Copper product carbon footprint data collection and processing method based on full life cycle

Abstract

The invention discloses a copper product carbon footprint data collection and processing method based on a full life cycle, and the method comprises the steps: dividing the production and processing life cycle of a copper product into a plurality of stages, and collecting the carbon emission data of the current life cycle; constructing a multivariate time sequence matrix X (t) by using the carbon emission data of the plurality of stages according to a time sequence, decomposing the X (t) into a dynamic mode, and calculating mode energy to obtain a dominant mode subset; using the dominant mode subset to obtain a reconstructed data sequence, calculating with X (t) to obtain an abnormal score, and when the abnormal score is greater than a preset score threshold, inputting the carbon emission data and the carbon footprint network into a pre-trained graph convolutional neural network to obtain a data abnormal stage; and energy consumption data and operation data of the plurality of devices in the data exception stage are collected, and a plurality of abnormal devices are obtained through correlation analysis. The invention relates to the field of industrial carbon emission, and solves the technical problems of difficulty in abnormal detection of carbon emission data and complexity in data processing.

Description

Technical Field

[0001] The present invention belongs to the field of industrial carbon emissions and relates to data processing and analysis technology, specifically to a method for collecting and processing carbon footprint data of copper products based on the entire life cycle. Background Art

[0002] As the world pays more and more attention to environmental protection, carbon emission management has become a key link in the sustainable development of enterprises. For copper product manufacturers, it is crucial to accurately collect carbon emission data. Carbon emission data can reflect the energy efficiency, process rationality and environmental impact of the enterprise's production process. Through the analysis of carbon emission data, enterprises can identify high-carbon emission links, take corresponding energy-saving and emission reduction measures, reduce production costs, meet the requirements of environmental protection regulations, and enhance the social responsibility and market competitiveness of enterprises.

[0003] The production and processing of copper products involves multiple complex stages, and the sources of carbon emissions in each stage are diverse and dispersed. Carbon emissions are generated in every link from raw material acquisition to final product processing. Therefore, the sources of carbon emission data are wide and complex, which brings great difficulties to data collection and integration. At the same time, the existing methods lack effective organization and processing methods when processing large amounts of carbon emission time series data, resulting in excessive calculations and long processing time, and unable to provide analysis results to enterprises in a timely manner, affecting the timeliness and accuracy of enterprise decision-making.

[0004] To achieve accurate tracking and management of carbon footprint, it is necessary to ensure the accuracy and comprehensiveness of carbon emission data. However, when carbon emission data is abnormal, the existing methods lack in-depth exploration of the internal connections between the various stages of the production process, making it difficult to accurately trace the root cause of the abnormality. When faced with abnormal carbon emission situations, enterprises are unable to take targeted measures to solve them, increasing their economic losses. Summary of the invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art; to this end, the present invention proposes a method for collecting and processing carbon footprint data of copper products based on the entire life cycle, which is used to solve the technical problems of difficulty in detecting anomalies in carbon emission data and complex data processing in the prior art.

[0006] To achieve the above objectives, the present invention provides a method for collecting and processing carbon footprint data of copper products based on the entire life cycle, comprising:

[0007] S1, divide the production and processing life cycle of copper products into several stages, and collect carbon emission data of the current life cycle through sensors to obtain carbon emission data of several stages;

[0008] S2, construct a multivariate time series matrix X(t) according to the chronological order of the carbon emission data of several stages, decompose X(t) into dynamic modes, and obtain the dominant mode subset by calculating the modal energy of the dynamic modes;

[0009] S3, using the dominant mode subset to obtain a reconstructed data sequence, and calculating the anomaly score by the reconstructed data sequence and X(t), and comparing whether the anomaly score is greater than the preset score threshold; if yes, jump to S4; if not, mark the next life cycle as the current life cycle and jump to S1;

[0010] S4, constructing a carbon footprint network G according to several stages, inputting the carbon emission data of several stages and the carbon footprint network G into the pre-trained graph convolutional neural network to obtain the data abnormal stage;

[0011] S5, collects energy consumption data and operation data of several devices in the data abnormality stage, and obtains several abnormal devices through correlation analysis.

[0012] Based on the above technical process, the present invention constructs a complete and efficient carbon emission data collection, processing, early warning and abnormal traceability system; through refined carbon emission data collection and dynamic modal analysis, it realizes accurate tracking and abnormal detection of carbon footprint in the production and processing of copper products, effectively solving the problems of incomplete carbon emission data collection, low processing efficiency and difficult abnormal traceability in traditional methods. By constructing a carbon footprint network and applying a graph convolutional neural network, the present invention not only improves the accuracy of data processing, but also enhances the real-time nature of abnormal detection and the accuracy of traceability, providing strong technical support for the green production and carbon emission management of copper products.

[0013] Furthermore, the multivariate time series matrix X(t)=[x1(t),x2(t),…,xn(t)] T ; Where t represents time, xi(t) represents the carbon emissions of the i-th stage at time t, i = 1, 2, …, n, and n represents the number of stages.

[0014] Further, the method of obtaining the dominant mode subset by calculating the modal energy of the dynamic mode includes:

[0015] S21, decomposing X(t) into a number of dynamic modes {Φm, λm} using a dynamic mode decomposition algorithm; wherein Φm represents a mode matrix, and λm represents a corresponding eigenvalue;

[0016] S22, according to the formula Em=||Φm|| 2 Calculate the energy value Em of the dynamic mode and obtain several modal energies; where ||·|| represents the norm operation;

[0017] S23, arranging the plurality of modal energies in descending order, and accumulating the sorted modal energies in sequence, calculating the ratio of the accumulated value to the sum of the modal energies, and when the ratio exceeds a preset threshold, screening out the corresponding plurality of modes to obtain a dominant modal subset.

[0018] Constructing a multivariate time series matrix provides an orderly structure for the data, which is not only convenient for batch processing and calculation, but also effectively reduces the data dimension through dynamic mode decomposition technology, thereby reducing the amount of calculation. This combination significantly improves the efficiency of data processing, enabling companies to quickly obtain analysis results and make decisions. In addition, the method of screening the dominant mode subset based on modal energy can adaptively focus on key information and avoid the problem of information overload. The extracted dominant mode subset reveals the main change pattern of carbon emissions, enhances the accuracy of key information analysis, helps to grasp the core feature trend, and provides a scientific basis for optimizing the production process.

[0019] Furthermore, the abnormality score is obtained by reconstructing the data sequence and calculating X(t), including:

[0020] S31, by formula Calculate the reconstructed data sequence in, represents the column vector of the jth modal matrix Φj in the dominant modal subset, λj represents the corresponding eigenvalue, bj is the coefficient vector determined by the initial conditions, and k represents the number of modes in the dominant modal subset;

[0021] S32, calculating the difference between the reconstructed data sequence and X(t) at the corresponding time point to obtain a residual vector r(t);

[0022] S33, calculate the standard deviation σ of the residual vector r(t) r , by the formula AS(t)=(||r(t)|| / σ r )×w(t) is used to calculate the anomaly score, where w(t) represents the dynamic weight.

[0023] Furthermore, the method of obtaining bj includes:

[0024] S31-1, construct the initial conditions with the multivariate time series matrix at the initial time t0 of the current life cycle, and obtain the initial conditions as follows: Where m represents the mode index, M represents the number of dynamic modes, represents the column vector of the modal matrix Φm, bm is the coefficient vector to be solved;

[0025] S31-2, write the initial conditions in matrix form: X(t0) = Φb; where, b=[b1,b2,…,bm] T ;

[0026] S31-3, solve according to the least squares method: b=(Φ T Φ) -1 Φ T X(t0), get the coefficient vector b;

[0027] S31-4, obtain the corresponding coefficients in the coefficient vector b according to the dominant mode subset to obtain bj.

[0028] By comparing the reconstructed data with the actual measured data, calculating the residual vector, and combining the dynamic weights to calculate the anomaly score, the accuracy of carbon emission anomaly detection can be improved, effectively reducing false positives and false negatives. Combining dynamic mode decomposition with the anomaly scoring mechanism can quickly and accurately identify anomalies in carbon emission data, enhance the timeliness of anomaly detection, prevent the problem from further deteriorating, and thus reduce the environmental risks and economic losses that may be caused by carbon emission anomalies.

[0029] Furthermore, the dynamic weight is obtained by:

[0030] According to w(t) = α(1-α) t-t’ The dynamic weight is calculated by the formula; where α represents the attenuation coefficient, which is used to control the attenuation speed of the dynamic weight, and t' represents the current time.

[0031] In the dynamic weight formula, the time interval t-t' is used as a variable in the exponential part, which intuitively reflects the timeliness of the data. As the time interval increases, that is, the older the data is, the smaller the value of t-t' is, so that the weight of the data point is lower. This time-order-based weight allocation method can reasonably allocate weights in chronological order, so that the analysis results are closer to the current production reality. Using dynamic weights in the process of calculating anomaly scores can make recent carbon emission data more influential in judging anomalies. When sudden anomalies occur in the production process, such as sudden equipment failure causing a sharp increase in carbon emissions, the weight of recent data is higher, and the anomaly score will rise rapidly, thereby detecting anomalies more quickly, improving the timeliness of anomaly detection, and avoiding the masking of recent abnormal changes due to the average effect of long-term historical data.

[0032] Further, the carbon footprint network G is constructed according to several stages, including:

[0033] S4-11, define several stages of the copper product production and processing life cycle as nodes of the carbon footprint network, and obtain several nodes;

[0034] S4-12, defining the edges and weights of several nodes according to the material flow, energy flow and carbon emission transfer relationship between several stages, and obtaining several edges and weights of several edges;

[0035] S4-13, according to the average carbon emissions of each stage and several equipment parameters, attribute information is added to several nodes of the carbon footprint network to obtain the carbon footprint network G(V,E,W); wherein V represents several nodes, E represents several edges, and W represents the weights of several edges.

[0036] Each stage of the copper product production and processing process does not exist in isolation, but is interconnected and influenced by material flow, energy flow and carbon emission transmission. Defining each stage as a node of the carbon footprint network and constructing edges and weights based on the actual relationship between them can transform the inherent logic of the production process into a network structure, thereby considering the carbon emissions in the entire production process more comprehensively and systematically.

[0037] Furthermore, the step of inputting the carbon emission data of several stages and the carbon footprint network G into the pre-trained graph convolutional neural network includes:

[0038] S42-1, inputting the carbon emission data of several stages and the carbon footprint network G into the pre-trained graph convolutional neural network to obtain abnormal probability values ​​of several nodes;

[0039] S42-2, marking nodes whose abnormal probability values ​​exceed preset probabilities as abnormal nodes, and obtaining corresponding data abnormal stages according to the abnormal nodes.

[0040] The constructed carbon footprint network G clarifies the relationship between each production stage. The graph convolutional neural network can perform in-depth analysis based on the network structure and node attributes to calculate the abnormal probability value of each node (i.e., production stage). By comparing with the preset probability, it can accurately identify abnormal nodes and then locate the corresponding data abnormal stage. Compared with traditional methods, the positioning is more accurate, which can provide a direction for enterprises to troubleshoot problems, improve the efficiency and reliability of abnormal detection, and reduce the cost of enterprise response.

[0041] Furthermore, the construction process of the pre-trained graph convolutional neural network includes:

[0042] S43-1, build and obtain graph convolution model based on deep learning algorithm;

[0043] S43-2, collect carbon emission data of several historical life cycles, and mark the carbon emission data according to abnormal conditions in several stages, to obtain several carbon emission data and several marked data;

[0044] S43-3, preprocessing a number of carbon emission data and a number of annotated data to obtain preprocessed data, and making a one-to-one correspondence between the preprocessed data and a number of nodes in the carbon footprint network to obtain a model data set;

[0045] S43-4, dividing the model data set into a training set, a validation set, and a test set according to a preset ratio, and setting a loss function, training parameters, and optimization algorithm for graph convolution model training;

[0046] S43-5, use the training set and the validation set to iteratively train and validate the graph convolution model, and save the graph convolution model with the highest validation accuracy to obtain the optimal graph convolution model;

[0047] S43-6, input the test set into the optimal graph convolution model, obtain the test accuracy, and determine whether the test accuracy is greater than the preset accuracy threshold; if yes, output the optimal graph convolution model as a pre-trained graph convolution neural network; if not, adjust the model's loss function, training parameters and optimization algorithm, and jump to S43-5.

[0048] Furthermore, the several abnormal devices obtained through correlation analysis include:

[0049] S5-1, collecting energy consumption data and operation data of several devices during the data abnormality stage to obtain data sets of several devices; wherein the energy consumption data includes the degree of power consumption and fuel usage per unit time, and the operation data includes the average temperature, average voltage and average current of the equipment operation;

[0050] S5-2, using the calculation formula of the Pearson correlation coefficient, calculate the correlation coefficient of each pair of devices in the data set to obtain a correlation matrix S; wherein the dimension of S is p×q, and Spq represents the correlation coefficient between the p-th device and the q-th device;

[0051] S5-3, collecting historical normal data sets of several devices in the data abnormality stage, and calculating several standard correlation coefficients based on the historical normal data sets;

[0052] S5-4, calculating the mean μ and standard deviation σ of several standard correlation coefficients of each pair of devices, and obtaining the correlation threshold of each pair of devices as [μ-βσ,μ+βσ] according to the mean μ and standard deviation σ; wherein k represents a preset adjustment coefficient;

[0053] S5-5, traverse each column of the correlation matrix S in turn, count the number of data in the p-th column that are not within the corresponding correlation threshold range, and obtain the number of abnormal data;

[0054] S5-6, determine whether the number of abnormal data in the p-th column is greater than a preset number threshold; if yes, mark the device p as an abnormal device; if no, continue to traverse the next column of data.

[0055] The historical normal data set contains the data patterns of the equipment under normal operating conditions, which reflect the stable correlation relationship between the equipment. Using historical data to calculate the mean μ and standard deviation σ of the standard correlation coefficient can provide a reasonable reference standard for the current data abnormal stage. Since the production environment and equipment operating conditions are similar and continuous to a certain extent, the statistical characteristics of historical normal data can help determine a range of normal correlation. By comparing the correlation of the current equipment pair with the threshold, it is possible to more accurately determine whether the current correlation is abnormal, reduce the interference of factors such as environmental fluctuations and short-term production changes on abnormal judgment, and improve the accuracy and stability of abnormal detection.

[0056] The application of carbon footprint network and graph convolutional neural network, as well as equipment correlation analysis method, can accurately locate the specific stage and equipment where carbon emission anomalies occur. Enterprises can conduct in-depth inspections and repairs in a targeted manner, improve the efficiency of problem solving, and reduce the time and cost of troubleshooting the causes of anomalies.

[0057] Compared with the prior art, the present invention has the following beneficial effects:

[0058] The production and processing of copper products involves multiple complex stages, and the carbon emission sources in each stage are diverse and scattered. The present invention divides the production and processing life cycle into several stages and deploys sensors at each stage to achieve systematic collection of carbon emission data, providing basic data support for subsequent precise analysis, and effectively solving the problem of incomplete and inaccurate acquisition of carbon emission data. In addition, the management of carbon emission data faces challenges such as large data volume and strong time series, which makes it difficult to effectively integrate and utilize. The present invention organizes data by constructing a multivariate time series matrix, so that the data is arranged in order in the time dimension, which is convenient for subsequent processing such as dynamic modal decomposition, and solves the problem of chaotic management of carbon emission data and difficulty in effective utilization.

[0059] The production process of copper products is complex, and there are many factors that affect carbon emissions, which makes it difficult to accurately detect and locate carbon emission anomalies. The present invention uses dynamic mode decomposition technology to obtain the dominant mode subset, and calculates the anomaly score by comparing with the actual data. It can effectively detect the anomaly of carbon emission data, and solves the problem that it is difficult to find carbon emission anomalies due to the complexity of the production process. At the same time, traditional methods are difficult to determine at which stage or which equipment the carbon emission anomaly occurs when faced with complex production processes and numerous equipment. The present invention constructs a carbon footprint network and combines it with a graph convolutional neural network, as well as equipment correlation analysis to accurately locate the data anomaly stage and abnormal equipment, solving the problem of inaccurate and untimely positioning of carbon emission anomalies. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0061] Figure 1 A technical flow diagram of the method for collecting and processing carbon footprint data of copper products based on the entire life cycle provided by the present invention;

[0062] Figure 2 Schematic diagram of the technical process of obtaining abnormal devices through correlation analysis provided by the present invention DETAILED DESCRIPTION

[0063] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0064] See also Figure 1 - Figure 2 The first embodiment of the present invention provides a method for collecting and processing carbon footprint data of copper products based on the entire life cycle, including:

[0065] S1, divide the production and processing life cycle of copper products into several stages, and collect carbon emission data of the current life cycle through sensors to obtain carbon emission data of several stages;

[0066] S2, construct a multivariate time series matrix X(t) according to the chronological order of the carbon emission data of several stages, decompose X(t) into dynamic modes, and obtain the dominant mode subset by calculating the modal energy of the dynamic modes;

[0067] S3, using the dominant mode subset to obtain a reconstructed data sequence, and calculating the anomaly score by the reconstructed data sequence and X(t), and comparing whether the anomaly score is greater than the preset score threshold; if yes, jump to S4; if not, mark the next life cycle as the current life cycle and jump to S1;

[0068] S4, constructing a carbon footprint network G according to several stages, inputting the carbon emission data of several stages and the carbon footprint network G into the pre-trained graph convolutional neural network to obtain the data abnormal stage;

[0069] S5, collects energy consumption data and operation data of several devices in the data abnormality stage, and obtains several abnormal devices through correlation analysis.

[0070] In this embodiment, by subdividing the copper product production and processing life cycle into multiple stages and using a sensor network to realize real-time collection of carbon emission data at each stage, not only the comprehensiveness of data collection is ensured, covering every link from raw material acquisition to final product processing, but also the dynamic changes of carbon emissions in the production process can be captured in a timely manner, providing enterprises with a real-time and complete view of carbon emissions.

[0071] Specifically, during the production preparation stage, various sensors are installed on the equipment startup preheating link and raw material pretreatment equipment, such as equipment startup monitoring sensors, material flow sensors, power consumption sensors, equipment vibration sensors, etc., to collect equipment startup parameters and raw material processing related data, which are used to monitor the equipment startup status and energy consumption, material flow and equipment operation stability during raw material pretreatment.

[0072] In the main production stages (such as smelting, refining, etc.), key equipment (smelting furnace, refining furnace, etc.) and production lines are equipped with a variety of high-precision sensors, such as furnace temperature sensors, oxygen flow sensors, exhaust gas emission monitoring sensor groups, product quality detection sensors, etc., to accurately measure furnace temperature, oxygen flow, exhaust gas emissions and product quality parameters;

[0073] During the product processing and forming stage, for copper material processing equipment (rolling, stretching equipment, etc.) and cooling links, equipment power sensors, mold pressure sensors, cooling medium flow sensors and temperature sensors are installed to monitor equipment operating power, mold pressure, cooling medium flow and temperature changes;

[0074] During the product packaging and storage stage, packaging material usage sensors are installed in the packaging area to record the amount of packaging materials used. Warehouse environment monitoring sensors (temperature and humidity sensors) and warehouse management systems are installed in the finished product warehouse to monitor the warehouse environment and record product in and out information.

[0075] Then, through the existing carbon emission calculation models and methods, the data collected by each sensor are integrated to calculate and obtain the carbon emission data for each stage. It should be noted that the division of the above several stages is only an example, and the specific division can be flexibly adjusted according to the actual production process, equipment layout, management model and other factors of the copper product manufacturer.

[0076] Next, the carbon emission data of each stage collected at the preset time interval is constructed into a multivariate time series matrix X(t) = [x1(t), x2(t), ..., xn(t)] in chronological order. T; Where t represents time, xi(t) represents the carbon emissions of the i-th stage at time t, i=1,2,…,n, n represents the number of stages, t=1,2,…,T, T represents the time of a complete life cycle; then the dynamic mode decomposition (DMD) algorithm is used to decompose the constructed multivariate time series matrix X(t). The DMD algorithm is a data-driven method for analyzing dynamic systems, which can extract the main dynamic modes from the data. In actual calculations, through a series of complex mathematical operations (involving knowledge such as eigenvalue decomposition in linear algebra), X(t) is decomposed into several dynamic modes {Φm,λm}, where Φm represents the modal matrix and λm represents the corresponding eigenvalue;

[0077] Then according to the formula Em=||Φm|| 2 Calculate the energy value Em of the dynamic mode and obtain several modal energies; where ||·|| represents norm operation, and the Frobenius norm can be sampled for operation;

[0078] After calculating the energy values ​​of all dynamic modes, these energy values ​​are arranged in descending order. Assume that the sorting result is E3>E1>E4>E2>… Then add up the sorted modal energies in turn, and calculate the proportion of the accumulated value to the sum of the modal energies. That is, first calculate the proportion of E3 in the total energy, then calculate the proportion of E3+E1 in the total energy, then calculate the proportion of E3+E1+E4 in the total energy, and so on, until the proportion exceeds the preset threshold (in this embodiment, the preset threshold is 80%), then stop accumulating, and select the corresponding modes as the dominant modal subsets. These dominant modal subsets contain the most important dynamic change patterns in the original carbon emission data, and they can be used in subsequent analysis to simplify data processing and highlight key information, so as to better perform operations such as carbon emission anomaly detection.

[0079] In step S3, we first need to calculate the coefficient vector based on the dominant mode subset obtained in the early stage and the corresponding initial conditions, and then obtain the reconstructed data sequence. Then, we calculate the residual vector by combining the reconstructed data sequence with the actual multivariate time series matrix, and further calculate the anomaly score by combining the dynamic weight. Finally, we compare the anomaly score with the preset score threshold to determine the subsequent process direction.

[0080] Specifically, in the calculation of the coefficient vector, the initial conditions must first be constructed using the multivariate time series matrix at the initial time t0 of the current life cycle: Where m represents the mode index, M represents the number of dynamic modes, represents the column vector of the modal matrix Φm, bm is the coefficient vector to be solved; then write it in the matrix form X(t0)=Φb; where, b=[b1,b2,…,bm]T ; Then the least square method is used to solve and obtain the complete coefficient vector. Then the corresponding coefficients are extracted from it according to the dominant mode subset, and these coefficients will be used for the subsequent calculation of the reconstructed data sequence.

[0081] Assume that the dominant mode subset has been obtained in the previous S2 step, which contains k = 3 modes (Φ1, Φ2, Φ3), and the total number of dynamic modes obtained in the entire dynamic mode decomposition process is M = 5, that is, it is assumed that the copper product life cycle is divided into 5 stages.

[0082] Then, taking the current life cycle as an example, assuming that the multivariate time series matrix collected at the start time t0 is: X(t0) =

[23142] T ; Assume that the modal matrix Φm (m = 1, 2, ..., 5) is:

[0083]

[0084] First follow Construct the initial conditions and then write them in matrix form X(t0) = Φb, where and is the column vector of Φm, b=[b1,b2,…,b5] T ;

[0085] Then, we use the least square method to solve b=(Φ T Φ) -1 Φ T X(t0). Calculate Φ T Φ gets a 5×5 matrix, then finds its inverse matrix, and then compares it with Φ T X(t0) is multiplied, and the coefficient vector is assumed to be: b = [0.50.30.20.10.4] T ; Since the dominant mode subsets are Φ1, Φ2, Φ3, the corresponding coefficients b1=0.5, b2=0.3, b3=0.2 are obtained from them;

[0086] Then, through the formula Calculate the reconstructed data sequence in, represents the column vector of the jth modal matrix Φj in the dominant modal subset, λj represents the corresponding eigenvalue, bj represents the coefficient vector, and k represents the number of modes in the dominant modal subset;

[0087] Then, calculate the residual vector And calculate the standard deviation σ of the residual vector r(t) r ;

[0088] Finally, according to the formula AS(t) = (||r(t)|| / σ r)×w(t) is used to calculate the anomaly score; where w(t) represents the dynamic weight and w(t)=α(1-α) t-t’ The formula calculates the dynamic weight, α represents the attenuation coefficient, which is used to control the attenuation speed of the dynamic weight and is determined based on a lot of practical experience, and t' represents the current time;

[0089] Over time, factors such as equipment wear, process adjustments, and changes in raw materials will cause changes in the pattern of carbon emission data. Recent carbon emission data can better reflect the current production status and possible abnormalities, while early data is less representative of the current production status. Therefore, the dynamic weight formula introduces a time-related attenuation coefficient to allow the data weight to change dynamically over time, thereby better adapting to the dynamic characteristics of the production process and enabling anomaly detection and analysis to more timely and accurately reflect current production realities.

[0090] Compare the calculated anomaly score with the preset scoring threshold. If the anomaly score is greater than the preset scoring threshold, it means that the current carbon emission data has an abnormality, and it is necessary to jump to step S4 to further analyze which specific production stages or equipment have problems; if the anomaly score is less than or equal to the preset scoring threshold, it means that the current carbon emission data is basically within the normal fluctuation range. At this time, the next life cycle is marked as the current life cycle, and jump to step S1 to continue collecting new carbon emission data, so as to continuously monitor and analyze the carbon emissions in the production process.

[0091] In step S3, the dominant mode subset is used to reconstruct the data sequence, which greatly reduces the amount of calculation compared to directly processing the original high-dimensional carbon emission data. At the same time, the least squares method is used to solve the coefficient vector b and the subsequent anomaly score calculation, which are based on mathematical models and optimization algorithms and have high computational efficiency. In addition, this method can adapt to changes in carbon emission data in different production stages and working conditions, because the dominant mode subset is dynamically selected according to the actual data characteristics, and the dynamic weight can also adjust the importance of the data according to time, so that the entire anomaly detection method has strong adaptability and robustness, and can work effectively in complex and changing production environments.

[0092] Then, in S4, by constructing a carbon footprint network, the complex internal connections of each stage in the entire copper product production process were integrated; and the graph convolutional neural network was used to mine the abnormal characteristics of the data to provide support for the precise positioning of carbon emission problems.

[0093] Specifically, we first build a carbon footprint network based on the production and processing of copper products, including:

[0094] S4-11, defines each stage of the copper product production and processing life cycle as a node of the carbon footprint network;

[0095] S4-11, define several stages of the copper product production and processing life cycle as nodes of the carbon footprint network, and obtain several nodes;

[0096] S4-12, define the edges and weights of several nodes according to the material flow, energy flow and carbon emission transfer relationship between several stages; for example, the high-temperature copper liquid is transported from the smelting stage to the refining stage, which is accompanied by a large amount of energy consumption and carbon emissions. The weight value of the edge connecting the two is determined based on these actual data;

[0097] S4-13, according to the average carbon emissions of each stage and several equipment parameters, attribute information is added to each node of the carbon footprint network to obtain the carbon footprint network G(V,E,W); wherein V represents several nodes, E represents several edges, and W represents the weights of several edges.

[0098] Each stage of the copper product production and processing process does not exist in isolation, but is interconnected and influenced by material flow, energy flow and carbon emission transmission relationships. Defining each stage as a node of the carbon footprint network and constructing edges and weights based on the actual relationship between them can transform the inherent logic of the production process into a network structure, thereby considering the carbon emissions in the entire production process in a more comprehensive and systematic manner. This representation method based on the network structure is conducive to mining the deep-level correlation information between the stages, avoiding the limitations of analyzing the carbon emission data of each stage separately, and providing a richer information basis for accurately locating abnormal stages.

[0099] Then the carbon emission data of each stage and the carbon footprint network G are input into the pre-trained graph convolutional neural network to obtain the data anomaly stage, including:

[0100] S42-1, inputting the carbon emission data of several stages and the carbon footprint network G into the pre-trained graph convolutional neural network, the neural network model outputs the abnormal probability value of each node after the internal graph convolution operation, feature extraction and classification processing, and obtains the abnormal probability values ​​of several nodes;

[0101] S42-2, marking nodes whose abnormal probability values ​​exceed the preset probability as abnormal nodes. For example, in this embodiment, nodes whose abnormal probability values ​​exceed 0.5 are marked as abnormal nodes, and then the corresponding stage is obtained according to the abnormal nodes, that is, the data abnormality stage.

[0102] In S4, the construction process of the pre-trained graph convolutional neural network specifically includes:

[0103] Based on the PyTorch deep learning framework, select appropriate graph convolution layers, activation functions and other components to build the graph convolution model structure and obtain the graph convolution neural network;

[0104] Collect carbon emission data from multiple historical life cycles. For the carbon emission data at each stage in each cycle, mark them according to whether there are any abnormalities in the actual production process. For example, if there is an equipment failure in the smelting stage of a certain cycle, which causes a sudden and substantial increase in carbon emissions and exceeds the normal fluctuation range, the carbon emission data corresponding to the smelting stage will be marked as abnormal (1 can be used to indicate abnormality and 0 can be used to indicate normality), and several carbon emission data and corresponding marked data will be obtained;

[0105] Preprocess the collected carbon emission data and annotated data. Common preprocessing operations include data normalization, missing value processing, etc. Then, the preprocessed data is matched one-to-one with several nodes in the carbon footprint network to ensure that the data of each node at different time points can be accurately matched, so as to construct a model data set;

[0106] The model dataset is divided into training set, validation set and test set with a preset ratio of 7:2:1. At the same time, the loss function, training parameters (including learning rate, number of iterations, batch size, etc.) and optimization algorithm (such as AdamW optimization algorithm, which is used to update the weight parameters of the model to minimize the loss function) for graph convolution model training are set;

[0107] The graph convolution model is iteratively trained and validated using the training set and validation set. In each iteration, the data in the training set is input into the model, the loss value is calculated according to the loss function, and then the weight parameters of the model are updated through the optimization algorithm so that the model continuously fits the data. After each round of training, the model is validated with the validation set to evaluate the accuracy of the model on the validation set (such as accuracy, recall, precision, etc.), and the F1 value is used as the main accuracy indicator. The validation accuracy, that is, the model state when the F1 value is the highest, is recorded to obtain the graph convolution model with the highest validation accuracy;

[0108] Input the test set into the saved graph convolution model with the highest verification accuracy to obtain the test accuracy. Assuming the preset F1 threshold is 90%, that is, if the test accuracy is greater than 90%, it is considered that the model performance meets the requirements, and the optimal graph convolution model is output as the pre-trained graph convolution neural network; if the test accuracy is less than or equal to 90%, adjust the model's loss function (such as replacing it with another type of loss function), training parameters (such as adjusting the learning rate, increasing the number of iterations, etc.) and optimization algorithm, and then repeat iterative training and verification optimization until a pre-trained model that meets the accuracy requirements is obtained.

[0109] Convolutional neural network (GCNN) has powerful graph structure data processing capabilities. It can automatically learn the complex feature representation of nodes and edges in the carbon footprint network, and analyze by propagating information in the network and integrating the information of nodes and their neighboring nodes. Inputting carbon emission data and carbon footprint network into GCNN together fully utilizes the characteristics of GCNN, enabling it to better capture complex patterns in the data, thereby improving the accuracy of judging the abnormal stage of data.

[0110] After determining the abnormal stage in the copper product production process, we further analyze the relationship between the equipment to quickly locate the specific abnormal equipment, guide subsequent accurate and efficient maintenance and repair work, and effectively ensure the smooth operation of the production process and compliance control of carbon emissions.

[0111] Specifically, in S5, the energy consumption data and operation data of several devices in the data abnormality stage are first collected to obtain data sets of several devices; wherein the energy consumption data includes the degree of power consumption and fuel usage per unit time, and the operation data includes the average temperature, average voltage and average current of the equipment operation;

[0112] Then, the calculation formula of the Pearson correlation coefficient is used to calculate the correlation coefficient of each pair of devices in the data set to obtain the correlation matrix S; wherein the dimension of S is p×q, and Spq represents the correlation coefficient between the pth device and the qth device;

[0113] Further collect data on the normal operation phase of these devices during several historical production cycles of copper products to obtain historical normal data sets for several devices, and also classify and organize them according to the energy consumption and operation data of the corresponding devices. Then, based on these historical normal data sets, calculate the correlation coefficient between each pair of devices in the historical normal state according to the Pearson correlation coefficient calculation formula, and obtain several standard correlation coefficients. These standard correlation coefficients reflect the degree of correlation between the devices in the normal production process, and provide a reference standard for the subsequent determination of the correlation threshold of the current abnormal stage;

[0114] For each pair of equipment, the mean μ and standard deviation σ are calculated based on several calculated standard correlation coefficients, and then the correlation threshold of each pair of equipment is obtained as [μ-βσ,μ+βσ]; where k represents the preset adjustment coefficient, which is usually set to 2; since the production environment and equipment operating conditions have similarity and continuity to a certain extent, the statistical characteristics of historical normal data (mean and standard deviation) can help determine a reasonable correlation threshold range, which can reduce the interference of environmental fluctuations, short-term production changes and other factors on abnormal judgment, making the judgment of abnormal equipment more accurate;

[0115] Next, traverse each column of the correlation matrix S in turn. For the p-th column of data, compare each element (i.e., the correlation coefficient Spq between the p-th device and other devices) with the corresponding correlation threshold [μ-βσ,μ+βσ]. If the value of Spq is not within this threshold range, it is regarded as an abnormal data point. By comparing and judging each element one by one, the number of data in the p-th column that are not within the corresponding correlation threshold range is counted. This number is also the number of data with abnormal correlation between device p and other devices. It reflects, to a certain extent, the degree of abnormality of the device in the entire device association network;

[0116] Then, the number of abnormal data in the pth column is compared with the preset number threshold. Assume that the preset number threshold is 5, and there are 10 devices in total, that is, each device uses 10 correlation coefficients (including its own); if the number of abnormal data is greater than 5, then the device p is marked as an abnormal device; otherwise, continue to traverse the next column of data until the comparative analysis of all devices is completed, and all abnormal devices are identified, so as to accurately screen out the problematic devices from a large number of devices, and provide a clear target object for the subsequent targeted solution of abnormal problems in the production process.

[0117] Through the above correlation analysis process, it is possible to accurately determine which devices show deviations from normal operating conditions during the data anomaly stage. By traversing each column of the correlation matrix in turn, counting the number of data that are not within the correlation threshold range, and comparing it with the preset number threshold, it is possible to screen out the truly abnormal devices from the numerous devices, avoiding mistakenly marking the normal fluctuating devices as abnormal devices, and also reducing the possibility of missing abnormal devices.

[0118] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0119] Working principle of the present invention:

[0120] The present invention realizes the comprehensive collection of carbon footprint data of copper products by subdividing the production and processing life cycle of copper products into multiple stages, and realizing the real-time collection of carbon emission data of each stage with the help of sensor networks; then constructs a multivariate time series matrix, and uses dynamic mode decomposition technology to improve the efficiency and pertinence of data processing, and selects the dominant mode subset by calculating the modal energy, highlighting the key information in the data, and avoiding the information overload problem when processing large-scale and complex data; then reconstructs the data to calculate the anomaly score, realizes the overall early warning of carbon emission data, and then uses the carbon footprint network and graph convolutional neural network for precise positioning, and quickly narrows the investigation scope to a specific production stage; finally, the energy consumption and operation data of the equipment in the data abnormal stage are correlated, and the abnormal situation is discovered from the perspective of equipment collaboration, and the abnormal equipment is accurately identified; the present invention constructs a complete and efficient carbon emission data collection, processing, early warning and abnormal traceability system, which provides solid data support and technical guarantee for copper product manufacturers to accurately control carbon emission status and promote sustainable development.

[0121] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A method for collecting and processing carbon footprint data of copper products based on the entire life cycle, characterized in that: include: S1, divide the production and processing life cycle of copper products into several stages, and collect carbon emission data of the current life cycle through sensors to obtain carbon emission data of several stages; S2, construct a multivariate time series matrix X(t) according to the chronological order of the carbon emission data of several stages, decompose X(t) into dynamic modes, and obtain the dominant mode subset by calculating the modal energy of the dynamic modes; S3, using the dominant mode subset to obtain a reconstructed data sequence, calculating the anomaly score by comparing the reconstructed data sequence with X(t), and comparing whether the anomaly score is greater than a preset score threshold; If yes, jump to S4; If not, the next life cycle is marked as the current life cycle and the process jumps to S1; S4, constructing a carbon footprint network G according to several stages, inputting the carbon emission data of several stages and the carbon footprint network G into the pre-trained graph convolutional neural network to obtain the data abnormal stage; S5, collects energy consumption data and operation data of several devices in the data abnormality stage, and obtains several abnormal devices through correlation analysis.

2. The method for collecting and processing carbon footprint data of copper products based on the entire life cycle according to claim 1 is characterized in that: The multivariate time series matrix X(t) = [x1(t), x2(t), ..., xn(t)] T ; Where t represents time, xi(t) represents the carbon emissions of the i-th stage at time t, i = 1, 2, …, n, and n represents the number of stages.

3. The method for collecting and processing carbon footprint data of copper products based on the entire life cycle according to claim 1 is characterized in that: The method of obtaining the dominant mode subset by calculating the modal energy of the dynamic mode includes: S21, decomposing X(t) into a number of dynamic modes {Φm, λm} using a dynamic mode decomposition algorithm; wherein Φm represents a mode matrix, and λm represents a corresponding eigenvalue; S22, according to the formula Em=||Φm|| 2 Calculate the energy value Em of the dynamic mode and obtain several modal energies; where ||·|| represents the norm operation; S23, arranging the plurality of modal energies in descending order, and accumulating the sorted modal energies in sequence, calculating the ratio of the accumulated value to the sum of the modal energies, and when the ratio exceeds a preset threshold, screening out the corresponding plurality of modes to obtain a dominant modal subset.

4. The method for collecting and processing carbon footprint data of copper products based on the entire life cycle according to claim 1 is characterized in that: The abnormality score is obtained by reconstructing the data sequence and calculating X(t), including: S31, by formula Calculate the reconstructed data sequence in, represents the column vector of the jth modal matrix Φj in the dominant modal subset, λj represents the corresponding eigenvalue, bj is the coefficient vector determined by the initial conditions, and k represents the number of modes in the dominant modal subset; S32, calculating the difference between the reconstructed data sequence and X(t) at the corresponding time point to obtain a residual vector r(t); S33, calculate the standard deviation σ of the residual vector r(t) r , by the formula AS(t)=(||r(t)|| / σ r )×w(t) is used to calculate the anomaly score, where w(t) represents the dynamic weight.

5. The method for collecting and processing carbon footprint data of copper products based on the entire life cycle according to claim 4 is characterized in that: The method of obtaining bj includes: S31-1, construct the initial conditions with the multivariate time series matrix at the initial time t0 of the current life cycle, and obtain the initial conditions as follows: Where m represents the mode index, M represents the number of dynamic modes, represents the column vector of the modal matrix Φm, bm is the coefficient vector to be solved; S31-2, write the initial conditions in matrix form: X(t0) = Φb; where, b=[b1,b2,…,bm] T ; S31-3, solve according to the least squares method: b=(Φ T Φ) -1 Φ T X(t0), get the coefficient vector b; S31-4, obtain the corresponding coefficients in the coefficient vector b according to the dominant mode subset to obtain bj.

6. The method for collecting and processing carbon footprint data of copper products based on the entire life cycle according to claim 4 is characterized in that: The dynamic weight is obtained by: According to w(t) = α(1-α) t-t’ The dynamic weight is calculated by the formula; where α represents the attenuation coefficient, which is used to control the attenuation speed of the dynamic weight, and t' represents the current time.

7. The method for collecting and processing carbon footprint data of copper products based on the entire life cycle according to claim 1 is characterized in that: The carbon footprint network G is constructed according to several stages, including: S4-11, define several stages of the copper product production and processing life cycle as nodes of the carbon footprint network, and obtain several nodes; S4-12, defining the edges and weights of several nodes according to the material flow, energy flow and carbon emission transfer relationship between several stages, and obtaining several edges and weights of several edges; S4-13, according to the average carbon emissions of each stage and several equipment parameters, attribute information is added to several nodes of the carbon footprint network to obtain the carbon footprint network G(V,E,W); wherein V represents several nodes, E represents several edges, and W represents the weights of several edges.

8. The method for collecting and processing carbon footprint data of copper products based on the entire life cycle according to claim 1 is characterized in that: The step of inputting carbon emission data of several stages and the carbon footprint network G into the pre-trained graph convolutional neural network includes: S42-1, inputting the carbon emission data of several stages and the carbon footprint network G into the pre-trained graph convolutional neural network to obtain abnormal probability values ​​of several nodes; S42-2, marking nodes whose abnormal probability values ​​exceed preset probabilities as abnormal nodes, and obtaining corresponding data abnormal stages according to the abnormal nodes.

9. The method for collecting and processing carbon footprint data of copper products based on the entire life cycle according to claim 1 or 8, characterized in that: The construction process of the pre-trained graph convolutional neural network includes: S43-1, build and obtain graph convolution model based on deep learning algorithm; S43-2, collect carbon emission data of several historical life cycles, and mark the carbon emission data according to abnormal conditions in several stages, to obtain several carbon emission data and several marked data; S43-3, preprocessing a number of carbon emission data and a number of annotated data to obtain preprocessed data, and making a one-to-one correspondence between the preprocessed data and a number of nodes in the carbon footprint network to obtain a model data set; S43-4, dividing the model data set into a training set, a validation set, and a test set according to a preset ratio, and setting a loss function, training parameters, and optimization algorithm for graph convolution model training; S43-5, use the training set and the validation set to iteratively train and validate the graph convolution model, and save the graph convolution model with the highest validation accuracy to obtain the optimal graph convolution model; S43-6, input the test set into the optimal graph convolution model, obtain the test accuracy, and determine whether the test accuracy is greater than the preset accuracy threshold; if yes, output the optimal graph convolution model as a pre-trained graph convolution neural network; if not, adjust the model's loss function, training parameters and optimization algorithm, and jump to S43-5.

10. The method for collecting and processing carbon footprint data of copper products based on the entire life cycle according to claim 1 is characterized in that: The correlation analysis yields several abnormal devices, including: S5-1, collecting energy consumption data and operation data of several devices during the data abnormality stage to obtain data sets of several devices; wherein the energy consumption data includes the degree of power consumption and fuel usage per unit time, and the operation data includes the average temperature, average voltage and average current of the equipment operation; S5-2, using the calculation formula of the Pearson correlation coefficient, calculate the correlation coefficient of each pair of devices in the data set to obtain a correlation matrix S; wherein the dimension of S is p×q, and Spq represents the correlation coefficient between the p-th device and the q-th device; S5-3, collecting historical normal data sets of several devices in the data abnormality stage, and calculating several standard correlation coefficients based on the historical normal data sets; S5-4, calculating the mean μ and standard deviation σ of several standard correlation coefficients of each pair of devices, and obtaining the correlation threshold of each pair of devices as [μ-βσ,μ+βσ] according to the mean μ and standard deviation σ; wherein k represents a preset adjustment coefficient; S5-5, traverse each column of the correlation matrix S in turn, count the number of data in the p-th column that are not within the corresponding correlation threshold range, and obtain the number of abnormal data; S5-6, determine whether the number of abnormal data in the p-th column is greater than a preset number threshold; if yes, mark the device p as an abnormal device; if no, continue to traverse the next column of data.

Images