CN116681187B - Enterprise carbon quota prediction method based on enterprise operation data - Google Patents
Enterprise carbon quota prediction method based on enterprise operation data Download PDFInfo
- Publication number
- CN116681187B CN116681187B CN202310968356.3A CN202310968356A CN116681187B CN 116681187 B CN116681187 B CN 116681187B CN 202310968356 A CN202310968356 A CN 202310968356A CN 116681187 B CN116681187 B CN 116681187B
- Authority
- CN
- China
- Prior art keywords
- carbon emission
- enterprise
- process flow
- carbon
- model
- 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.)
- Active
Links
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 title claims abstract description 349
- 229910052799 carbon Inorganic materials 0.000 title claims abstract description 349
- 238000000034 method Methods 0.000 title claims abstract description 215
- 238000004519 manufacturing process Methods 0.000 claims abstract description 129
- 238000012544 monitoring process Methods 0.000 claims abstract description 113
- 230000009467 reduction Effects 0.000 claims abstract description 38
- 238000013135 deep learning Methods 0.000 claims abstract description 11
- 230000008569 process Effects 0.000 claims description 197
- 239000011159 matrix material Substances 0.000 claims description 31
- 238000011156 evaluation Methods 0.000 claims description 28
- 238000012549 training Methods 0.000 claims description 15
- 239000000446 fuel Substances 0.000 claims description 10
- 230000006870 function Effects 0.000 claims description 9
- 238000012360 testing method Methods 0.000 claims description 9
- 230000008901 benefit Effects 0.000 claims description 8
- 238000012417 linear regression Methods 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 3
- 230000001419 dependent effect Effects 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims description 3
- 238000009826 distribution Methods 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims description 3
- 238000000611 regression analysis Methods 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 3
- 230000007613 environmental effect Effects 0.000 abstract description 5
- 238000005516 engineering process Methods 0.000 description 5
- 238000003860 storage Methods 0.000 description 5
- MWUXSHHQAYIFBG-UHFFFAOYSA-N Nitric oxide Chemical compound O=[N] MWUXSHHQAYIFBG-UHFFFAOYSA-N 0.000 description 3
- 238000002485 combustion reaction Methods 0.000 description 3
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 2
- 238000010248 power generation Methods 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 229910002092 carbon dioxide Inorganic materials 0.000 description 1
- 239000001569 carbon dioxide Substances 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000003245 coal Substances 0.000 description 1
- 238000009833 condensation Methods 0.000 description 1
- 230000005494 condensation Effects 0.000 description 1
- 238000006477 desulfuration reaction Methods 0.000 description 1
- 230000023556 desulfurization Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000001704 evaporation Methods 0.000 description 1
- 239000003546 flue gas Substances 0.000 description 1
- 239000000295 fuel oil Substances 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 239000003345 natural gas Substances 0.000 description 1
- 239000003758 nuclear fuel Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000004064 recycling Methods 0.000 description 1
- 238000011946 reduction process Methods 0.000 description 1
- 238000003303 reheating Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000011282 treatment Methods 0.000 description 1
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
- G06Q10/04—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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/088—Non-supervised learning, e.g. competitive learning
-
- 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
- G06Q10/067—Enterprise or organisation modelling
-
- 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
- G06Q30/00—Commerce
- G06Q30/018—Certifying business or products
-
- 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—Information and communication technology [ICT] specially adapted for implementation of business processes of 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Biomedical Technology (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Quality & Reliability (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Primary Health Care (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
An enterprise carbon quota prediction method based on enterprise operation data relates to the technical field of data prediction, carbon emission monitoring points are set in the production process of an enterprise according to production process flow information and historical production data information of the enterprise, carbon emission monitoring data of all the monitoring points are collected, and an enterprise production carbon emission full-flow model is constructed; judging and generating fault early warning information of the enterprise production process flow according to the carbon emission monitoring data, constructing a fault early warning model, adding the fault early warning model to an enterprise production carbon emission full-flow model, realizing carbon emission anomaly tracing of the carbon emission full-flow, and adding a carbon emission prediction model through deep learning on the basis of the enterprise production carbon emission full-flow model and the fault early warning model; and predicting the carbon emission in the next monitoring period of the enterprise according to the carbon emission prediction model, predicting the carbon quota that the enterprise needs to purchase or sell in the next monitoring period, and helping the enterprise to better realize the environmental protection and emission reduction targets.
Description
Technical Field
The application relates to the technical field of data prediction, in particular to an enterprise carbon quota prediction method based on enterprise operation data.
Background
With the increasing environmental awareness and the increasing strictness of carbon emission management, the reduction of carbon emissions has become one of the key problems in the global scope, and in order to be able to better control the total amount of carbon emissions, many countries have promoted carbon trade markets, convert the carbon emissions rights of enterprises into trade-able commercial products, help to encourage enterprises to voluntarily reduce the carbon emissions to achieve the goal of sustainable development, and enterprises need to consider the carbon emissions limitation as one of the operational risks and consider the reduction and control of the carbon emissions during the operation. Carbon trade is one of the main current international environmental protection and emission reduction modes, and how to predict the carbon emission of a company and the demand for carbon quota are key points of successful strategic management of the company.
An enterprise needs to master an effective carbon quota prediction method based on enterprise operation data to reduce operation cost and better realize environmental protection and emission reduction targets, and the existing carbon quota prediction technology often lacks instantaneity and accuracy, cannot respond to changes of carbon emission in each process flow in the enterprise production flow in time, cannot monitor and track and analyze the carbon emission data in each process flow in real time, and is inaccurate in carbon emission prediction amount.
Disclosure of Invention
In order to solve the problems that the existing carbon quota prediction technology often lacks real-time performance and accuracy, cannot timely respond to the change of carbon emission in each process flow in an enterprise production flow, cannot monitor and track and analyze carbon emission data in each process flow in real time, the application aims to provide an enterprise carbon quota prediction method based on enterprise operation data, which comprises the following steps:
step S1: setting carbon emission monitoring points in the production process of an enterprise according to the production process flow information and the historical production data information of the enterprise, collecting carbon emission monitoring data of each monitoring point, marking the collection time, and setting a monitoring period;
step S2: acquiring enterprise operation data information of each monitoring point, and constructing an enterprise production carbon emission full-flow model through carbon emission monitoring data and enterprise operation data information of each monitoring point;
step S3: judging and generating fault early warning information of the enterprise production process flow according to the carbon emission monitoring data, constructing a fault early warning model, adding the fault early warning model to an enterprise production carbon emission full-flow model, realizing carbon emission anomaly tracing of the carbon emission full-flow, and adding a carbon emission prediction model through deep learning on the basis of the enterprise production carbon emission full-flow model and the fault early warning model;
step S4: predicting the carbon emission amount in the next monitoring period of the enterprise according to the carbon emission prediction model, and predicting the carbon quota which the enterprise needs to purchase or sell in the next monitoring period according to the predicted carbon emission amount and the historical carbon quota.
Further, setting carbon emission monitoring points in the production process of the enterprise according to the production process flow information and the historical production data information of the enterprise, and acquiring the carbon emission monitoring data of each monitoring point comprises the following steps:
acquiring the technological process characteristics of each production device of an enterprise, extracting technological process information according to the technological process characteristics, splitting the production process of the enterprise according to the technological process information, and dividing the production process into a plurality of technological process subsequences;
the historical production data information comprises historical carbon emission and historical production economic benefit of each process flow subsequence, an evaluation index is set according to process flow characteristics, the historical carbon emission and the historical production economic benefit in each process flow subsequence, an evaluation index weight is set, an evaluation index matrix is established according to the evaluation index and the evaluation index weight, preset importance levels related to each process flow subsequence are set, and a membership matrix representing fuzzy relation between each process flow subsequence and the preset importance levels is established;
obtaining importance levels of the process flow subsequences according to the membership matrix and the evaluation index matrix, comparing the importance levels of the process flow subsequences with corresponding preset importance levels, and setting carbon emission monitoring points in the process flow subsequences with the importance levels greater than the preset importance levels;
and acquiring the process flow characteristics and the historical carbon emission of the process flow subsequences with the importance level larger than the preset importance level, and determining the number of carbon emission monitoring points and the point taking distribution of the process flow subsequences by combining the importance level of the process flow subsequences.
Further, the process of obtaining the enterprise operation data information of each monitoring point location and constructing the enterprise production carbon emission whole-flow model through the carbon emission monitoring data and the enterprise operation data information of each monitoring point location comprises the following steps:
acquiring physical entity and position information of each production device of an enterprise in a physical space in an enterprise production process flow, constructing three-dimensional modeling for each production device of the enterprise, mapping the three-dimensional modeling to a digital space, and mapping an assembly connection relation of each production device of the enterprise in the physical space to the digital space;
and acquiring carbon emission monitoring data and enterprise operation data of each process flow subsequence in the enterprise production process, producing twin data according to the carbon emission monitoring data and the enterprise operation data of each process flow subsequence, and matching the twin data, the assembly connection relation of each production device of the enterprise with the three-dimensional model to generate an enterprise production carbon emission whole-flow model.
Further, judging and generating fault early warning information of the enterprise production process according to the carbon emission monitoring data, wherein the process of constructing the fault early warning model comprises the following steps:
setting a carbon emission threshold and a preset time threshold, and acquiring the accumulated time when the carbon emission monitoring data of the target process flow subsequence in the monitoring period is greater than the carbon emission threshold;
when the accumulated time is greater than a preset time threshold, generating a fault label on working condition data and carbon emission monitoring data of production equipment of the process flow subsequence;
constructing a fault early warning model based on an RBN neural network, constructing a historical data set according to historical working condition data with fault labels and historical carbon emission monitoring data in an enterprise production carbon emission full-flow model, dividing the historical data set into a training set and a testing set, performing real-time learning training on the fault early warning model through the training set until a loss function is stable in training, storing model parameters, and performing similarity verification on an output data matrix of the fault early warning model after iterative training through the testing set;
and inputting the working condition data and the carbon emission monitoring data of the production equipment of the process flow subsequence in the current monitoring period into a fault early-warning model verified by a test set, and acquiring fault early-warning information according to an output layer of the fault early-warning model.
Further, adding the fault early warning model to an enterprise production carbon emission full-flow model, and realizing the carbon emission anomaly traceability of the carbon emission full-flow comprises the following steps:
the method comprises the steps of adding a fault early-warning model into an enterprise production carbon emission full-flow model, respectively extracting time features and space features of fault early-warning information output by the fault early-warning model according to the enterprise production carbon emission full-flow model, generating a fault early-warning space-time feature sequence, carrying out fault tracing detection on a process flow subsequence according to the fault early-warning space-time feature sequence, and marking the state of the process flow subsequence as an abnormal state.
Further, the process of adding the carbon emission prediction model through deep learning on the basis of the enterprise carbon emission full-flow model and the fault early warning model comprises the following steps:
acquiring historical carbon emission of each process flow subsequence in a monitoring period under different enterprise operation data conditions, carrying out regression analysis by taking historical enterprise operation data of each process flow subsequence and process flow subsequence states as independent variables and taking the historical carbon emission of each process flow subsequence as the dependent variables, and constructing a multiple linear regression function representing between the enterprise carbon emission and the operation data;
inputting enterprise operation data of the process flow subsequence of the current monitoring period and the state of the process flow subsequence of the current monitoring period predicted by the fault early warning model into a multiple linear regression function to obtain the carbon emission variation trend characteristic of the process flow subsequence;
representing the assembly connection relation of all enterprise production equipment in the enterprise production carbon emission full-flow model and the three-dimensional model in a topological graph form, constructing a carbon emission prediction model based on a graph attention network, performing deep learning on the topological graph representation form by using the graph attention network, and guiding the carbon emission variation trend characteristics of all process flow subsequences into the graph attention network; and obtaining attention weights of the carbon emission of nodes of each topological graph to the carbon emission of other nodes of the topological graph through an attention mechanism, and distributing the attention weights to the nodes of each topological graph to complete the construction of a carbon emission prediction model.
Further, the process of predicting the carbon emission in the next monitoring period of the enterprise according to the carbon emission prediction model includes:
and inputting enterprise operation data of each process flow sub-sequence in the current monitoring period and the state of each process flow sub-sequence into a carbon emission prediction model to obtain the carbon emission prediction quantity and total carbon emission prediction quantity of each process flow sub-sequence in the next monitoring period and the influence coefficient of the carbon emission quantity of each process flow sub-sequence on the total carbon emission prediction quantity.
Further, predicting the carbon quota that the enterprise needs to purchase or sell in the next monitoring period according to the predicted carbon emission and the historical carbon quota includes:
determining the carbon quota demand of the next monitoring period according to the historical carbon quota, and comparing the total carbon emission predicted quantity generated by the carbon emission prediction model with the carbon quota demand;
if the total carbon emission predicted amount is lower than the carbon quota demand amount, selling redundant carbon quota to a carbon trade market to obtain additional economic benefit;
if the total carbon emission predicted amount is higher than the carbon quota demand amount, carrying out carbon emission reduction operation on enterprises, acquiring a carbon emission reduction allowable maximum value of each process flow sub-sequence, acquiring an influence coefficient of the carbon emission amount of each process flow sub-sequence on the total carbon emission predicted amount, arranging the process flow sub-sequences according to the influence coefficient from large to small to generate a carbon emission reduction sequence, firstly selecting a first process flow sub-sequence with the largest influence coefficient in the carbon emission reduction sequence, adjusting enterprise operation data of the process flow sub-sequence to carry out the carbon emission reduction operation, judging whether the total carbon emission predicted amount is higher than the carbon quota demand amount when the carbon emission reduction amount of the process flow sub-sequence reaches the carbon emission reduction allowable maximum value of the process flow sub-sequence, and if the total carbon emission predicted amount is higher than the carbon quota demand amount, selecting a second process flow sub-sequence in the carbon emission reduction sequence to repeat the carbon emission reduction operation until the total carbon emission predicted amount is lower than or equal to the carbon quota demand amount; and if the carbon emission reduction operation is finished by all the process flow subsequences in the carbon emission reduction sequence, the total carbon emission prediction amount is still higher than the carbon quota demand amount, and the carbon quota amount equal to the difference amount is purchased from the carbon trade market according to the difference amount of the total carbon emission prediction amount and the carbon quota demand amount at the moment.
Compared with the prior art, the application has the beneficial effects that: the fault early warning model is added to the enterprise production carbon emission full-flow model, so that the traceability of carbon emission abnormality of the carbon emission full-flow is realized, the carbon emission prediction model is added through deep learning on the basis of the enterprise production carbon emission full-flow model and the fault early warning model, the enterprise carbon quota prediction is carried out by combining historical static data of each process flow subsequence region and collected and accessed dynamic data, the visualization of the carbon emission control of each process flow subsequence in the enterprise production process is realized, the control precision of the carbon emission reduction process of each process flow subsequence in the enterprise production process is obviously improved, and the environmental protection and emission reduction targets of the enterprise are better realized.
Drawings
Fig. 1 is a schematic diagram of an enterprise carbon quota prediction method based on enterprise operation data according to an embodiment of the application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the present application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
As shown in fig. 1, an enterprise carbon quota prediction method based on enterprise operation data includes the following steps:
step S1: setting carbon emission monitoring points in the production process of an enterprise according to the production process flow information and the historical production data information of the enterprise, collecting carbon emission monitoring data of each monitoring point, marking the collection time, and setting a monitoring period;
step S2: acquiring enterprise operation data information of each monitoring point, and constructing an enterprise production carbon emission full-flow model through carbon emission monitoring data and enterprise operation data information of each monitoring point;
step S3: judging and generating fault early warning information of the enterprise production process flow according to the carbon emission monitoring data, constructing a fault early warning model, adding the fault early warning model to an enterprise production carbon emission full-flow model, realizing carbon emission anomaly tracing of the carbon emission full-flow, and adding a carbon emission prediction model through deep learning on the basis of the enterprise production carbon emission full-flow model and the fault early warning model;
step S4: predicting the carbon emission amount in the next monitoring period of the enterprise according to the carbon emission prediction model, and predicting the carbon quota which the enterprise needs to purchase or sell in the next monitoring period according to the predicted carbon emission amount and the historical carbon quota.
It should be further noted that, in the implementation process, the production process flow information of the enterprise includes:
the fuel supply flow comprises the following steps: the enterprise purchases, stores and distributes the quantity of fuel required by other production process flows of the enterprise, and the fuel used by the enterprise comprises, but is not limited to, fuel oil, natural gas, coal, nuclear fuel and the like; fuel combustion flow: combustion is a critical step in the generation of steam, which releases carbon dioxide and other gases that are released to the atmosphere through an exhaust conduit; the combustion power generation flow comprises the following steps: the energy of the fuel will be used to generate electricity, typically by driving a turbine with steam, which is cooled during turbine operation to produce electricity, so that various treatments such as reheating, re-evaporation, condensation, etc. are required before recycling; and the emission flow is reduced: in order to reduce carbon emissions, various enterprises have adopted different technologies to reduce emissions, such as flue gas desulfurization, nitrogen oxide emission reduction technologies, and carbon capture and storage technologies, transportation and storage: the transportation and storage flow is as follows: after the power generation is completed, the products are required to be stored and transported, and the transportation mode is to transmit the generated power to the market through a power transmission line; while the storage space may alternatively be stored in a variety of different ways, such as in a battery or other storage facility.
It should be further noted that, in the implementation process, the historical production data information of the enterprise includes: historical carbon emission and historical management data information of each process flow sub-sequence, wherein the historical management data comprises fuel consumption, yield, profit margin and the like of each process flow sub-sequence;
it should be further described that, in the specific implementation process, carbon emission monitoring points are set in the production process of the enterprise according to the production process flow information and the historical production data information of the enterprise, and the process of collecting the carbon emission monitoring data of each monitoring point comprises the following steps:
acquiring process flow characteristics of each production device of an enterprise, and extracting process flow information according to the process flow characteristics, wherein the process flow characteristics comprise the type of the production device used in the process flow, average fuel consumption and characteristic indexes of production steps of the production device; determining the technological process information according to the type of the production equipment used in the technological process, the average fuel consumption and the characteristic index of the production steps of the production equipment; splitting the enterprise production process according to the process flow information, and dividing the enterprise production process into a plurality of process flow subsequences;
the historical production data information comprises historical carbon emission and historical production economic benefit of each process flow subsequence, an evaluation index is set according to process flow characteristics, the historical carbon emission and the historical production economic benefit in each process flow subsequence, an evaluation index weight is set, an evaluation index matrix is established according to the evaluation index and the evaluation index weight, preset importance levels related to each process flow subsequence are set, and a membership matrix representing fuzzy relation between each process flow subsequence and the preset importance levels is established;
obtaining importance levels of the process flow subsequences according to the membership matrix and the evaluation index matrix, comparing the importance levels of the process flow subsequences with corresponding preset importance levels, and setting carbon emission monitoring points in the process flow subsequences with the importance levels greater than the preset importance levels;
it should be further noted that, in the specific implementation process, the process of obtaining the importance level of each process flow subsequence according to the membership matrix and the evaluation index matrix includes:
fusing the membership matrix with the evaluation index matrix to obtain a fuzzy comprehensive evaluation matrix about the importance level of each process flow subsequence;
substituting a plurality of sub-sequence data index information of each process flow in the enterprise production process into a fuzzy comprehensive evaluation matrix to obtain membership degrees of the sub-sequence data index information of each process flow with the importance grades of I, II, III and IV, and selecting the importance grade with the largest membership degree in the sub-sequence data index information of each process flow as the importance grade of each process flow sub-sequence;
wherein, the fusion formula of the membership matrix and the evaluation index matrix is as follows:
wherein,,for a fuzzy comprehensive evaluation matrix concerning the importance level of each process flow subsequence +.>For membership matrix>For evaluation index matrix, ">"means multiplication of elements at the corresponding positions of the membership matrix and the evaluation index matrix,">Is a weighting parameter for controlling the balance between the membership matrix and the evaluation index matrix in the fuzzy comprehensive evaluation matrix.
And acquiring the process flow characteristics and the historical carbon emission of the process flow subsequences with the importance level larger than the preset importance level, and determining the number of carbon emission monitoring points and the point taking distribution of the process flow subsequences by combining the importance level of the process flow subsequences.
It should be further noted that, in the implementation process, the process of acquiring the business data information and classifying the business data information includes:
the enterprise management data information comprises fuel consumption, yield, profit rate and the like of each process flow subsequence, a database is set for the management data information, the database comprises database sub-databases for storing enterprise management data of different types, category labels of the database sub-databases are obtained, a plurality of clustering centers are generated according to the category labels of the database sub-databases, the obtained enterprise management data are subjected to numerical processing to generate an enterprise management data set, euclidean distance between each enterprise management data in the enterprise management data set and each clustering center is calculated, a clustering center with the smallest Euclidean distance between the cluster center and the enterprise management data is selected, the category labels of the clustering centers are bound and associated with the enterprise management data, and the enterprise management data are distributed to the database sub-databases corresponding to the category labels.
It should be further described that, in the implementation process, the process of obtaining the enterprise operation data information of each monitoring point location and constructing the enterprise production carbon emission full-flow model through the carbon emission monitoring data and the enterprise operation data information of each monitoring point location includes:
acquiring physical entity and position information of each production device of an enterprise in a physical space in an enterprise production process flow, constructing three-dimensional modeling for each production device of the enterprise, mapping the three-dimensional modeling to a digital space, and mapping an assembly connection relation of each production device of the enterprise in the physical space to the digital space;
acquiring carbon emission monitoring data and enterprise operation data of each process flow subsequence in the enterprise production process, producing twin data according to the carbon emission monitoring data and the enterprise operation data of each process flow subsequence, and matching the twin data, the assembly connection relation of each production device of the enterprise and the three-dimensional model to generate an enterprise production carbon emission whole-flow model; the enterprise production carbon emission full-flow model realizes visualization of carbon emission control of each process flow subsequence and refined control of carbon emission of each process flow subsequence in the enterprise production process;
it should be further noted that, in the specific implementation process, the process of determining and generating the fault early-warning information of the enterprise production process according to the carbon emission monitoring data, and constructing the fault early-warning model includes:
setting a carbon emission threshold and a preset time threshold, and acquiring the accumulated time when the carbon emission monitoring data of the target process flow subsequence in the monitoring period is greater than the carbon emission threshold;
when the accumulated time is greater than a preset time threshold, generating a fault label on working condition data and carbon emission monitoring data of production equipment of the process flow subsequence;
constructing a fault early warning model based on an RBN neural network, constructing a historical data set according to historical working condition data with fault labels and historical carbon emission monitoring data in an enterprise production carbon emission full-flow model, dividing the historical data set into a training set and a testing set, performing real-time learning training on the fault early warning model through the training set until a loss function is stable in training, storing model parameters, and performing similarity verification on an output data matrix of the fault early warning model after iterative training through the testing set;
inputting working condition data and carbon emission monitoring data of production equipment of the process flow subsequence in the current monitoring period into a fault early-warning model verified by a test set, and acquiring fault early-warning information according to an output layer of the fault early-warning model;
the fault early warning model is used for predicting whether the production equipment of the process flow subsequence is faulty or not according to the working condition data and the carbon emission monitoring data of the production equipment of the process flow subsequence.
It should be further described that, in the specific implementation process, the fault early warning model is added to the enterprise production carbon emission full-flow model, and the process for implementing the carbon emission anomaly tracing of the carbon emission full-flow includes:
adding a fault early-warning model into an enterprise production carbon emission full-flow model, wherein the adding process is to enable an input layer of the fault early-warning model to be connected into each process flow subsequence output layer of the enterprise production carbon emission full-flow model, and after working condition data and carbon emission monitoring data of production equipment of each process flow subsequence of the output layer in the enterprise production carbon emission full-flow model are generated, enabling working condition data and carbon emission monitoring data of production equipment of each process flow subsequence of the output layer to be connected into the input layer of the fault early-warning model, and obtaining fault early-warning information through the output layer of the fault early-warning model; and then respectively extracting time features and space features of fault early-warning information output by the fault early-warning model according to the enterprise production carbon emission full-process model, generating a fault early-warning space-time feature sequence, acquiring process flow subsequence position information and the prediction time of faults according to the fault early-warning space-time feature sequence, performing fault tracing detection on the process flow subsequence, and marking the state of the process flow subsequence as an abnormal state.
It should be further noted that, in the implementation process, the process of adding the carbon emission prediction model through deep learning based on the enterprise carbon emission complete process model and the fault early warning model includes:
acquiring historical carbon emission of each process flow subsequence in a monitoring period under different enterprise operation data conditions, carrying out regression analysis by taking historical enterprise operation data of each process flow subsequence and process flow subsequence states as independent variables and taking the historical carbon emission of each process flow subsequence as the dependent variables, and constructing a multiple linear regression function representing between the enterprise carbon emission and the operation data;
inputting enterprise operation data of the process flow subsequence of the current monitoring period and the state of the process flow subsequence of the current monitoring period predicted by the fault early warning model into a multiple linear regression function to obtain the carbon emission variation trend characteristic of the process flow subsequence;
representing the assembly connection relation of all enterprise production equipment in the enterprise production carbon emission full-flow model and the three-dimensional model in a topological graph form, constructing a carbon emission prediction model based on a graph attention network, performing deep learning on the topological graph representation form by using the graph attention network, and guiding the carbon emission variation trend characteristics of all process flow subsequences into the graph attention network; the attention weight of the carbon emission of each topological graph node to the carbon emission of other nodes of the topological graph is obtained through an attention mechanism, and the attention weight is distributed to each topological graph node to complete the construction of a carbon emission prediction model; the input quantity of the carbon emission prediction model is enterprise operation data and the subsequence state of each technological process, and the output quantity is carbon emission quantity.
It should be further noted that, in the implementation process, the process of predicting the carbon emission in the next monitoring period of the enterprise according to the carbon emission prediction model includes:
and inputting enterprise operation data of each process flow sub-sequence in the current monitoring period and the state of each process flow sub-sequence into a carbon emission prediction model to obtain the carbon emission prediction quantity and total carbon emission prediction quantity of each process flow sub-sequence in the next monitoring period and the influence coefficient of the carbon emission quantity of each process flow sub-sequence on the total carbon emission prediction quantity.
It should be further noted that, in the implementation process, the process of predicting the carbon quota that the enterprise needs to purchase or sell in the next monitoring period according to the predicted carbon emission and the historical carbon quota includes:
determining the carbon quota demand of the next monitoring period according to the historical carbon quota, and comparing the total carbon emission predicted quantity generated by the carbon emission prediction model with the carbon quota demand;
if the total carbon emission predicted amount is lower than the carbon quota demand amount, selling redundant carbon quota to a carbon trade market to obtain additional economic benefit;
if the total carbon emission prediction amount is higher than the carbon quota demand amount, carrying out carbon emission reduction operation on enterprises, obtaining the carbon emission reduction allowable maximum value of each process flow sub-sequence, obtaining the influence coefficient of the carbon emission amount of each process flow sub-sequence produced by the carbon emission prediction model on the total carbon emission prediction amount, wherein the influence coefficient = the carbon emission amount/the total carbon emission prediction amount of each process flow sub-sequence produced by the carbon emission prediction model, arranging the process flow sub-sequences according to the order of the influence coefficient from large to small to generate a carbon emission reduction sequence, firstly selecting the first process flow sub-sequence with the largest influence coefficient in the carbon emission reduction sequence, adjusting enterprise operation data of the process flow sub-sequence to carry out carbon emission reduction operation, and judging whether the total carbon emission prediction amount is higher than the carbon quota demand amount at the moment when the carbon emission reduction amount of the process flow sub-sequence reaches the carbon emission reduction allowable maximum value of the process flow sub-sequence, and if the total carbon emission prediction amount is higher than the carbon quota demand amount, selecting the second process sub-sequence in the carbon emission reduction sequence to repeat the carbon emission reduction operation until the total carbon emission prediction amount is lower than the carbon quota demand amount; and if the carbon emission reduction operation is finished by all the process flow subsequences in the carbon emission reduction sequence, the total carbon emission prediction amount is still higher than the carbon quota demand amount, and the carbon quota amount equal to the difference amount is purchased from the carbon trade market according to the difference amount of the total carbon emission prediction amount and the carbon quota demand amount at the moment.
The above embodiments are only for illustrating the technical method of the present application and not for limiting the same, and it should be understood by those skilled in the art that the technical method of the present application may be modified or substituted without departing from the spirit and scope of the technical method of the present application.
Claims (5)
1. An enterprise carbon quota prediction method based on enterprise business data is characterized by comprising the following steps:
step S1: setting carbon emission monitoring points in the production process of an enterprise according to the production process flow information and the historical production data information of the enterprise, collecting carbon emission monitoring data of each monitoring point, marking the collection time, and setting a monitoring period;
step S2: acquiring enterprise operation data information of each monitoring point, and constructing an enterprise production carbon emission full-flow model through carbon emission monitoring data and enterprise operation data information of each monitoring point; wherein the enterprise business data information comprises fuel consumption, yield and profit margin of each process flow sub-sequence;
step S3: judging and generating fault early warning information of the enterprise production process flow according to the carbon emission monitoring data, constructing a fault early warning model, adding the fault early warning model to an enterprise production carbon emission full-flow model, realizing carbon emission anomaly tracing of the carbon emission full-flow, and adding a carbon emission prediction model through deep learning on the basis of the enterprise production carbon emission full-flow model and the fault early warning model;
step S4: predicting the carbon emission amount in the next monitoring period of the enterprise according to the carbon emission prediction model, and predicting the carbon quota which the enterprise needs to purchase or sell in the next monitoring period according to the predicted carbon emission amount and the historical carbon quota;
the process of obtaining the enterprise operation data information of each monitoring point location and constructing the enterprise production carbon emission whole-flow model through the carbon emission monitoring data and the enterprise operation data information of each monitoring point location comprises the following steps:
acquiring physical entity and position information of each production device of an enterprise in a physical space in an enterprise production process flow, constructing three-dimensional modeling for each production device of the enterprise, mapping the three-dimensional modeling to a digital space, and mapping an assembly connection relation of each production device of the enterprise in the physical space to the digital space;
acquiring carbon emission monitoring data and enterprise operation data of each process flow subsequence in the enterprise production process, producing twin data according to the carbon emission monitoring data and the enterprise operation data of each process flow subsequence, and matching the twin data, the assembly connection relation of each production device of the enterprise and the three-dimensional model to generate an enterprise production carbon emission whole-flow model; and
the process of adding the fault early warning model to the enterprise production carbon emission full-flow model to realize carbon emission anomaly traceability of the carbon emission full-flow comprises the following steps:
adding the fault early-warning model into an enterprise production carbon emission full-flow model, respectively extracting time features and space features of fault early-warning information output by the fault early-warning model according to the enterprise production carbon emission full-flow model, generating a fault early-warning space-time feature sequence, carrying out fault tracing detection on a process flow subsequence according to the fault early-warning space-time feature sequence, and marking the state of the process flow subsequence as an abnormal state; and
the process for adding the carbon emission prediction model through deep learning on the basis of the enterprise carbon emission full-flow model and the fault early warning model comprises the following steps of:
acquiring historical carbon emission of each process flow subsequence in a monitoring period under different enterprise operation data conditions, carrying out regression analysis by taking historical enterprise operation data of each process flow subsequence and process flow subsequence states as independent variables and taking the historical carbon emission of each process flow subsequence as the dependent variables, and constructing a multiple linear regression function representing between the enterprise carbon emission and the operation data;
inputting enterprise operation data of the process flow subsequence of the current monitoring period and the state of the process flow subsequence of the current monitoring period predicted by the fault early warning model into a multiple linear regression function to obtain the carbon emission variation trend characteristic of the process flow subsequence;
representing the assembly connection relation of all enterprise production equipment in the enterprise production carbon emission full-flow model and the three-dimensional model in a topological graph form, constructing a carbon emission prediction model based on a graph attention network, performing deep learning on the topological graph representation form by using the graph attention network, and guiding the carbon emission variation trend characteristics of all process flow subsequences into the graph attention network; and obtaining attention weights of the carbon emission of nodes of each topological graph to the carbon emission of other nodes of the topological graph through an attention mechanism, and distributing the attention weights to the nodes of each topological graph to complete the construction of a carbon emission prediction model.
2. The enterprise carbon quota prediction method based on enterprise business data as claimed in claim 1, wherein the process of setting carbon emission monitoring points in the production process of the enterprise according to the production process flow information and the historical production data information of the enterprise, and collecting the carbon emission monitoring data of each monitoring point comprises the following steps:
acquiring the technological process characteristics of each production device of an enterprise, extracting technological process information according to the technological process characteristics, splitting the production process of the enterprise according to the technological process information, and dividing the production process into a plurality of technological process subsequences;
the historical production data information comprises historical carbon emission and historical production economic benefit of each process flow subsequence, an evaluation index is set according to process flow characteristics, the historical carbon emission and the historical production economic benefit in each process flow subsequence, an evaluation index weight is set, an evaluation index matrix is established according to the evaluation index and the evaluation index weight, preset importance levels related to each process flow subsequence are set, and a membership matrix representing fuzzy relation between each process flow subsequence and the preset importance levels is established;
obtaining importance levels of the process flow subsequences according to the membership matrix and the evaluation index matrix, comparing the importance levels of the process flow subsequences with corresponding preset importance levels, and setting carbon emission monitoring points in the process flow subsequences with the importance levels greater than the preset importance levels;
and acquiring the process flow characteristics and the historical carbon emission of the process flow subsequences with the importance level larger than the preset importance level, and determining the number of carbon emission monitoring points and the point taking distribution of the process flow subsequences by combining the importance level of the process flow subsequences.
3. The method for predicting enterprise carbon quota based on enterprise business data as claimed in claim 2, wherein the process of constructing the fault early warning model comprises the steps of:
setting a carbon emission threshold and a preset time threshold, and acquiring the accumulated time when the carbon emission monitoring data of the target process flow subsequence in the monitoring period is greater than the carbon emission threshold;
when the accumulated time is greater than a preset time threshold, generating a fault label on working condition data and carbon emission monitoring data of production equipment of the process flow subsequence;
constructing a fault early warning model based on an RBN neural network, constructing a historical data set according to historical working condition data with fault labels and historical carbon emission monitoring data in an enterprise production carbon emission full-flow model, dividing the historical data set into a training set and a testing set, performing real-time learning training on the fault early warning model through the training set until a loss function is stable in training, storing model parameters, and performing similarity verification on an output data matrix of the fault early warning model after iterative training through the testing set;
and inputting the working condition data and the carbon emission monitoring data of the production equipment of the process flow subsequence in the current monitoring period into a fault early-warning model verified by a test set, and acquiring fault early-warning information according to an output layer of the fault early-warning model.
4. A method for predicting carbon quota in an enterprise based on enterprise business data as claimed in claim 3, wherein predicting the carbon emission in the next monitoring period of the enterprise based on the carbon emission prediction model comprises:
and inputting enterprise operation data of each process flow sub-sequence in the current monitoring period and the state of each process flow sub-sequence into a carbon emission prediction model to obtain the carbon emission prediction quantity and total carbon emission prediction quantity of each process flow sub-sequence in the next monitoring period and the influence coefficient of the carbon emission quantity of each process flow sub-sequence on the total carbon emission prediction quantity.
5. The method for predicting carbon quota in an enterprise based on enterprise business data as claimed in claim 4, wherein predicting carbon quota for an enterprise to purchase or sell in a next monitoring period based on the predicted carbon emission and the historical carbon quota comprises:
determining the carbon quota demand of the next monitoring period according to the historical carbon quota, and comparing the total carbon emission predicted quantity generated by the carbon emission prediction model with the carbon quota demand;
if the total carbon emission predicted amount is higher than the carbon quota demand amount, carrying out carbon emission reduction operation on enterprises, obtaining the carbon emission reduction allowable maximum value of each process flow sub-sequence, obtaining the influence coefficient of the carbon emission amount of each process flow sub-sequence on the total carbon emission predicted amount, arranging the process flow sub-sequences according to the order of the influence coefficient from large to small to generate a carbon emission reduction sequence, firstly selecting the first process flow sub-sequence with the largest influence coefficient in the carbon emission reduction sequence, adjusting enterprise operation data of the process flow sub-sequence to carry out the carbon emission reduction operation, judging whether the total carbon emission predicted amount is higher than the carbon quota demand amount when the carbon emission reduction amount of the process flow sub-sequence reaches the carbon emission reduction allowable maximum value of the process flow sub-sequence, and if the total carbon emission predicted amount is higher than the carbon quota demand amount, selecting the second process flow sub-sequence in the carbon emission reduction sequence to repeat the carbon emission reduction operation until the total carbon emission predicted amount is lower than or equal to the carbon quota demand amount.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310968356.3A CN116681187B (en) | 2023-08-03 | 2023-08-03 | Enterprise carbon quota prediction method based on enterprise operation data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310968356.3A CN116681187B (en) | 2023-08-03 | 2023-08-03 | Enterprise carbon quota prediction method based on enterprise operation data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116681187A CN116681187A (en) | 2023-09-01 |
| CN116681187B true CN116681187B (en) | 2023-10-20 |
Family
ID=87782265
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310968356.3A Active CN116681187B (en) | 2023-08-03 | 2023-08-03 | Enterprise carbon quota prediction method based on enterprise operation data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116681187B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117274017A (en) * | 2023-10-13 | 2023-12-22 | 东莞市东智创新科技有限公司 | Carbon emission monitoring system based on enterprise operation data |
| CN117217419B (en) * | 2023-11-07 | 2024-02-09 | 中电山河数字科技(南通)有限公司 | Method and system for monitoring full life cycle carbon emission of industrial production |
| CN117312888B (en) * | 2023-11-28 | 2024-02-06 | 天津市扬天环保科技有限公司 | Data integration processing method and system for fixed pollution source |
| CN117408394B (en) * | 2023-12-14 | 2024-05-31 | 国网天津市电力公司电力科学研究院 | Carbon emission factor prediction method and device for electric power system and electronic equipment |
| CN117560300B (en) * | 2023-12-28 | 2024-04-30 | 广东云百智联科技有限公司 | Intelligent internet of things flow prediction and optimization system |
| CN118197650B (en) * | 2024-05-17 | 2024-07-30 | 长春中医药大学 | Intelligent monitoring system for evaluating safety of gynecological minimally invasive surgery |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2019175416A (en) * | 2018-03-28 | 2019-10-10 | 赫普科技発展（北京）有限公司 | Blockchain-based carbon trading system |
| CN112669061A (en) * | 2020-12-23 | 2021-04-16 | 华电电力科学研究院有限公司 | Method, system and device for analyzing excess and shortage of carbon quota of thermal power plant and readable storage medium |
| CN113987056A (en) * | 2021-10-28 | 2022-01-28 | 重庆东煌高新科技有限公司 | Carbon emission inversion system and method based on deep learning |
-
2023
- 2023-08-03 CN CN202310968356.3A patent/CN116681187B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2019175416A (en) * | 2018-03-28 | 2019-10-10 | 赫普科技発展（北京）有限公司 | Blockchain-based carbon trading system |
| CN112669061A (en) * | 2020-12-23 | 2021-04-16 | 华电电力科学研究院有限公司 | Method, system and device for analyzing excess and shortage of carbon quota of thermal power plant and readable storage medium |
| CN113987056A (en) * | 2021-10-28 | 2022-01-28 | 重庆东煌高新科技有限公司 | Carbon emission inversion system and method based on deep learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116681187A (en) | 2023-09-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116681187B (en) | Enterprise carbon quota prediction method based on enterprise operation data | |
| CN110298574B (en) | Convolutional neural network-based electricity user payment risk rating method | |
| WO2023236478A1 (en) | Blockchain-based system and method for management and operation of enterprise carbon emission and energy consumption data | |
| Xiao et al. | Status quo and opportunities for building energy prediction in limited data Context—Overview from a competition | |
| CN111507013A (en) | Line loss fault positioning implementation method for power system | |
| CN113421165A (en) | Method and system for evaluating and managing green financial products | |
| CN112785060A (en) | Lean operation and maintenance level optimization method for power distribution network | |
| CN110675020A (en) | High-price low-access user identification method based on big data | |
| CN111639850A (en) | Quality evaluation method and system for multi-source heterogeneous data | |
| CN115905319B (en) | Automatic identification method and system for abnormal electricity fees of massive users | |
| Xuefeng et al. | Risk identification and influence analysis model for urban energy internet based on knowledge graph improved decision-making trial and evaluation laboratory | |
| CN117787792B (en) | Medical instrument quality safety risk supervision-based method and system | |
| CN116029579A (en) | Relay protection equipment purchasing evaluation method and system | |
| Gujjarlapudi et al. | Data driven machine learning models for short‐term load forecasting considering electrical vehicle load | |
| CN114897262A (en) | Rail transit equipment fault prediction method based on deep learning | |
| Shiyun et al. | Data analysis and cloud computing of power grid infrastructure projects under the background of informatization | |
| Wang et al. | Research on power equipment fault diagnosis based on improved SVM algorithm | |
| Luo et al. | Assisted decision making for conditional maintenance of distribution network equipment based on multi-task deep learning | |
| CN112016631A (en) | Improvement scheme related to low-voltage treatment | |
| CN117172138B (en) | Urban traffic carbon emission prediction method and device based on deep learning | |
| Sheikhalishahi et al. | An integrated fuzzy AHP-fuzzy DEA approach for location optimization of renewable energy plants | |
| Kovalyov | Key Technologies of Digital Twins: A Model-Based Perspective | |
| CN118133677B (en) | Self-adaptive wind turbine power probability interval curve modeling method and application system thereof | |
| Zhang et al. | Health Condition Assessment of Marine Systems Based on an Improved Radar Chart | |
| Lee et al. | Explainable AI-based approaches for power quality prediction in distribution networks considering the uncertainty of renewable energy |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |