CN115222214A - Carbon emission verification method, device, electronic equipment and storage medium - Google Patents
Carbon emission verification method, device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN115222214A CN115222214A CN202210731084.0A CN202210731084A CN115222214A CN 115222214 A CN115222214 A CN 115222214A CN 202210731084 A CN202210731084 A CN 202210731084A CN 115222214 A CN115222214 A CN 115222214A
- Authority
- CN
- China
- Prior art keywords
- carbon emission
- value
- data
- carbon
- coal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/80—Management or planning
- Y02P90/84—Greenhouse gas [GHG] management systems
Abstract
The application provides a carbon emission verification method, a carbon emission verification device, electronic equipment and a storage medium, and relates to the field of carbon emission monitoring, wherein the method comprises the following steps: acquiring enterprise data; the enterprise data at least comprises coal quality, heat supply quantity and power generation quantity; calculating a carbon emission characteristic value according to the carbon emission characteristic association relation and the enterprise data by the target mechanism model; and fitting the target prediction model based on the carbon emission characteristic value to obtain a carbon emission parameter interval. By adopting the method provided by the application, the incidence relation among the carbon emission reported data can be constructed, each carbon emission parameter is coupled, and the mechanism model and the prediction model are combined to check the carbon emission data of the enterprise, so that the accuracy of the carbon emission data is improved.
Description
Technical Field
The application relates to the field of carbon emission monitoring, in particular to a carbon emission verification method, a carbon emission verification device, electronic equipment and a storage medium.
Background
For carbon emission enterprises, in order to achieve the carbon emission reduction target of carbon peak and carbon neutralization so as to protect the meteorological environment, decisions need to be made on the aspect of carbon emission planning to reduce the carbon emission of the enterprises. In formulating a carbon emission plan, calculations of carbon quota and carbon tax are required based on enterprise production data. In addition, the data fields for reporting the carbon emission by the enterprise are more, and a large amount of reports are difficult to report in an error mode, so that the calculation of the carbon quota and the carbon tax is influenced. Therefore, the problems that the correlation relationship among the carbon emission parameters is difficult to determine and the accurate real carbon emission of the enterprise is difficult to accurately predict exist.
Disclosure of Invention
Based on the above, an object of the embodiments of the present application is to provide a carbon emission verification method, a carbon emission verification device, an electronic device, and a storage medium, in which correlation between carbon emission report data is mined, and each carbon emission parameter is coupled on the basis of big data, so as to calculate an interval of a reasonable value of carbon emission, and provide data support for formulating a carbon emission plan.
In a first aspect, an embodiment of the present application provides a carbon emission verification method, including:
acquiring enterprise data; the enterprise data at least comprises coal quality, heat supply quantity and power generation quantity;
calculating a carbon emission characteristic value according to the carbon emission characteristic association relation and the enterprise data by the target mechanism model;
and fitting a target prediction model based on the carbon emission characteristic value to obtain a carbon emission parameter interval.
In the implementation process, the incidence relation among the carbon emission filling data can be constructed, each carbon emission parameter is coupled, and the carbon emission data of an enterprise is checked by combining a mechanism model and a prediction model, so that the accuracy of the carbon emission data is improved.
Optionally, the carbon emission characteristic values may include carbon emission derived characteristics and fruit characteristics;
before the calculating, by the target mechanistic model, the carbon emission derived feature from the carbon emission feature correlations and the enterprise data, the method may further comprise:
constructing the carbon emissions-derived signature based on a plurality of causal signatures;
constructing a feature association relation in an initial mechanism model based on the screened cause features and the screened effect features, taking a plurality of historical enterprise data as the input of the initial mechanism model, extracting the cause features from the historical enterprise data, calculating to obtain the value of the effect features based on the feature association relation, and determining the deviation between the value of the effect features and the actual value;
and respectively storing the historical enterprise data and the corresponding deviation between the value of the carbon emission derived characteristic and the value of the effect characteristic and the real value to form the target mechanism model.
Optionally, the carbon emission derived characteristics may include coal quality derived characteristics and conversion efficiency derived characteristics, as the characteristics may include low calorific value, as-received carbon content, coupled coal quality, coal amount, power generation, and carbon oxidation rate and heat supply ratio;
the constructing the carbon emission derived signature based on the plurality of cause signatures may comprise:
constructing coal derived characteristics according to a low calorific value and a received base carbon content in a coal burning process, wherein the coal derived characteristics are the distance of each coal characteristic point in a coordinate system of the low calorific value and the received base carbon content;
and constructing conversion efficiency derivative characteristics according to the coupled coal quality, the coal quantity, the power generation amount, the carbon oxidation rate and the heat supply ratio in the coal burning process.
In the implementation process, the characteristic parameters in the carbon emission process can be modeled in a mechanism mode, corresponding characteristics are calculated and derived through basic characteristics, and the characteristics are compared with historical data of enterprises, so that the characteristic data can comprehensively represent the carbon emission process, and the accuracy and the reliability of the data can be improved.
Optionally, before the fitting of the carbon emission parameter interval based on the carbon emission derived feature by the target prediction model, the method may comprise:
screening samples from historical enterprise data obtained by calculation of the initial mechanism model and corresponding characteristic samples, and taking the screened samples as training samples of the initial prediction model;
and training the initial prediction model based on the training samples to obtain the target prediction model when training is completed.
Optionally, the training the initial prediction model based on the training samples may include:
for the factor features in the training samples, fitting out a corresponding probability density curve based on kernel density estimation, and determining a value interval of the factor features based on a preset confidence value;
determining a relation straight line of the received base carbon content and the low heating value based on linear regression for the coal derived characteristics in the carbon emission derived characteristics, and determining the distance of the coal characteristic point corresponding to each training sample;
and for the conversion efficiency derivative characteristics in the carbon emission derivative characteristics, fitting according to the conversion efficiency corresponding to each training sample to obtain a function of the installed capacity, the unit calorific value carbon content and the type of the press set.
In the implementation process, the prediction model can be trained by combining two modes of supervised learning and unsupervised learning, so that the trained target training model can be correspondingly predicted and calculated according to different characteristics, and the robustness of the prediction model and the accuracy of carbon emission verification can be improved.
Optionally, the fitting of the target prediction model to the carbon emission parameter interval based on the carbon emission characteristic value may include:
and receiving the carbon emission characteristic value calculated by the target mechanism model, judging whether the carbon emission characteristic value is in a reasonable interval or not based on data of a training sample, if so, fitting based on the carbon emission characteristic value to obtain a carbon emission parameter interval, and otherwise, returning an unreasonable characteristic value.
In the implementation process, the data reasonability can be judged before the characteristic value is calculated, the calculation process is ended in advance when the data is unreasonable, and the verification is performed after the data is determined to be reasonable, so that the calculation efficiency can be improved, and the calculation resources are saved.
Optionally, before the fitting of the target prediction model to the carbon emission parameter interval based on the carbon emission characteristic value, the method may further include:
performing data cleaning on the enterprise data;
and if the data in the enterprise data are determined to be missing, filling the missing data based on the median value of the data.
In the implementation process, data can be cleaned and filled, certain characteristic missing values can be intelligently filled, samples meeting the mechanism model are screened out, and accordingly data reliability can be improved.
In a second aspect, embodiments of the present application provide a carbon emission verification apparatus, which may include:
the acquisition module is used for acquiring enterprise data; wherein the enterprise data at least comprises coal quality, heat supply amount and power generation amount.
And the first prediction module is used for calculating the carbon emission characteristic value according to the carbon emission characteristic incidence relation and the enterprise data by the target mechanism model.
And the second prediction module is used for obtaining a carbon emission parameter interval by the target prediction model based on the fitting of the carbon emission characteristic value.
Optionally, the carbon emission characteristics may include carbon emission derived and fruit characteristics.
The first prediction module may be further operable to construct a carbon emission derived signature based on a plurality of factor signatures prior to calculating the carbon emission derived signature from a target mechanistic model based on a carbon emission signature correlation and the enterprise data; constructing a feature association relation in an initial mechanism model based on the screened cause features and the screened effect features, taking a plurality of historical enterprise data as the input of the initial mechanism model, extracting the cause features from the historical enterprise data, calculating to obtain the value of the effect features based on the feature association relation, and determining the deviation between the value of the effect features and the actual value; and respectively saving the historical enterprise data and the corresponding deviation between the values of the carbon emission derived characteristics and the fruit characteristics and the real values to form the target mechanism model.
Optionally, the first prediction module may be specifically configured to, for the characteristics including low calorific value, on-demand carbon content, coupled coal quality, coal quantity, power generation and carbon oxidation rate, and heat supply ratio, and the carbon emission derived characteristics may include coal derived characteristics and conversion efficiency derived characteristics:
constructing coal derived characteristics according to a low calorific value and a received base carbon content in a coal burning process, wherein the coal derived characteristics are the distance of each coal characteristic point in a coordinate system of the low calorific value and the received base carbon content; and constructing conversion efficiency derivative characteristics according to the coupled coal quality, the coal quantity, the power generation amount, the carbon oxidation rate and the heat supply ratio in the coal burning process.
Optionally, the second prediction module may be further operable to:
screening samples from historical enterprise data obtained by calculation of the initial mechanism model and corresponding characteristic samples, and taking the screened samples as training samples of the initial prediction model; and training the initial prediction model based on the training samples to obtain the target prediction model when the training is completed.
Optionally, the second prediction module may be specifically configured to:
for the factor features in the training samples, fitting out a corresponding probability density curve based on kernel density estimation, and determining a value interval of the factor features based on a preset confidence value; determining a relation straight line of the received base carbon content and the low heating value based on linear regression for the coal derived characteristics in the carbon emission derived characteristics, and determining the distance of the coal characteristic point corresponding to each training sample; and for the conversion efficiency derivative characteristics in the carbon emission derivative characteristics, fitting according to the conversion efficiency corresponding to each training sample to obtain a function of the installed capacity, the unit calorific value carbon content and the type of the press set.
Optionally, the second prediction module may be further operable to:
and receiving a carbon emission characteristic value calculated by the target mechanism model, judging whether the carbon emission characteristic value is in a reasonable interval or not based on data of training samples, if so, fitting based on the carbon emission characteristic value to obtain a carbon emission parameter interval, and otherwise, returning an unreasonable characteristic value.
Optionally, the carbon emission verification apparatus may further include a preprocessing module, configured to perform data cleaning on the enterprise data; and if the data in the enterprise data are determined to be missing, filling the missing data based on the median value of the data.
In a third aspect, an embodiment of the present application provides an electronic device, where the electronic device includes a memory and a processor, where the memory stores program instructions, and the processor executes the steps in any one of the foregoing implementation manners when reading and executing the program instructions.
In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, where computer program instructions are stored in the computer-readable storage medium, and when the computer program instructions are read and executed by a processor, the steps in any of the foregoing implementation manners are performed.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments of the present application will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and that those skilled in the art can also obtain other related drawings based on the drawings without inventive efforts.
FIG. 1 is a schematic illustration of a carbon emission verification method provided in an embodiment of the present application;
FIG. 2 is a schematic diagram of a carbon emission verification process provided by an embodiment of the present application;
FIG. 3 is a schematic diagram illustrating the steps of mechanism modeling provided by an embodiment of the present application;
FIG. 4 is a schematic illustration of steps provided in an embodiment of the present application for constructing a carbon emissions-derived feature;
FIG. 5 is a diagram illustrating a linear relationship between a lower calorific value and a carbon content of a received base and a distribution of the lower calorific value and the carbon content of the received base according to an embodiment of the present disclosure;
FIG. 6 is a schematic diagram illustrating steps of predictive model training provided in an embodiment of the present application;
FIG. 7 is a schematic diagram of an alternative model training procedure provided in an embodiment of the present application;
FIG. 8 is a schematic diagram illustrating a step of preprocessing data according to an embodiment of the present application;
fig. 9 is a schematic diagram of a carbon emission verification apparatus provided in an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application. For example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions. In addition, the functional modules in the embodiments of the present invention may be integrated together to form an independent part, or each module may exist alone, or two or more modules may be integrated to form an independent part.
In the research process, the applicant finds that the current carbon emission monitoring methods of enterprises mainly comprise two methods, one is to directly detect the carbon emission based on sensor data, and the other is to judge the carbon emission of the enterprises based on material conservation, namely through the coal quality and the coal quantity. In the first approach, the solution based on sensor measurements is highly dependent on the reliability of the sensor and requires that both the flow and concentration quantities be monitored simultaneously and then the carbon emissions calculated. If any sensor is abnormal, the measured data has larger error, the actual emission value is larger than the monitored value and is not beneficial to realizing the double-carbon target, and the actual emission value is smaller than the monitored carbon emission value, so that some economic burden is brought to enterprises.
In the second approach, carbon emissions based on conservation of materials and energy need to take into account more parameters such as the amount of coal fired, the amount of carbon received as base, and the lower calorific value of the coal. In addition, the enterprise may use fuel such as gas and fuel oil as auxiliary energy, so the way of calculating the carbon emission is more complicated.
Therefore, an embodiment of the present application provides a carbon emission verification method, which determines an association relationship of carbon emission parameters by using a mechanism model, and verifies carbon emission data of an enterprise by combining a deep learning model, referring to fig. 1, where fig. 1 is a schematic diagram of steps of the carbon emission verification method provided in the embodiment of the present application, and the steps of the carbon emission verification method may include:
in step S11, enterprise data is acquired.
The enterprise data can comprise coal quality, heat supply quantity and power generation quantity, and other related parameter fields such as enterprise ID, installed capacity, equipment operation hours, heat supply ratio, power supply quantity, heat supply quantity, coal consumption, carbon content of unit heat value, low heating value, outsourcing electric quantity, power grid emission factor and other parameters can be included in the practical application process.
The carbon emission enterprises can include petrochemical enterprises, chemical enterprises, building material enterprises, steel enterprises, colored enterprises, paper-making enterprises, electric power enterprises and aviation enterprises. In the embodiment of the present application, an electric power enterprise, i.e., a power plant, is used as a carbon emission enterprise to describe the scheme in the present application.
In step S12, a carbon emission characteristic value is calculated by the target mechanism model according to the carbon emission characteristic association relation and the enterprise data.
In step S13, a carbon emission parameter interval is obtained by fitting a target prediction model based on the carbon emission characteristic value.
Please refer to fig. 2 on the basis of fig. 1, fig. 2 is a schematic diagram of a carbon emission verification process provided in an embodiment of the present application, and the overall concept of the present application is mainly divided into three parts, in which the first part is to model data by a mechanism. By this step, other characteristics can be calculated from the underlying characteristics and compared with the data reported by the enterprise. And the second part is to combine big data of each enterprise, calculate the distribution situation of each feature and derived features based on the mechanism model and fit the distribution situation into a corresponding machine learning model. And the third part is to check that after new data is loaded, the model can automatically load a mechanism model to calculate relevant derived features, then the derived features and the relevant features are input into the machine learning model, the reasonability of each field presented by an enterprise is judged according to the models, and if the data is not reasonable, a corresponding reason is given. And matching reasonable distribution of the characteristics by the model according to a preset algorithm, further providing a reasonable distribution interval of the above parameters, and calculating an interval of a reasonable carbon emission value by coupling the distribution.
In the embodiment of the present application, for step S12, the technical idea of the present application is to model data in a mechanism manner, specifically, other features may be calculated by a mechanism model based on basic features and compared with data reported by an enterprise, so that an embodiment of the present application provides an implementation manner of mechanism modeling, please refer to fig. 3 on the basis of fig. 1 and fig. 2, fig. 3 is a schematic diagram of a step of mechanism modeling provided by the embodiment of the present application, and the step of modeling may include:
in step S31, the carbon emission derived feature is constructed based on a plurality of causal features.
In the embodiment of the present application, taking an example that the carbon emission-derived feature includes a coal quality-derived feature and a conversion efficiency-derived feature as an example, please refer to fig. 4 on the basis of fig. 3, where fig. 4 is a schematic diagram of steps of constructing the carbon emission-derived feature provided in the embodiment of the present application, and the steps of constructing the carbon emission-derived feature may include:
step S311, constructing coal derived characteristics according to the low calorific value and the received base carbon content in the coal burning process, wherein the coal derived characteristics are the distance between each coal characteristic point in the coordinate system of the low calorific value and the received base carbon content.
Step S312, constructing conversion efficiency derivative characteristics according to the coupling coal quality, the coal quantity, the power generation amount, the carbon oxidation rate and the heat supply ratio in the coal burning process.
In the embodiment of the present application, two basic features selected for analyzing the coal quality are a low calorific value and a received base carbon content, please refer to fig. 5, where fig. 5 is a linear relationship between the low calorific value and the received base carbon content and a distribution schematic diagram of the low calorific value and the received base carbon content provided in the embodiment of the present application, and in an implementation process, a linear relationship between the low calorific value and the received base carbon content as shown in fig. 5 may be obtained by two-dimensionally plotting the above features, and a distance on the graph of each new point input into the mechanism model may be determined by a distance on the graph of each new point input into the mechanism model
To carry out the presentation of the contents,wherein x is 0 And y 0 And A and B are parameters of straight lines corresponding to the linear relation.
For the conversion efficiency derived characteristics, the embodiment of the application couples the basic characteristics of coal quality, coal quantity, power generation quantity, carbon oxidation rate, heat supply ratio and the like by
To obtain, wherein ele p For power generation, n is the type of fuel used, m i Mass of fuel used, r heats H _ lowheat as heat supply ratio i Is a low calorific value, x oxidei For carbon oxidation rate, eps is a correction parameter.
It should be understood that the steps for constructing the carbon emission derivative feature provided in the embodiment of the present application are not limited to the sequence shown in fig. 4, and in a specific implementation process, step S311 may be implemented first and then step S312 is implemented, step S312 may be implemented first and then step S311 is implemented, or one of step S311 and step S312 may be implemented alternatively.
In the embodiment of the application, a plurality of characteristic values in the carbon emission process can be coupled by constructing the derivative characteristics, the interval of the reasonable value of the carbon emission can be calculated by matching whether the characteristics are reasonably distributed, one derivative characteristic is generated by calculating a plurality of characteristics, analysis can be simplified and more dimensionality analysis results can be provided when the derivative characteristics are analyzed for rationality, and the accuracy of carbon emission accounting can be improved.
In step S32, a feature association relationship is constructed in an initial mechanism model based on the factor features and the fruit features that are screened, a plurality of historical enterprise data are used as inputs of the initial mechanism model, the factor features are extracted from the historical enterprise data, a value of the fruit features is obtained by calculation based on the feature association relationship, and a deviation between the value of the fruit features and a true value is determined.
In the embodiment of the application, the basis of mechanism model construction is to establish an association equation based on characteristics in a carbon emission process based on a physical and chemical conservation relation, specifically, enterprise data can be screened for cause characteristics and effect characteristics, characteristics and basic characteristics for accounting are screened, the basic characteristics and the mechanism model can be selected at will, and installed capacity, equipment operation hours, heat supply ratio, power supply quantity, heat supply quantity, coal consumption, carbon content of a unit calorific value, a low heating value, outsourcing electric quantity and power grid emission factors are taken as cause characteristics; the following description will be given by taking the discharge of outsourcing power carbon, the discharge of unit carbon dioxide, the discharge intensity of heat supply carbon, the discharge intensity of power supply carbon, fuel heat, heat supply coal consumption, heat supply gas consumption, the discharge of fossil fuel combustion carbon, the carbon content of unit heat value and the load rate as the effect characteristics.
A mechanism model is established through the selected correlation relationship of the characteristics on the physical chemistry, and an accounting characteristic (effect characteristic) can be calculated by means of the mechanism model and the basic characteristic, wherein the effect characteristic can be a randomly selected carbon emission process basic characteristic, the effect characteristic is a carbon emission process characteristic which has a causal correlation with the cause characteristic, for example, the installed capacity is selected as the cause characteristic, and the larger the installed capacity is, the higher the corresponding load rate is, so that the load rate can be used as an effect characteristic of the installed capacity. In addition, those skilled in the art should understand the correspondence relationship between the above factor characteristics and the effect characteristics, and the application scope thereof is not limited to the above embodiments, and those skilled in the art can apply the above factor characteristics and the effect characteristics to other specific scenarios without departing from the scope of the present invention after understanding the correspondence relationship and logic.
For example, the characteristic correlation equation established in the embodiment of the present application may include:
a. carbon emissions from fossil fuel combustion:
wherein n is the type of fuel used, m i Quality of fuel used, C i Is the carbon content of the fuel, x oxidei The carbon oxidation rate;
b. outsourcing power carbon emission: m is eleco2 ＝c ele γ, wherein, c ele The method is outsourcing power, and gamma is a power grid emission factor;
c. power supply and coal consumption:
the heat supply coal consumption is as follows:
wherein r is heats In terms of heat supply ratio, ele is power supply quantity, and eps is a correction parameter; m is i The coal is converted into standard coal for fuel consumption.
d. Power supply carbon emission intensity: ce fossico2 ＝m co2 *(1-r heats ) /(ele + eps), intensity of carbon emissions supplied: ch fossico2 ＝m co2 *(1-r heats ) /(ele + eps), where m co2 Carbon emissions;
e. carbon content per calorific value of fuel: mc of heat ＝(c_recivebase i )/h_lowheat i Wherein, c _ receivebase i Indicating the received base carbon content, h _ lowheat i Represents a lower calorific value;
f. heat of fuel: mc of heati ＝m i *h_lowwheat i *x oxidei ；
g. Load factor d load ＝ele p *T r *C load Wherein ele p For power generation, T r For hours of operation, C load Is the installed capacity.
And calculating to obtain a plurality of fruit characteristics corresponding to the factor characteristics through the established characteristic association relation, and obtaining deviation values of the fruit characteristics and corresponding data of the historical enterprise data.
In step S33, the historical enterprise data and the corresponding deviations of the values of the carbon emission derived features and the effect features from the real values are respectively saved to form the target mechanism model.
Therefore, the characteristic parameters in the carbon emission process are modeled in a mechanism mode, corresponding characteristics are calculated and derived through basic characteristics, and the characteristics are compared with historical data of enterprises, so that the characteristic data can comprehensively represent the carbon emission process, and the accuracy and the reliability of the data can be improved.
For step S13, an implementation manner of the prediction model training is further provided in the embodiment of the present application, please refer to fig. 6, where fig. 6 is a schematic diagram of the steps of the prediction model training provided in the embodiment of the present application, and the implementation manner of the prediction model training may include the following steps:
in step S61, a sample is screened from the historical enterprise data calculated by the initial mechanism model and the corresponding feature sample, and the screened sample is used as a training sample of the initial prediction model.
In step S62, the initial prediction model is trained based on the training samples to obtain the target prediction model when training is completed.
In the embodiment of the present application, the main purpose of the machine learning model is to record data of a historical sample, and continue to use the factor characteristics adopted in the above steps as an example to explain, before training the model, a model training sample needs to be determined. Therefore, the mode of screening the model training samples in the embodiment of the present application may be:
after the initial prediction model receives a plurality of characteristic values calculated by the initial mechanism model, deviation values of percentages of the characteristic values and historical data can be calculated, then, a corresponding deviation probability density curve is fit to be synthesized according to kernel density estimation, and a reasonable boundary range of the characteristic values is determined based on a preset confidence threshold value. The confidence threshold value can be set according to prior knowledge or actual conditions of enterprises, and can also be selected by using algorithms such as isolated forests or density clustering. And screening historical data of the enterprise through a confidence threshold value, and selecting appropriate data as a training sample of the initial prediction model.
After the training samples are selected, a training step for the initial prediction model may be performed, and for step S62, an alternative model training implementation is provided in the embodiment of the present application, please refer to fig. 7, where fig. 7 is a schematic diagram of an alternative model training step provided in the embodiment of the present application, and the step may include:
in step S621, for the cause features in the training samples, a corresponding probability density curve is fitted based on the kernel density estimation, and a value interval of the cause features is determined based on a preset confidence value.
In step S622, for the coal derived features in the carbon emission derived features, a relation straight line between the received base carbon content and the low calorific value is determined based on linear regression, and a distance of a coal feature point corresponding to each training sample is determined.
In step S623, for the conversion efficiency derivative characteristics in the carbon emission derivative characteristics, a function of installed capacity, carbon content per unit calorific value, and type of the press set is obtained according to the conversion efficiency fitting corresponding to each training sample.
The following is a specific description of training an initial prediction model in the embodiment of the present application, training on the model may be divided into two types, namely, supervised learning modeling and unsupervised modeling, and for received base carbon content, heat supply carbon emission intensity, power supply carbon emission intensity, heat supply coal consumption, power supply coal consumption and low heating value, a suitable probability density curve is fitted by using kernel density estimation, and then intervals with reasonable values are selected by setting reasonable confidence levels, and models such as isolated forests and density clusters can be selected for screening as required, so as to select reasonable model parameters.
For the derived characteristic distance, a straight line receiving the base carbon content and the lower heating value is obtained through linear regression, and parameters of the corresponding straight line are obtained. The distance from each sample to the straight line is calculated from the straight line and then processed in the same manner as in the above step.
For the derived feature conversion efficiency, a function of installed capacity, carbon content of a unit calorific value and a type of a press set can be firstly fit according to the conversion efficiency of a sample, and according to actual needs, a fitting process can be regressed by using models such as XGBoost, multilayer Perceptron (MLP) or multiple linear regression.
After the initial training model is trained through the plurality of characteristics to determine corresponding model parameters, a target training model which can be obtained through training in a file form and can complete training can be determined.
Therefore, the prediction model can be trained by combining two modes of supervised learning and unsupervised learning in the embodiment of the application, so that the trained target training model can perform corresponding prediction and calculation aiming at different characteristics, and the robustness of the prediction model and the accuracy of carbon emission accounting can be improved.
Before training the model by using the training sample, data may be preprocessed, please refer to fig. 8, where fig. 8 is a schematic diagram illustrating steps of preprocessing data provided in an embodiment of the present application, and the steps of preprocessing data may include:
in step S81, data cleansing is performed on the enterprise data.
In step S82, if it is determined that data in the enterprise data is missing, the missing data is filled based on the median value of the data.
The data may be cleaned by identifying possible error values or abnormal values through a statistical analysis method, or by checking data values with a simple rule base (common sense rule, business specific rule, etc.), or by using constraints between different attributes and external data to detect and clean the data. When the data are detected and the missing values exist, the missing data can be intelligently filled based on the median values of the characteristic values, and therefore samples meeting model training can be screened out.
In addition, the data are not limited to be preprocessed in the process of training the model, the data can be cleaned and filled in the mode before the historical data are used for constructing the mechanism model, and the abnormal condition can be screened and eliminated to ensure that the final carbon emission is calculated to be reasonable, so that the data reliability is improved.
In an optional embodiment, for the step of predicting to obtain the carbon emission parameter interval by using the target prediction model in step S13, the carbon emission characteristic value calculated by the target mechanism model may be received, and it is determined whether the carbon emission characteristic value is in a reasonable interval based on data of a training sample, if so, the carbon emission parameter interval is obtained based on the carbon emission characteristic value fitting, and if not, an unreasonable characteristic value is returned.
When a sample calculated by the target mechanism model is input into the target prediction model, parameters obtained by previous training are called, characteristics such as the content of base carbon, the emission intensity of heat supply carbon, the emission intensity of power supply carbon, the consumption of heat supply coal, the consumption of power supply coal, a low heating value and the like received in the machine learning model are checked, whether the analysis is reasonable or not is judged, and if the analysis is not reasonable, unreasonable characteristic items are returned for reason analysis.
And for the coal quality derivative characteristics, calculating the distance between the sample and the straight line by adopting the same method as the steps, judging whether the distance is reasonable, if so, returning information representing the reasonable coal quality, and if not, returning information representing the possible abnormality of the coal quality.
Similarly, comparing the conversion efficiency derivative characteristics obtained from the corresponding items in the input data with the result obtained by the mechanism model calculation, and if the difference is not large, determining that the difference is reasonable; and if the efficiency calculated by the mechanism model is far higher than the value calculated by the prediction model, verifying whether the low-level calorific value of the coal quality is abnormal, if so, considering that other fuels exist, and if so, returning corresponding abnormal information. In combination with the actual situation, there is generally no case where the efficiency of the mechanism model calculation is much lower than that of the prediction model calculation. Similarly, the lower calorific value and the corresponding lower calorific value carbon content can be adjusted through coupling so that the conversion efficiency is as close as possible to the conversion efficiency fitted by the prediction model, and then the correct carbon emission value can be obtained through regression by a mechanism model.
After the calculation process is carried out, the target prediction model can output corresponding accounting results, which can include a reasonable interval of coal quality, a reasonable interval of carbon emission, a result of derived feature calculation judgment, a reasonable interval of carbon dioxide emission and the like.
In summary, the carbon emission verification method provided by the embodiment of the application can construct the incidence relation among the carbon emission filling data, couple each carbon emission parameter, and verify the carbon emission data of the enterprise by combining the mechanism model and the prediction model, so that the accuracy of the carbon emission data can be improved.
Based on the same inventive concept, an embodiment of the present invention further provides a carbon emission testing apparatus 90, please refer to fig. 9, fig. 9 is a schematic diagram of the carbon emission testing apparatus provided in the embodiment of the present invention, and the carbon emission testing apparatus 90 may include:
an obtaining module 91, configured to obtain enterprise data; wherein the enterprise data at least comprises coal quality, heat supply amount and power generation amount.
And the first prediction module 92 is used for calculating a carbon emission characteristic value according to the carbon emission characteristic association relation and the enterprise data by the target mechanism model.
And a second prediction module 93, configured to fit the target prediction model based on the carbon emission characteristic value to obtain a carbon emission parameter interval.
Therefore, the embodiment of the application can couple all carbon emission parameters by constructing the incidence relation among the carbon emission reported data and check the carbon emission data of an enterprise by combining the mechanism model and the prediction model, thereby improving the accuracy of the carbon emission data.
Optionally, the carbon emission characteristic value may include a carbon emission derived characteristic value and a fruit characteristic value.
The first prediction module 92 may be further configured to construct a carbon emission derivative signature based on a plurality of factor signatures prior to calculating the carbon emission derivative signature from the target mechanistic model based on the carbon emission signature correlations and the enterprise data; constructing a feature association relation in an initial mechanism model based on the screened cause features and the screened effect features, taking a plurality of historical enterprise data as the input of the initial mechanism model, extracting the cause features from the historical enterprise data, calculating to obtain the value of the effect features based on the feature association relation, and determining the deviation between the value of the effect features and the actual value; and respectively saving the historical enterprise data and the corresponding deviation between the values of the carbon emission derived characteristics and the fruit characteristics and the real values to form the target mechanism model.
Alternatively, the first prediction module 92 may be specifically configured to:
constructing coal derived characteristics according to a low calorific value and a received base carbon content in a coal burning process, wherein the coal derived characteristics are the distance of each coal characteristic point in a coordinate system of the low calorific value and the received base carbon content; and constructing conversion efficiency derivative characteristics according to the coupled coal quality, the coal quantity, the power generation amount, the carbon oxidation rate and the heat supply ratio in the coal burning process.
Therefore, the characteristic parameters in the carbon emission process are modeled in a mechanism mode, the corresponding characteristics are calculated and derived through the basic characteristics, and the characteristics are compared with the historical data of enterprises, so that the characteristic data can comprehensively represent the carbon emission process, and the accuracy and the reliability of the data can be improved.
Optionally, the second prediction module 93 may be further configured to:
screening samples from historical enterprise data obtained by calculation of the initial mechanism model and corresponding characteristic samples, and taking the screened samples as training samples of the initial prediction model; and training the initial prediction model based on the training samples to obtain the target prediction model when training is completed.
Optionally, the second prediction module 93 may be specifically configured to:
for the factor features in the training samples, fitting out a corresponding probability density curve based on kernel density estimation, and determining a value interval of the factor features based on a preset confidence value; determining a relation straight line of the received base carbon content and the low heating value based on linear regression for the coal derived characteristics in the carbon emission derived characteristics, and determining the distance of the coal characteristic point corresponding to each training sample; and for the conversion efficiency derivative characteristics in the carbon emission derivative characteristics, fitting according to the conversion efficiency corresponding to each training sample to obtain a function of the installed capacity, the carbon content of the unit heat value and the type of the press set.
Therefore, the prediction model can be trained by combining two modes of supervised learning and unsupervised learning in the embodiment of the application, so that the trained target training model can be correspondingly predicted and calculated according to different characteristics, and the robustness of the prediction model and the accuracy of carbon emission verification can be improved.
Optionally, the second prediction module 93 may be further configured to:
and receiving the carbon emission characteristic value calculated by the target mechanism model, judging whether the carbon emission characteristic value is in a reasonable interval or not based on data of a training sample, if so, fitting based on the carbon emission characteristic value to obtain a carbon emission parameter interval, and otherwise, returning an unreasonable characteristic value.
Therefore, the data reasonability judgment can be carried out before the characteristic value is calculated, the calculation process is ended in advance when the data are unreasonable, and the verification step is carried out after the data are determined to be reasonable, so that the calculation efficiency can be improved, and the calculation resource can be saved.
Optionally, the carbon emission verification device 90 may further include a preprocessing module for performing data cleaning on the enterprise data; and if the data in the enterprise data are determined to be missing, filling the missing data based on the median value of the data.
Therefore, the data can be cleaned and filled, certain characteristic missing values can be filled intelligently, samples meeting a mechanism model are screened out, and accordingly data reliability can be improved.
Based on the same inventive concept, an embodiment of the present application further provides an electronic device, where the electronic device includes a memory and a processor, where the memory stores program instructions, and the processor executes the steps in any one of the above implementation manners when reading and executing the program instructions.
Based on the same inventive concept, embodiments of the present application further provide a computer-readable storage medium, where computer program instructions are stored, and when the computer program instructions are read and executed by a processor, the computer program instructions perform the steps in any of the above implementation manners.
The computer readable storage medium may be any of various media that can store program codes, such as a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read Only Memory (PROM), an Erasable Read Only Memory (EPROM), an electrically Erasable Read Only Memory (EEPROM), and the like. The storage medium is used for storing a program, and the processor executes the program after receiving an execution instruction.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described apparatus embodiments are merely illustrative, and for example, the division of the units into only one type of logical function may be implemented in other ways, and for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not implemented. In addition, the shown or discussed coupling or direct coupling or communication connection between each other may be through some communication interfaces, indirect coupling or communication connection between devices or units, and may be in an electrical, mechanical or other form.
In addition, units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional modules in the embodiments of the present application may be integrated together to form an independent part, or each module may exist alone, or two or more modules may be integrated to form an independent part.
Alternatively, all or part of the implementation may be in software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the invention to occur, in whole or in part.
The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.).
In this document, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising 8230; \8230;" comprises 8230; "does not exclude the presence of additional like elements in a process, method, article, or apparatus that comprises the element.
The above description is only an example of the present application and is not intended to limit the scope of the present application, and various modifications and changes may be made to the present application by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (10)
1. A carbon emission verification method, comprising:
acquiring enterprise data; the enterprise data at least comprises coal quality, heat supply quantity and power generation quantity;
calculating a carbon emission characteristic value according to the carbon emission characteristic association relation and the enterprise data by the target mechanism model;
and fitting the target prediction model based on the carbon emission characteristic value to obtain a carbon emission parameter interval.
2. The method of claim 1, wherein the carbon emission characteristics comprise carbon emission derived characteristics and fruit characteristics;
before the calculating, by the target mechanistic model, a carbon emission derivative signature from the carbon emission signature correlation and the enterprise data, the method further comprises:
constructing the carbon emission derived signature based on a plurality of cause signatures;
constructing a feature association relation in an initial mechanism model based on the screened cause features and the screened effect features, taking a plurality of historical enterprise data as the input of the initial mechanism model, extracting the cause features from the historical enterprise data, calculating to obtain the value of the effect features based on the feature association relation, and determining the deviation of the value of the effect features and the actual value;
and respectively storing the historical enterprise data and the corresponding deviation between the value of the carbon emission derived characteristic and the value of the effect characteristic and the real value to form the target mechanism model.
3. The method of claim 2, wherein the cause characteristics include lower calorific value, carbon content of received coal, coupled coal quality, coal amount, power generation amount, and carbon oxidation rate and heat supply ratio; the carbon emission derived features include coal derived features and conversion efficiency derived features;
said constructing said carbon emission derived signature based on a plurality of said cause signatures comprises:
constructing coal derived characteristics according to a low calorific value and a carbon content of a received base in a coal burning process; wherein the coal derived characteristic is the distance of each coal characteristic point in the coordinate system of the low calorific value and the received carbon content;
and constructing conversion efficiency derivative characteristics according to the coupled coal quality, the coal quantity, the power generation amount, the carbon oxidation rate and the heat supply ratio in the coal burning process.
4. The method of claim 1, wherein prior to the step of deriving from the target prediction model a carbon emission parameter interval based on the carbon emission-derived feature fit, the method comprises:
screening samples from historical enterprise data obtained by calculation of the initial mechanism model and corresponding characteristic samples, and taking the screened samples as training samples of the initial prediction model;
and training the initial prediction model based on the training samples to obtain the target prediction model when the training is completed.
5. The method of claim 4, wherein the training the initial predictive model based on the training samples comprises:
for the factor features in the training samples, fitting out a corresponding probability density curve based on kernel density estimation, and determining a value interval of the factor features based on a preset confidence value;
determining a relation straight line of the received base carbon content and the low heating value based on linear regression for the coal derived characteristics in the carbon emission derived characteristics, and determining the distance of the coal characteristic point corresponding to each training sample;
and for the conversion efficiency derivative characteristics in the carbon emission derivative characteristics, fitting according to the conversion efficiency corresponding to each training sample to obtain a function of the installed capacity, the unit calorific value carbon content and the type of the press set.
6. The method of claim 1, wherein the obtaining a carbon emission parameter interval from a target prediction model based on the fit of carbon emission characteristic values comprises:
and receiving the carbon emission characteristic value calculated by the target mechanism model, judging whether the carbon emission characteristic value is in a reasonable interval or not based on data of a training sample, if so, fitting based on the carbon emission characteristic value to obtain a carbon emission parameter interval, and otherwise, returning an unreasonable characteristic value.
7. The method of claim 1, wherein prior to said fitting by a target prediction model of a carbon emission parameter interval based on the carbon emission characteristic values, the method further comprises:
performing data cleaning on the enterprise data;
and if the data in the enterprise data are determined to be missing, filling the missing data based on the median value of the data.
8. A carbon emission verification device, comprising:
the acquisition module is used for acquiring enterprise data; the enterprise data at least comprises coal quality, heat supply quantity and power generation quantity;
the first prediction module is used for calculating a carbon emission characteristic value according to the carbon emission characteristic association relation and the enterprise data by a target mechanism model;
and the second prediction module is used for obtaining a carbon emission parameter interval by the target prediction model based on the fitting of the carbon emission characteristic value.
9. An electronic device comprising a memory having stored therein program instructions and a processor that, when executed, performs the steps of the method of any of claims 1-7.
10. A computer-readable storage medium, having stored thereon computer program instructions, which, when executed by a processor, perform the steps of the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210731084.0A CN115222214A (en) | 2022-06-24 | 2022-06-24 | Carbon emission verification method, device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210731084.0A CN115222214A (en) | 2022-06-24 | 2022-06-24 | Carbon emission verification method, device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115222214A true CN115222214A (en) | 2022-10-21 |
Family
ID=83610102
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210731084.0A Pending CN115222214A (en) | 2022-06-24 | 2022-06-24 | Carbon emission verification method, device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115222214A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116827971A (en) * | 2023-08-29 | 2023-09-29 | 北京国网信通埃森哲信息技术有限公司 | Block chain-based carbon emission data storage and transmission method, device and equipment |
| CN117808497A (en) * | 2024-03-01 | 2024-04-02 | 清华四川能源互联网研究院 | Electric power carbon emission abnormity detection module and method based on distance and direction characteristics |
-
2022
- 2022-06-24 CN CN202210731084.0A patent/CN115222214A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116827971A (en) * | 2023-08-29 | 2023-09-29 | 北京国网信通埃森哲信息技术有限公司 | Block chain-based carbon emission data storage and transmission method, device and equipment |
| CN116827971B (en) * | 2023-08-29 | 2023-11-24 | 北京国网信通埃森哲信息技术有限公司 | Block chain-based carbon emission data storage and transmission method, device and equipment |
| CN117808497A (en) * | 2024-03-01 | 2024-04-02 | 清华四川能源互联网研究院 | Electric power carbon emission abnormity detection module and method based on distance and direction characteristics |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115222214A (en) | Carbon emission verification method, device, electronic equipment and storage medium | |
| US9995655B2 (en) | Assessment of power system equipment for equipment maintenance and/or risk mitigation | |
| JP4237610B2 (en) | Maintenance support method and program | |
| CN106471475B (en) | Improving future reliability predictions based on system operation and performance data modeling | |
| US10444121B2 (en) | Fault detection using event-based predictive models | |
| KR101044744B1 (en) | Operating ? Maintenance System and Method for Power Distribution System Facility Based on Reliability | |
| CN104966141A (en) | Industrial asset health model update | |
| KR101358673B1 (en) | Facilities condition assessment method using smartphone and system thereof | |
| MX2014003947A (en) | Systems and methods for subsurface oil recovery optimization. | |
| CN115952081A (en) | Software testing method, device, storage medium and equipment | |
| Sharma et al. | Hybrid Software Reliability Model for Big Fault Data and Selection of Best Optimizer Using an Estimation Accuracy Function | |
| CN117611190A (en) | Regional power system carbon emission measuring and calculating method, device and medium | |
| CN111931323B (en) | Memory, hydrocracking equipment fault prediction method, device and equipment | |
| CN112308338A (en) | Power data processing method and device | |
| KR102647438B1 (en) | Method for analysis of root cause of chemical processes and method for modeling of yield prediction | |
| Zantek et al. | A decision dependent stochastic process model for repairable systems with applications | |
| CN116957306B (en) | User side response potential evaluation method and system based on resource collaborative interaction | |
| US20220307945A1 (en) | Analysis apparatus, analysis method and computer readable medium | |
| CN117272844B (en) | Method and system for predicting service life of distribution board | |
| Abdurakipov | Increasing the efficiency of electric submersible pumps by using big data processing and machine learning technologies | |
| JP6859381B2 (en) | State change detection device and state change detection program | |
| He et al. | Software component reliability evaluation method based on characteristic parameters | |
| JP6932467B2 (en) | State change detection device, state change detection system and state change detection program | |
| CN117290734A (en) | Machine room energy efficiency analysis method and system based on Internet of things | |
| Carlucci et al. | Data-centric Maintenance and Operational Knowledge and Its Impact on Classification |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |