Method and device for collecting carbon footprint information of cyanamide product

Abstract

The invention discloses a cyanamide product carbon footprint information acquisition method and device, and relates to the technical field of cyanamide product carbon footprint acquisition, and the method comprises the following steps: S1, equipment data and carbon emission detection; s2, reversely deducing the characteristics of the raw materials; s3, raw material source retrieval; and S4, data comparison and analysis. According to the cyanamide product carbon footprint information acquisition method and device, the implicit relationship among the equipment operation data, the process parameters and the raw material characteristics is dominated, a quantitative basis is provided for reverse deduction of the raw material characteristics, and finally, accurate source positioning is realized, so that whether the specific source of the raw material is consistent with data provided by a provider or not is determined; therefore, the situation of falsification is avoided, a producer does not need to carry out random submission inspection or sampling inspection after receiving the raw materials, the characteristics of the raw materials can be reversely deduced only by detecting the equipment operation parameters and the carbon emission, the labor burden is greatly reduced, and real-time reverse deduction can be achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of carbon footprint collection of cyanamide products, and in particular to a method and device for collecting carbon footprint information of cyanamide products. Background Art

[0002] By determining system boundaries, collecting data and using calculation methods, the carbon footprint information of cyanamide products can be collected more comprehensively. By collecting carbon footprint information, companies can accurately identify the links with higher carbon emissions in the life cycle of cyanamide products, thereby formulating more targeted emission reduction measures.

[0003] During the production phase, the carbon footprint collection method for cyanamide products records all carbon emission data from the time raw materials enter the production equipment to the time products are packaged and put into storage. This includes carbon emissions generated by energy consumption during the reaction process, separation and purification, drying, and other processes. Currently, the carbon footprint collection method estimates carbon emissions based on raw material characteristics and equipment operation data. However, the raw material characteristics data is often provided by suppliers. If the manufacturer requires accurate raw material characteristics, it can only conduct random sampling or submit for inspection. If the actual raw material characteristics are inconsistent with the data provided by the supplier, the final output data on the carbon emissions of the cyanamide product will be inaccurate. Summary of the Invention

[0004] In view of the shortcomings of the existing technology, the present invention provides a method and device for collecting carbon footprint information of cyanamide products, which solves the problems raised in the above background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a method for collecting carbon footprint information of cyanamide products, the method comprising the following steps:

[0006] S1. Equipment data and carbon emission detection:

[0007] Clarify the production process of cyanamide products and record the operating methods of each process. Set up detection points at the links that generate carbon emissions during the production process. For continuous production links, use online real-time detection methods and record detection data every 5 minutes. For intermittent production links, test after each operation cycle.

[0008] S2. Reverse raw material characteristics:

[0009] Establish a data model and, based on the analysis and research of historical production data, determine the correlation between processing equipment operating data, processing method parameters and raw material characteristics. Use statistical methods such as regression analysis and principal component analysis to establish a mathematical model to describe the functional relationship between equipment operating parameters, process parameters and raw material characteristics.

[0010] Then, the processing equipment operation data and processing method information collected during the current production process are input into the established data model. Through calculation and analysis of the model, the various characteristic parameters of the raw materials are inferred, and the inferred raw material characteristic parameters are compiled into a report;

[0011] S3. Raw material source search:

[0012] Collect information on all raw material suppliers, enter the collected information into the raw material database, and establish detailed raw material files;

[0013] Using a fuzzy matching algorithm, the similarity between the raw material characteristic parameters currently obtained by reverse inference and the raw material characteristic parameters of each supplier in the raw material database is calculated. Based on the similarity score, a list of suppliers with a similarity score greater than or equal to the matching threshold is screened out, and the candidate raw material source information is organized into a list;

[0014] S4. Data comparison and analysis:

[0015] Compare and analyze the raw material characteristic parameters of the suppliers in the candidate raw material source list with the data provided by the provider, compare each characteristic indicator one by one, calculate the difference value and difference rate of the indicator, and analyze whether the difference is within the allowable range.

[0016] Furthermore, in step S2, the raw material characteristics include but are not limited to the purity, impurity content, calorific value, and water content of the raw materials.

[0017] Furthermore, in step S2, the report includes but is not limited to the name, specifications, various characteristic indicators and their values of the raw materials.

[0018] Furthermore, in step S2, the core formula of the data model is a multiple linear regression model, and the formula is as follows:

[0019] y=β0+β1X1+β2X2+…+β n X n +ε

[0020] Among them, y is the dependent variable, which represents the predicted value parameter of raw material characteristics, X i The independent variables represent equipment operating parameters or process parameters.

[0021] Furthermore, in the formula, β i The regression coefficient represents the degree of influence of the independent variable on the dependent variable, and ε is the error term, which represents the random factors not captured by the model, such as environmental fluctuations and measurement errors.

[0022] Furthermore, in step S3, the supplier information includes supplier name, address, contact information, raw material type, raw material characteristic parameters, and raw material batch.

[0023] Furthermore, in step S3, the similarity calculation formula is:

[0024]

[0025] Among them, S is the similarity score, W i is the weight of the i-th indicator, X i is the raw material characteristic parameter value obtained by reverse deduction. The higher the similarity score, the closer the raw material characteristics are.

[0026] Furthermore, in the similarity calculation formula, y i It is the supplier's raw material characteristic parameter value in the raw material database.

[0027] Furthermore, in the similarity calculation formula, n is the number of matching indicators.

[0028] A device is provided, which uses the above-mentioned method for collecting carbon footprint information of cyanamide products. The device includes a server equipped with a model algorithm for inferring raw material characteristic parameters.

[0029] The present invention provides a method and device for collecting carbon footprint information of cyanamide products, which has the following beneficial effects:

[0030] 1. This method and device for collecting carbon footprint information on cyanamide products makes the implicit relationship between equipment operating data, process parameters, and raw material characteristics explicit, providing a quantitative basis for inferring raw material characteristics and ultimately achieving precise source location. This allows for determining whether the specific source of the raw materials is consistent with the data provided by the provider, thereby avoiding fraud. Furthermore, the manufacturer does not need to conduct random inspections or spot checks after receiving the raw materials. Instead, it only needs to test equipment operating parameters and carbon emissions to infer raw material characteristics, greatly reducing the manual burden and enabling real-time inference. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 The present invention is a flow chart of a method for collecting carbon footprint information of cyanamide products. DETAILED DESCRIPTION

[0032] The following embodiments of the present invention are described in further detail with reference to the accompanying drawings and examples. The following examples are used to illustrate the present invention but are not intended to limit the scope of the present invention.

[0033] like Figure 1 As shown, the present invention provides a technical solution: a method for collecting carbon footprint information of cyanamide products, the method comprising the following steps:

[0034] S1. Equipment data and carbon emission detection:

[0035] Clarify the production process of cyanamide products and record the operating methods of each process. Set up detection points at the links that generate carbon emissions during the production process. For continuous production links, use online real-time detection methods and record detection data every 5 minutes. For intermittent production links, test after each operation cycle.

[0036] S2. Reverse raw material characteristics:

[0037] Establish a data model and, based on the analysis and research of historical production data, determine the correlation between processing equipment operating data, processing method parameters and raw material characteristics. Use statistical methods such as regression analysis and principal component analysis to establish a mathematical model to describe the functional relationship between equipment operating parameters, process parameters and raw material characteristics.

[0038] Then, the processing equipment operation data and processing method information collected during the current production process are input into the established data model. Through calculation and analysis of the model, the various characteristic parameters of the raw materials are inferred, and the inferred raw material characteristic parameters are compiled into a report;

[0039] The raw material characteristics include but are not limited to the purity, impurity content, calorific value, and water content of the raw materials. The report includes but is not limited to the name, specifications, various characteristic indicators and their values of the raw materials.

[0040] The core formula of the data model is the multiple linear regression model, which is as follows:

[0041] y=β0+β1X1+β2X2+…+β n X n +ε

[0042] Among them, y is the dependent variable, which represents the predicted value parameter of raw material characteristics, X i The independent variable represents the equipment operating parameters or process parameters, β i The regression coefficient represents the degree of influence of the independent variable on the dependent variable, and ε is the error term, which represents the random factors not captured by the model, such as environmental fluctuations and measurement errors.

[0043] S3. Raw material source search:

[0044] Collect information on all raw material suppliers, enter the collected information into the raw material database, and establish detailed raw material files;

[0045] Using a fuzzy matching algorithm, the similarity between the raw material characteristic parameters currently obtained by reverse inference and the raw material characteristic parameters of each supplier in the raw material database is calculated. Based on the similarity score, a list of suppliers with a similarity score greater than or equal to the matching threshold is screened out, and the candidate raw material source information is organized into a list;

[0046] Supplier information includes supplier name, address, contact information, raw material type, raw material characteristic parameters, and raw material batch;

[0047] Similarity calculation formula:

[0048]

[0049] Among them, S is the similarity score, W i is the weight of the i-th indicator, X i is the raw material characteristic parameter value obtained by reverse deduction. The higher the similarity score, the closer the raw material characteristics are. i is the supplier's raw material characteristic parameter value in the raw material database, and n is the number of matching indicators;

[0050] S4. Data comparison and analysis:

[0051] Compare and analyze the raw material characteristic parameters of the suppliers in the candidate raw material source list with the data provided by the provider, compare each characteristic indicator one by one, calculate the difference value and difference rate of the indicator, and analyze whether the difference is within the allowable range.

[0052] Based on the above description, when applied in the production and processing of cyanamide products;

[0053] In the data model, it is assumed that the purity inversion model is obtained by fitting historical data:

[0054] Purity=60+0.3T+0.05P-0.2M-0.1t+ε

[0055] T: average temperature of the reactor during the constant temperature stage, P: average power of the stirring motor, M: initial water content of the raw materials when they are added, t: reaction time, Purity: raw material purity, ε: error term covers all random factors that the model fails to capture. The physical meaning of the purity inverse model is that increasing temperature and stirring power promotes reaction sufficiency (increases purity), while excessive initial water content and reaction time may lead to side reactions (decreases purity).

[0056] When there are too many independent variables (such as 20+ equipment operating parameters), PCA is used to map high-dimensional data to low-dimensional principal components. The formula is as follows:

[0057] The kth principal component expression

[0058] PC k =αk1x1+αk2x2+…+αk n x n

[0059] Among them, αk i The load coefficient of the i-th independent variable on the k-th principal component (the larger the absolute value, the higher the contribution of the variable to the principal component);

[0060] Constraints: (load normalization);

[0061] For example, PCA is performed on 10 parameters such as reactor temperature, pressure, power, and steam flow, and the first two principal components are extracted (cumulative variance contribution ≥ 85%):

[0062] PC1 = 0.6T + 0.5P + 0.4S - 0.3F (principal component 1, representing "energy input characteristics")

[0063] PC2 = 0.4T - 0.3P + 0.6F + 0.2S (Principal component 2, representing "process fluctuation characteristics")

[0064] Among them, F is the feed flow rate, and a regression relationship is established with the raw material calorific value Q through PC1 and PC2:

[0065] Q = 1000 + 200 PC1 - 50 PC2

[0066] To correlate equipment operation data (e.g., X = [T, P, S]) with carbon emissions data (e.g., Y = [CO2, CH4]), use CCA to find the maximum correlation feature between the two sets of variables:

[0067] Canonical Pair Formula

[0068]

[0069] Where u and v are the linear combinations of equipment data and carbon emission data, respectively, maximizing the correlation coefficient ρ(u, v);

[0070] Constraints: Var(u) = Var(v) = 1;

[0071] CCA finds a strong correlation between equipment power P, reaction time t and CO2 emissions:

[0072] u=0.8P+0.6t, v=0.9CO2+0.3CH4, ρ(u, v)=0.92

[0073] This indicates that when the equipment is operated at high power and the reaction time is too long, carbon emissions increase significantly, which can be used to infer the reaction activity of the raw materials (low activity requires longer time / higher power);

[0074] After the model is established, its effectiveness needs to be verified. The core test formula is:

[0075] Coefficient of determination R 2

[0076]

[0077] Among them, yi : actual raw material characteristic value, Model prediction value, Sample mean, R 2 The closer it is to 1, the better the model fitting effect;

[0078] Test F:

[0079]

[0080] (regression sum of squares), (residual sum of squares);

[0081] If F>Fα(k,nk-1), the model as a whole is significantly effective;

[0082] Formula application examples:

[0083] Data preparation: Collect 100+ batches of historical data and build a dataset (X1, X2, ..., X n , y);

[0084] Parameter estimation: Solve β0, β1, ..., β by least squares method n , making Minimize, calculation formula:

[0085]

[0086] Where X is the independent variable matrix, including the constant term 1; y is the dependent variable vector;

[0087] Model Validation: Calculating R 2 and F, ensuring that the model is significant and well-fitted;

[0088] Reverse application: Input the current equipment operating parameters X1, X2, ..., X n ,calculate:

[0089] y=β0+β1X1+β2X2+…+β n X n +ε

[0090] Obtain predicted values of raw material properties (such as purity and water content);

[0091] Based on the above description, the implicit relationship between equipment operating data, process parameters and raw material characteristics is made explicit, providing a quantitative basis for inferring raw material characteristics, and ultimately achieving accurate source positioning. This allows us to determine whether the specific source of the raw materials is consistent with the data provided by the provider, thereby avoiding fraud. There is no need for the producer to conduct random inspections or spot checks after receiving the raw materials. Instead, it only needs to test the equipment operating parameters and carbon emissions to infer the raw material characteristics, which greatly reduces the manual burden and enables real-time inference.

[0092] A device is provided, which uses the above-mentioned method for collecting carbon footprint information of cyanamide products. The device includes a server equipped with a model algorithm for inferring raw material characteristic parameters.

[0093] In summary, when using the method and device for collecting carbon footprint information of cyanamide products, first input the current equipment operating parameters X1, X2, ..., X n ,calculate:

[0094] y=β0+β1X1+β2X2+…+β n X n +ε

[0095] Obtain the predicted value of raw material characteristics, and use the fuzzy matching algorithm to calculate the similarity between the raw material characteristic parameters currently obtained by reverse inference and the raw material characteristic parameters of each supplier in the raw material database;

[0096] Similarity calculation formula:

[0097]

[0098] Based on the similarity score, a list of suppliers with similarity scores greater than or equal to a matching threshold is screened out, and the candidate raw material source information is organized into a list;

[0099] Then compare whether the supplier of the raw material exists in the list. If so, it means that the calculated raw material characteristic parameters and the raw material characteristic parameters provided by the supplier are within the allowable error threshold, thereby indicating that the raw material is correct. If the supplier of the raw material does not exist in the list, it means that the calculated raw material characteristic parameters and the raw material characteristic parameters provided by the supplier are beyond the allowable error threshold, indicating that the raw material does not meet the raw material characteristic parameters provided by the supplier, and is suspected of being fake.

[0100] The embodiments of the present invention are presented for purposes of illustration and description and are not intended to be exhaustive or to limit the invention to the disclosed forms. Many modifications and variations will be apparent to those skilled in the art. The embodiments are chosen and described in order to better illustrate the principles of the invention and its practical application and to enable those skilled in the art to understand the invention and design various embodiments with various modifications as suited for specific applications.

Claims

1. A method for collecting carbon footprint information of cyanamide products, characterized by: The method for collecting carbon footprint information of cyanamide products comprises the following steps: S1. Equipment data and carbon emission detection: Clarify the production process of cyanamide products and record the operating methods of each process. Set up detection points at the links that generate carbon emissions during the production process. For continuous production links, use online real-time detection methods and record detection data every 5 minutes. For intermittent production links, test after each operation cycle. S2. Reverse raw material characteristics: Establish a data model and, based on the analysis and research of historical production data, determine the correlation between processing equipment operating data, processing method parameters and raw material characteristics. Use statistical methods such as regression analysis and principal component analysis to establish a mathematical model to describe the functional relationship between equipment operating parameters, process parameters and raw material characteristics. Then, the processing equipment operation data and processing method information collected during the current production process are input into the established data model. Through calculation and analysis of the model, the various characteristic parameters of the raw materials are inferred, and the inferred raw material characteristic parameters are compiled into a report; S3. Raw material source search: Collect information on all raw material suppliers, enter the collected information into the raw material database, and establish detailed raw material files; Using a fuzzy matching algorithm, the similarity between the raw material characteristic parameters currently obtained by reverse inference and the raw material characteristic parameters of each supplier in the raw material database is calculated. Based on the similarity score, a list of suppliers with a similarity score greater than or equal to the matching threshold is screened out, and the candidate raw material source information is organized into a list; S4. Data comparison and analysis: Compare and analyze the raw material characteristic parameters of the suppliers in the candidate raw material source list with the data provided by the provider, compare each characteristic indicator one by one, calculate the difference value and difference rate of the indicator, and analyze whether the difference is within the allowable range.

2. The method for collecting carbon footprint information of a cyanamide product according to claim 1, characterized in that: In step S2, the raw material characteristics include but are not limited to the purity, impurity content, calorific value, and water content of the raw material.

3. The method for collecting carbon footprint information of cyanamide products according to claim 1, characterized in that: In step S2, the report includes but is not limited to the name, specification, various characteristic indicators and their values of the raw materials.

4. The method for collecting carbon footprint information of cyanamide products according to claim 1, characterized in that: In step S2, the core formula of the data model is a multiple linear regression model, and the formula is as follows: y=β0+β1X1+β2X2+…+β n X n +e Among them, y is the dependent variable, which represents the predicted value parameter of raw material characteristics, X i The independent variables represent equipment operating parameters or process parameters.

5. The method for collecting carbon footprint information of cyanamide products according to claim 4, characterized in that: In the above formula, β i The regression coefficient represents the degree of influence of the independent variable on the dependent variable, and ε is the error term, which represents the random factors not captured by the model, such as environmental fluctuations and measurement errors.

6. The method for collecting carbon footprint information of cyanamide products according to claim 1, characterized in that: In step S3, the supplier information includes supplier name, address, contact information, raw material type, raw material characteristic parameters, and raw material batch.

7. The method for collecting carbon footprint information of cyanamide products according to claim 1, characterized in that: In step S3, the similarity calculation formula is: Among them, S is the similarity score, W i is the weight of the i-th indicator, X i is the raw material characteristic parameter value obtained by reverse deduction. The higher the similarity score, the closer the raw material characteristics are.

8. The method for collecting carbon footprint information of cyanamide products according to claim 7, characterized in that: In the similarity calculation formula, y i It is the supplier's raw material characteristic parameter value in the raw material database.

9. The method for collecting carbon footprint information of cyanamide products according to claim 7, characterized in that: In the similarity calculation formula, n is the number of matching indicators.

10. A device, using the method for collecting carbon footprint information of a cyanamide product according to any one of claims 1 to 9, characterized in that: The device includes a server equipped with a model algorithm for inversely estimating raw material characteristic parameters.

Images