermediates has reached the maximum allowable number of recycling times and should be treated as waste.

[0053] A second aspect provides a computer-readable storage medium having computer program instructions stored thereon, wherein the computer program instructions implement the above-mentioned management method when executed by a processor.

[0054] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0055] The yield correction coefficient is trained based on historical data to correct the yield function, so that the energy input required for each process can be predicted before actual production, and the appropriate amount of energy can be prepared to reduce energy waste caused by excessive preparation, while also reducing the risk of energy shortage caused by insufficient estimation; since the production of a product requires multiple processes, there is a time difference between processes, and they are usually not carried out at the same time; in order to ensure the energy supply of each process when producing the product, the energy used to produce the product must be prepared in advance, and the pre-prepared energy is called when the process produces the product, so as to realize the energy supply operation. In the process from S400 to S700, by continuously correcting the yield function, adapting to production changes under different conditions, the energy demand is dynamically adjusted to ensure that even in the face of uncertain factors (such as raw material fluctuations), a better energy efficiency can be maintained. The energy scheduling strategy for determining each process of the zero-carbon factory mentioned in step S800 is based on a comprehensive consideration of the entire process topology, which means that it not only focuses on the optimal state of a single process, but also takes into account the mutual influence between each process to achieve a global optimal solution. Therefore, when performing multi-process joint operations, this holistic perspective can help better coordinate the energy distribution among different processes and improve the operating efficiency of the entire system. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and should not be regarded as limiting the scope. For those of ordinary skill in the art, other relevant drawings can be obtained based on these drawings without creative work. In the drawings:

[0057] Figure 1 As the main flow chart;

[0058] Figure 2 This is a schematic diagram of the process topology structure. DETAILED DESCRIPTION

[0059] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with embodiments and drawings. The exemplary embodiments of the present invention and their description are only used to explain the present invention and are not intended to limit the present invention.

[0060] First embodiment:

[0061] Combination Figure 1 and Figure 2 , a zero-carbon factory management method based on big data, comprising the following steps:

[0062] S100, obtaining environmental data and historical data of the zero-carbon factory, and preprocessing the environmental data and historical data;

[0063] S200, building a zero-carbon factory environmental model through the above environmental data, and updating the zero-carbon factory environmental model according to the environmental data at each time point; wherein the above zero-carbon factory environmental model includes a process topology structure; each node in the above process topology structure is configured with a yield function;

[0064] The steps of training the above zero-carbon factory environment model include:

[0065] S300, extracting the energy input, raw material input and product output of a process from the above historical data;

[0066] S400, input the above energy input and raw material input into the corresponding node of the process topology structure, and determine the expected product amount through the yield function of the node, the formula is: ,in, represents the expected product amount, represents the yield function; Indicates the energy input of various energy sources; Indicates the raw material input amount of various raw materials;

[0067] By using the above product output and expected product amount, the yield function of the node is corrected to obtain the yield correction coefficient, which is: ,in, Indicates the output of the product of the node; Indicates the yield correction coefficient of the node;

[0068] S500, correct the expected product amount of the node by the above yield correction coefficient to obtain the corrected product amount, the formula is: ,in, Indicates the amount of the modified product of the node; the product of this node is used as the raw material of the next node;

[0069] S600, configuring a batching table (the batching table includes data on the ratio of the product to the auxiliary materials), and determining the auxiliary material input amount of the next node through the batching table and the corrected product amount;

[0070] By using the above-mentioned corrected product amount and auxiliary material input amount, the raw material input amount of the next node is determined. The formula is: ,in, represents the raw material input amount of the next node, Indicates the auxiliary material input amount of the next node;

[0071] Configure an energy scheduling table (the energy scheduling table includes the relationship between the product and raw materials produced by the process when one or more energy sources are supplied to the process), and determine the energy input amount of the next node through the above energy scheduling table and the raw material input amount of the next node (take the energy type and energy input amount with the highest yield in the energy scheduling table);

[0072] S700, return to S400 and continue to execute until all nodes of the process topology structure are corrected, and the zero-carbon factory environment model after training is obtained;

[0073] S800. Input energy data and raw material data into the process topology structure after training to determine the energy scheduling strategy for each process of the zero-carbon factory; wherein the energy data includes energy input, and the raw material data includes raw material input.

[0074] The above-mentioned zero-carbon factory management method based on big data simulates the relationship between the processes within the zero-carbon factory by constructing and training the process topology structure, and uses the yield function to predict and optimize the input and output of energy and materials. It has the following beneficial effects on predicting the energy input of each process when multiple processes are operated in conjunction:

[0075] The yield correction coefficient is trained based on historical data to correct the yield function, so that the energy input required for each process can be predicted before actual production, and the appropriate amount of energy can be prepared to reduce energy waste caused by excessive preparation, while also reducing the risk of energy shortage caused by insufficient estimation; since the production of a product requires multiple processes, there is a time difference between processes, and they are usually not carried out at the same time; in order to ensure the energy supply of each process when producing the product, the energy used to produce the product must be prepared in advance, and the pre-prepared energy is called when the process produces the product, so as to realize the energy supply operation. In the process from S400 to S700, by continuously correcting the yield function, adapting to production changes under different conditions, the energy demand is dynamically adjusted to ensure that even in the face of uncertain factors (such as raw material fluctuations), a better energy efficiency can be maintained. The energy scheduling strategy for determining each process of the zero-carbon factory mentioned in step S800 is based on a comprehensive consideration of the entire process topology, which means that it not only focuses on the optimal state of a single process, but also takes into account the mutual influence between each process to achieve a global optimal solution. Therefore, when performing multi-process joint operations, this holistic perspective can help better coordinate the energy distribution among different processes and improve the operating efficiency of the entire system.

[0076] By predicting and planning energy input in advance, we can avoid the cost increase caused by temporary increase in energy purchases or the shutdown losses caused by energy supply interruptions, aiming to improve energy utilization while reducing unnecessary energy consumption.

[0077] Second embodiment:

[0078] On the basis of the first embodiment, after S800, a carbon capture operation needs to be performed, and the steps of determining the carbon capture time are as follows:

[0079] S910, determining the total carbon absorption amount of the zero-carbon factory environmental model in time period t through the above environmental data;

[0080] S920, determining the total carbon emissions of the zero-carbon factory environment model in time period t by inputting the energy data and raw material data of the modified process topology structure;

[0081] S930, determining the carbon capture time of the zero-carbon factory environment model in time period t through the above-mentioned total carbon absorption and total carbon emission;

[0082] According to the above carbon capture time, a control signal is generated to control the energy input of the carbon capture equipment.

[0083] Time period t refers to the time from the start of the first process to the end of the last process of a product; adding carbon capture operations to the zero-carbon factory management method can further enhance the factory's environmental friendliness and carbon neutrality capabilities.

[0084] First, assess the amount of carbon dioxide that natural or technological carbon sinks (such as greenery, algae cultivation, etc.) within the factory can absorb in a specific time period;

[0085] Secondly, predict the CO2 emissions generated during the production process;

[0086] Secondly, in order to ensure the carbon balance of the zero-carbon factory and reduce energy waste, it is necessary to plan the duration of the carbon capture operation so that carbon emissions and carbon absorption offset each other. The specific implementation method can be: subtract the total carbon absorption obtained by S910 from the total carbon emissions obtained by S920. If the difference is negative, it means that there is net emission and the carbon capture equipment needs to be started for additional carbon capture; conversely, if the difference is positive, it means that no special carbon capture is required at this stage. The duration of carbon capture can be determined according to the size of net emissions to ensure that the carbon neutrality goal is ultimately achieved.

[0087] Finally, a control signal is generated to control the energy input of the carbon capture equipment, optimize the energy utilization efficiency in the carbon capture process, and avoid waste. The specific implementation method can be: according to the calculated carbon capture time, the system automatically generates a corresponding control signal to adjust the working parameters of the carbon capture equipment (carbon capture can use ultracapacitor voltage swing adsorption technology) to adjust its energy input.

[0088] Through the above methods, zero-carbon factories can more flexibly respond to possible fluctuations in carbon emissions during the production process and take timely measures to compensate, thereby better achieving the goal of carbon neutrality. In addition, intelligent regulation of the operation of carbon capture equipment can also reduce unnecessary energy consumption and enhance the overall economic benefits and environmental performance of the factory.

[0089] Third embodiment:

[0090] Based on the second embodiment, the specific steps of S910 include:

[0091] S911, obtaining environmental data for building the above-mentioned zero-carbon factory environmental model within a time period t, and extracting the vegetation type at each time point, the quantity of each vegetation type, and the carbon absorption and carbon emission of each vegetation type per unit time from the environmental data;

[0092] S912. Determine the total carbon absorption of the zero-carbon factory environment model in time period t using the following formula:

[0093] ,

[0094] in, represents the total carbon absorption of the zero-carbon factory environment model in time period t; Indicates the number of vegetation types; Indicates The amount of carbon absorbed by vegetation types per unit time; Indicates Carbon emissions per unit time by vegetation type; Indicates the start time of period t; represents the end time of period t; Represents the total number of vegetation types.

[0095] Collect necessary ecological data to quantify the impact of vegetation on the carbon cycle. Through the sensor network deployed in the zero-carbon factory (such as ground stations, drones, satellite remote sensing, etc.), a variety of environmental parameters including temperature, humidity, and light intensity can be collected in real time or regularly; from the above environmental data, pay special attention to vegetation types and their distribution. For each vegetation type, record its quantity, type, and carbon absorption (CO2 absorption by photosynthesis) and carbon emission (CO2 release by respiration) per unit time. This information can be obtained through field surveys, historical database queries, etc.

[0096] By calculating the net amount of carbon absorbed by each vegetation type per unit time, accumulating the net carbon absorbed by all vegetation types, and combining the absorption time, the total carbon absorption of the entire zero-carbon factory environmental model within a specified period of time is obtained. This method not only helps to understand how the internal ecosystem of the factory participates in the carbon cycle, but also can be used as part of optimizing factory design, such as adding more efficient carbon-absorbing vegetation types, or adjusting the existing vegetation layout to improve the overall carbon absorption efficiency. In addition, the calculation of carbon absorption is an important basis for evaluating and managing the carbon footprint of the factory, and supports the formulation of more scientific and reasonable carbon capture and emission reduction strategies.

[0097] In a specific embodiment, the specific steps of S920 include:

[0098] S921. Obtain energy data and raw material data of the input process topology structure within time period t; wherein the energy data also includes energy type and carbon emission coefficient of each energy type, and the raw material data also includes raw material type and carbon emission coefficient of each raw material type;

[0099] S922. Determine the total carbon emissions of the zero-carbon factory environment model in time period t using the following formula:

[0100] ,

[0101] in, represents the total carbon emissions of the zero-carbon factory environment model in time period t; Indicates Node Energy input by energy type; Indicates Carbon emission coefficient of each energy type; represents the conversion factor between carbon and carbon dioxide; Indicates Node Raw material input quantity of each raw material type; Indicates Carbon emission coefficient of each raw material type; The total number of nodes representing the process topology; Indicates the total number of energy types; Indicates the total number of raw material types; Indicates the carbon capture equipment Energy input by energy type; It represents the carbon capture duration in time period t, that is, the startup duration of the carbon capture equipment.

[0102] Collect necessary production activity data to quantify carbon emissions. Considering that the carbon capture process itself consumes energy, this additional energy demand also needs to be included in the total carbon emissions. A comprehensive assessment of carbon emissions within a zero-carbon factory not only covers the energy and raw material consumption in the main production processes, but also takes into account the carbon footprint of the carbon capture operation itself. By quantifying these factors, the factory can formulate emission reduction strategies more scientifically, optimize resource allocation, and ensure that the predetermined carbon neutrality goals are achieved or even exceeded.

[0103] The energy type (such as electricity, natural gas, etc.) input to each node and its corresponding carbon emission coefficient can be obtained through real-time collection by the energy monitoring system in the factory, or based on historical records and information provided by suppliers. The material management system or environmental declaration provided by the supplier can be used to obtain the types of raw materials entering the process topology and the carbon emission coefficient of each type of raw material.

[0104] In a specific embodiment, the carbon capture time of the zero-carbon factory environment model in time period t is determined using the following formula:

[0105] ,

[0106] in, It represents the amount of carbon captured per unit time; Represents the carbon capture duration in time period t.

[0107] The length of time the carbon capture equipment needs to work to offset net carbon emissions is calculated. If the carbon capture time is negative or zero, it means that the plant's natural carbon sinks (such as vegetation) are sufficient to compensate for its carbon emissions and no additional carbon capture activities are required; conversely, if the carbon capture time is positive, it indicates that the carbon capture equipment needs to be activated, and the value indicates how long it needs to run. This method allows the plant management system to dynamically adjust the carbon capture strategy to ensure a balance between carbon emissions and carbon absorption, thereby achieving carbon neutrality goals. By calculating the carbon capture time, the plant can not only effectively reduce the concentration of carbon dioxide in the atmosphere when necessary, but also optimize energy use and reduce operating costs.

[0108] An application scenario that can be used for reference is to assume that a winery plans to produce a batch of wine. The same batch means that the raw materials are put into the same process at one time and the product is obtained after going through all the processes. The brewing cycle of this batch of wine is two weeks. It can be assumed that there are no other product manufacturing processes when brewing this batch of wine. During this period, if the vegetation in the vineyards and other green areas of the winery is used, it is calculated that a total of 5 tons of carbon dioxide are absorbed in these two weeks. The energy consumption in the production process (such as heating, cooling, fermentation tank stirring, etc.) and raw material processing lead to the emission of about 8 tons of carbon dioxide. Specifically, the raw materials are put into the first process. At this time, the operation of the first process produces carbon emissions, and at this time, other processes are not started and there is no carbon emission. The first process generates a product. After obtaining the product, the first process stops running and the second process is started. At this time, the operation of the second process produces carbon emissions, and other processes are not started and there is no carbon emission. Therefore, the carbon emissions of each process can be accumulated to obtain the total carbon emissions. In addition, the energy required for the operation of the carbon capture equipment also contributes a certain amount of carbon emissions. According to the above calculation, if the carbon capture equipment captures 0.5 tons of carbon dioxide per day per unit time, it needs to run for 6 days to offset the net emission of 3 tons of carbon dioxide (i.e. 8-5=3 tons).

[0109] Fourth embodiment:

[0110] Based on any of the above embodiments, S400 further includes the following steps:

[0111] Each node in the above process topology is configured with a material loss function ;

[0112] The estimated intermediate amount is determined by the above material loss function, raw material input and expected product amount. The formula is: ,in, Indicates the estimated intermediate volume;

[0113] Extract the intermediate output of the corresponding process from the above historical data; correct the material loss function of the node through the above intermediate output and the expected intermediate quantity to obtain the material loss correction coefficient, which is: ,in, Indicates the intermediate output of the node; Indicates the material loss correction factor of the node;

[0114] The estimated intermediate material quantity of the node is corrected by the above material loss correction coefficient to obtain the corrected intermediate material quantity. The formula is: ,in, Indicates the modified intermediate quantity of this node.

[0115] In addition to the yield function, each node is also configured with a material loss function. The material loss function is used to describe the inevitable material losses (such as evaporation, leakage, side reactions, etc.) in the production process, which will affect the final product quantity. Using the raw material input and the expected product quantity as input parameters, combined with the node's material loss function, the expected intermediate quantity is calculated. This step aims to consider the impact of material loss on the production process and ensure that the prediction is closer to the actual production situation. The intermediate output of the corresponding process is extracted from the historical data, which is the data recorded in the actual production process in the past and used as a comparison benchmark; the actual intermediate output is compared with the expected intermediate quantity. If there is a difference between the two, the material loss function is adjusted to better reflect the actual situation. According to the obtained material loss correction coefficient, the material loss function of the node is updated so that more accurate parameters can be used in subsequent simulations and predictions. After considering material loss, the model can simulate the production process more realistically and improve the prediction accuracy of the material quantity at each stage. Since the energy input is related to the product output, when the prediction accuracy of the product output is improved, the prediction accuracy of the energy input is also improved accordingly.

[0116] Fifth embodiment:

[0117] Based on any of the above embodiments, Figure 2 ,Each node in the above process topology is configured with a recycling times threshold;

[0118] Recycling the intermediates of each node, and counting the number of times the intermediates are recycled;

[0119] The intermediate whose recycling times are less than the recycling threshold is used as the raw material of the node that recycles the intermediate;

[0120] The intermediates whose recycling times are equal to or greater than the recycling threshold are regarded as waste.

[0121] Introducing an intermediate recycling mechanism into the process topology of a zero-carbon factory and configuring a recycling threshold for each node can further optimize resource utilization efficiency and reduce waste generation. Limit the number of times intermediates are recycled to ensure the quality of the materials; track the number of times each batch of intermediates is recycled to determine their subsequent treatment. If the number of recycling times is less than the recycling threshold, the batch of intermediates is regarded as qualified reusable raw materials and can be re-entered into the corresponding production node for continued use, which helps to save raw materials and reduce production costs, while reducing the demand for new materials and reducing raw material consumption; if the number of recycling times is equal to or greater than the recycling threshold, it is considered that the batch of intermediates has reached the maximum allowable number of recycling times and should be treated as waste.

[0122] By setting a reasonable recycling threshold, the value of intermediates is maximized, waste is reduced, and resource utilization is improved; the dependence on fresh raw materials is effectively reduced, procurement costs are saved, and waste disposal costs are also reduced. Product quality problems caused by excessive recycling are reduced.

[0123] Sixth embodiment:

[0124] A computer-readable storage medium stores computer program instructions, which implement the management method when executed by a processor.

[0125] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A zero-carbon factory management method based on big data, characterized in that: The following steps are involved: S100, obtaining environmental data and historical data of the zero-carbon factory, and preprocessing the environmental data and historical data; S200, building a zero-carbon factory environmental model through the environmental data, and updating the zero-carbon factory environmental model according to the environmental data at each time point; wherein the zero-carbon factory environmental model includes a process topology structure; each node in the process topology structure is configured with a yield function; Training the zero-carbon factory environment model comprises: S300, extracting energy input, raw material input and product output of a process from the historical data; S400, inputting the energy input amount and the raw material input amount into a corresponding node of a process topology structure, and determining an expected product amount through a yield function of the node; Correcting the yield function of the node by the product output and the expected product amount to obtain a yield correction coefficient; S500, correcting the expected product amount of the node by the yield correction coefficient to obtain a corrected product amount; wherein the product of the node is used as a raw material for the next node; S600, configuring a batching table, and determining the auxiliary material input amount of the next node through the batching table and the corrected product amount; Determine the raw material input amount of the next node by using the corrected product amount and auxiliary material input amount; configuring an energy scheduling table, and determining the energy input amount of the next node through the energy scheduling table and the raw material input amount of the next node; S700, returning to S400 and continuing to execute until all nodes of the process topology structure are corrected, and the zero-carbon factory environment model after training is obtained; S800. Input energy data and raw material data into the process topology structure after training to determine the energy scheduling strategy for each process of the zero-carbon factory; wherein the energy data includes energy input, and the raw material data includes raw material input.

2. The zero-carbon factory management method according to claim 1, characterized in that: After S800, carbon capture operation needs to be performed. The steps to determine the carbon capture time are as follows: S910, determining the total carbon absorption amount of the zero-carbon factory environmental model in time period t through the environmental data; S920, determining the total carbon emissions of the zero-carbon factory environment model in time period t by inputting the energy data and raw material data of the modified process topology structure; S930, determining the carbon capture time of the zero-carbon factory environment model in time period t according to the total carbon absorption and the total carbon emission; According to the carbon capture time, a control signal is generated to control the energy input of the carbon capture device.

3. The zero-carbon factory management method according to claim 2, characterized in that: The specific steps of S910 include: S911, obtaining environmental data for building the zero-carbon factory environmental model within a time period t, and extracting the vegetation type at each time point, the quantity of each vegetation type, and the carbon absorption and carbon emission of each vegetation type per unit time from the environmental data; S912. Determine the total carbon absorption of the zero-carbon factory environment model in time period t using the following formula: ， in, represents the total carbon absorption of the zero-carbon factory environment model in time period t; Indicates the number of vegetation types; Indicates The amount of carbon absorbed by vegetation types per unit time; Indicates Carbon emissions per unit time by vegetation type; Indicates the start time of period t; represents the end time of period t; Represents the total number of vegetation types.

4. The zero-carbon factory management method according to claim 3, characterized in that: The specific steps of S920 include: S921, obtaining energy data and raw material data of the input process topology structure within time period t; wherein the energy data also includes energy type and carbon emission coefficient of each energy type, and the raw material data also includes raw material type and carbon emission coefficient of each raw material type; S922. Determine the total carbon emissions of the zero-carbon factory environment model in time period t using the following formula: ， in, represents the total carbon emissions of the zero-carbon factory environment model in time period t; Indicates Node Energy input by energy type; Indicates Carbon emission coefficient of each energy type; represents the conversion factor between carbon and carbon dioxide; Indicates Node Raw material input quantity of each raw material type; Indicates Carbon emission coefficient of each raw material type; The total number of nodes representing the process topology; Indicates the total number of energy types; Indicates the total number of raw material types; Indicates the carbon capture equipment Energy input by energy type; Represents the carbon capture duration in time period t.

5. The zero-carbon factory management method according to claim 4, characterized in that: Use the following formula to determine the carbon capture time of the zero-carbon plant environmental model in time period t: ， in, It represents the amount of carbon captured per unit time; Represents the carbon capture duration in time period t.

6. The zero-carbon factory management method according to claim 1, characterized in that: S400 also includes the following steps: Each node in the process topology is configured with a material loss function; Determining the estimated intermediate amount through the material loss function, the raw material input amount and the estimated product amount; The intermediate output of the corresponding process is extracted from the historical data; the material loss function of the node is corrected through the intermediate output and the estimated intermediate quantity to obtain a material loss correction coefficient.

7. The zero-carbon factory management method according to claim 6, characterized in that: Each node in the process topology is configured with a recycling times threshold; Recycling the intermediates of each node, and counting the number of times the intermediates are recycled; Using the intermediate whose recycling times are less than the recycling threshold as the raw material of the node that recycles the intermediate; The intermediates whose recycling times are equal to or greater than the recycling threshold are regarded as waste.

8. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the management method according to any one of claims 1 to 7 is implemented.

Images