CN115879638A - Carbon emission prediction method for oil field transfer station system - Google Patents
Carbon emission prediction method for oil field transfer station system Download PDFInfo
- Publication number
- CN115879638A CN115879638A CN202211721961.2A CN202211721961A CN115879638A CN 115879638 A CN115879638 A CN 115879638A CN 202211721961 A CN202211721961 A CN 202211721961A CN 115879638 A CN115879638 A CN 115879638A
- Authority
- CN
- China
- Prior art keywords
- carbon emission
- prediction model
- data
- transfer station
- population
- 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.)
- Granted
Links
Images
Classifications
-
- 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
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a method for predicting carbon emission of an oil field transfer station system, which comprises the following steps: acquiring total historical carbon emission data of an oil field transfer station system; preprocessing the data to process invalid data; analyzing the characteristic value of the data, drawing a characteristic variable correlation heat map, screening out influencing characteristic variables, and obtaining a data set with selected characteristics; establishing a carbon emission prediction model based on a decision tree and training; returning the optimal result found by the genetic algorithm combined with grid search global optimization to the decision tree-based carbon emission prediction model to obtain and train the optimal decision tree carbon emission prediction model based on genetic algorithm optimization; and (4) predicting the carbon emission of the oil field transfer station system by using a decision tree carbon emission prediction model optimized based on a genetic algorithm. The method utilizes the genetic algorithm to search and optimize globally, compensates the local search and optimization of the network of the traditional decision tree, and realizes high precision, short time and high efficiency of carbon emission prediction.
Description
The technical field is as follows:
the invention belongs to the technical field of oil and gas storage and transportation, and particularly relates to a carbon emission prediction method for an oil field transfer station system.
Background art:
the petroleum industry is the basic industry of national economy and energy safety in China, and is also the industry with high energy consumption, high pollution and high carbon emission. The petroleum refining industry in China is rapidly developed since the innovation, the accumulated processing amount of crude oil in China reaches 70355.4 ten thousand tons in 1-12 months in 2021, the accumulated processing amount is increased by 4.3 percent, and the corresponding energy consumption and carbon emission also show a rapid increase trend. Under the situation, it is very important to accurately and efficiently master the carbon emission level of enterprises in advance, and powerful support is provided for formulating a feasible emission reduction way.
The ground gathering and transportation system is an important component of energy consumption carbon emission in oil field production, and the oil field transfer station system is an important production link of the ground gathering and transportation system and plays a role in linking up and down in the oil and gas transportation process, so that the carbon emission prediction of the oil field transfer station system is very necessary. The carbon emission prediction boundary of the oil field transfer station system is mainly determined as carbon emission generated in the process of producing heat energy consumption and electric energy consumption, wherein the heat energy consumption is mainly used for improving the temperature of a medium and reducing the transportation viscosity of the medium; the electric energy consumption is mainly used for increasing the pressure of the medium and providing the energy required by the medium transportation. The heat energy consumption is mainly concentrated in the production of a heating furnace in the transfer station system, fuel in the heating furnace is combusted to provide heat energy for a medium, and the heating furnace is a main fuel combustion source carbon emission node; the electric energy consumption is mainly concentrated in the production of the pump unit in the transfer station system, the pump unit consumes the electric energy to provide pressure energy for a medium, and the pump unit is a carbon emission node of a main indirect power consumption source. Meanwhile, when carbon emission of a transfer station system is predicted, physical parameters of a medium are important factors, and the physical parameters of the medium often comprise density, specific heat capacity and the like.
The existing carbon emission prediction methods are more, a prediction model gradually becomes a research hotspot, and the traditional classical prediction method and machine learning model-based prediction are mainly adopted. The traditional prediction method is popular and easy to understand in prediction theory, but the prediction result has large error and low operation efficiency, and the nonlinear relation between independent variables and dependent variables cannot be obtained.
The invention content is as follows:
the invention aims to provide a carbon emission prediction method for an oil field transfer station system, which is used for solving the problems of large error of a prediction result and low operation efficiency of the carbon emission prediction method in the prior art.
The technical scheme adopted by the invention for solving the technical problems is as follows: the method for predicting the carbon emission of the oil field transfer station system comprises the following steps:
the method comprises the following steps: acquiring total historical carbon emission data of an oil field transfer station system;
step two: preprocessing the carbon emission data of the oil field transfer station system to process invalid data;
step three: analyzing the characteristic value of the data preprocessed in the step two, drawing a characteristic variable correlation heat map, screening out influencing characteristic variables to obtain a data set with selected characteristics, and dividing the data set into a training set and a testing set;
step four: establishing a carbon emission prediction model based on a decision tree, putting a training set into the decision tree-based prediction model for training to obtain a trained carbon emission prediction model;
step five: the grid search method is used for exhaustion of hyper-parameters, and an absolute coefficient R is adopted 2 As criteria for the evaluation model:
where n is the number of samples, pre y Y is actual data;
step six: optimizing grid search by adopting a genetic algorithm to achieve global optimization, loading the carbon emission prediction model processed in the fourth step, taking a training set as input, taking the average value of three scores obtained by three-fold cross validation as a fitness function to obtain an initialized population P (t), and then performing selective population iteration by using the fitness function to obtain a new population P (t + 2);
step seven: transmitting the optimal result found by the genetic algorithm and the grid search global optimization back to the decision tree-based carbon emission prediction model, and updating the model to obtain the optimal decision tree carbon emission prediction model based on the genetic algorithm optimization;
step eight: training a decision tree carbon emission prediction model optimized based on a genetic algorithm, cross-verifying the standard deviation of the calculation accuracy, adjusting grid parameters, and training to obtain a training result; analyzing the training result, if the effect is converged, ending the training, if the effect is not converged, adjusting the parameters until the prediction requirement is met;
step nine: and outputting data, and predicting the carbon emission of the oil field transfer station system by using a decision tree carbon emission prediction model optimized based on a genetic algorithm.
The method for drawing the characteristic variable correlation heat map in the scheme specifically comprises the following steps: utilizing feature selection () function to screen out the factors influencing the characteristic variables, such as daily gas consumption, energy utilization rate of a metering and transferring station, daily power consumption, provided heat energy, pressure difference, comprehensive energy consumption of unit liquid amount, provided pressure energy, daily liquid amount, unit liquid amount set gas transmission consumption, unit liquid amount set power transmission consumption, pressure energy absorbed by oil, heat energy absorbed by oil, specific heat capacity, temperature difference, density, electric energy utilization rate, fuel heating value and heat energy utilization rate, judging the magnitude of the correlation among the variables according to the magnitude of the correlation coefficient in a correlation coefficient graph, wherein the higher the correlation coefficient is, the higher the linear correlation degree among the variables is, the irrelevant variables and the target variables are deleted, and the data set after the characteristic is selected.
The concrete method of the step six in the scheme is as follows:
taking a training set as input, taking an average value of three score obtained by three-fold cross validation as a fitness function to obtain an initialized population P (t), and then carrying out population selection iteration through the fitness function, wherein a roulette method is adopted for a selected genetic operator, and a specific expression is as follows:
wherein P is the number of the population, in which
Fitness j Is the total fitness value of the population. A new population P (t + 1) is generated through the selection of the fitness function, the genetic operator operation is continued on the basis of the population, and the operation is carried out according to the sequence of selection, intersection and variation; the selection is operated in a roulette mode, the individuals with high fitness are left with high probability, and the individuals with low fitness are eliminated; the crossing is to carry out the following operation on individuals in the population according to a certain probability:
in the formula x n Is the nth individual, and b is a random number between 0 and 1; mutation is to perform mutation operation on a certain gene of a certain individual according to a certain probability; and obtaining a new population P (t + 2) through the operation of the three genetic operators, wherein the population is a hyper-parameter based on a decision tree prediction model, and then carrying out three-fold cross validation to verify whether a termination condition is met, if the model is not obviously optimized and promoted for 10 continuous periods, setting early stop or 100 generations of population iteration, and if the termination condition is not met, continuing updating the population iteration again.
The invention has the following beneficial effects:
1. the invention combines the historical data of the oil field transfer station, researches a carbon emission prediction method of an oil field transfer station system, utilizes a genetic algorithm to search and optimize globally, makes up the local search and optimization of a traditional decision tree network, can improve the carbon emission prediction accuracy, has short time and high efficiency, is beneficial to developing various works of carbon accounting and energy and carbon reduction for the oil field transfer station system, and makes up the deficiency of the oil field transfer station system in the research of the carbon emission prediction of an energy internet project.
2. The invention aims to provide a carbon emission prediction method of an oil field transfer station system, which aims to improve the model prediction accuracy, eliminate unimportant characteristics among data and redundancy by utilizing a characteristic value analysis method, reduce the overfitting condition of the model to a certain extent, optimize model parameters by utilizing the characteristic of global optimization of a genetic algorithm, further improve the precision of the carbon emission prediction model and accelerate the optimization efficiency, and provide an accurate prediction model for the oil field transfer station system to carry out various work of carbon accounting, energy saving and carbon reduction.
Description of the drawings:
FIG. 1 is a flow chart of a method for predicting carbon emissions of an oilfield transfer station system according to an embodiment of the present invention;
fig. 2 is a flowchart of a data verification method for an oil field transfer station of a method for predicting carbon emission of an oil field transfer station system according to an embodiment of the present invention;
FIG. 3 is a characteristic variable correlation analysis diagram of a carbon emission prediction method for an oilfield transfer station system according to an embodiment of the present invention;
FIG. 4 is a flowchart of a method for predicting carbon emission of an oilfield transfer station system by optimizing a grid search using a genetic algorithm according to an embodiment of the present invention;
fig. 5 is a screenshot of a training process of a method for predicting carbon emission of an oil field transfer station system according to an embodiment of the present invention;
fig. 6 is a schematic diagram of a prediction result provided by the embodiment of the present invention.
The specific implementation mode is as follows:
the invention will be further described with reference to the accompanying drawings in which:
the carbon emission prediction method of the oil field transfer station system comprises the following steps:
preprocessing the carbon emission data of the oil field transfer station system, including identifying abnormal data through a box type graph, based on jupyter in an Anaconda platform, adopting Python language programming, reconstructing missing data, and checking the validity of the data; analyzing the characteristic value, and drawing a characteristic variable correlation heat map; performing label classification on the data set, dividing the classified data set into a training set and a prediction set, and taking 70% of the data set as the training set and 30% of the data set as a test set;
inputting a carbon emission prediction model based on a decision tree, wherein the input of the prediction model is a characteristic variable after characteristic value analysis, the output is a carbon emission prediction value, grid parameters are adjusted, grid parameters such as probability of a chance from one generation to the next generation, cross validation parameters, population number, iteration times, variation probability and the like are set, and training is carried out to obtain a training result; when the carbon emission prediction model based on the decision tree is trained, if the carbon emission prediction model is not obviously optimized and promoted within a set period range, the training is ended; when the carbon emission prediction model based on the decision tree is trained, the input independent variables are 'daily gas consumption', 'daily power consumption', 'energy utilization ratio of a transfer station' and 'provided heat energy' in a data set, and the output dependent variables are carbon emission data.
The training of the carbon emission prediction model based on the decision tree comprises the following steps:
acquiring pre-collected historical carbon emission data of an oil field transfer station system, and preprocessing the data;
analyzing the characteristic value, and drawing a characteristic variable correlation heat map;
performing label classification on the data set, and dividing the classified data set into a training set and a prediction set;
inputting a carbon emission prediction model based on a decision tree, adjusting grid parameters, and training to obtain a training result;
and analyzing the training result, if the effect is converged, ending the training, and if the effect is not converged, adjusting the parameters until the prediction requirement is met.
Example 1:
the method for predicting the carbon emission of the oil field transfer station system comprises the following steps:
the method comprises the following steps: and acquiring total data date of historical carbon emission of the oil field transfer station system.
Step two: firstly, carrying out standardization processing on historical carbon emission data of an oil field transfer station, wherein the data obey normal distribution with the mean value of 0 and the variance of 1; then, data processing is performed by executing an date _ process () function, where the date _ process () function includes data integrity check, duplicate value check, abnormal value check, missing value and abnormal value processing for the transfer station, and the specific flow is as shown in fig. 2, and invalid data is processed.
Step three: and drawing a characteristic variable correlation coefficient graph. And screening out the influence characteristic variables by using a feature selection () function. As shown in fig. 3, the factors affecting the carbon emission include daily gas consumption, energy utilization rate of the transfer station, daily power consumption, provided heat energy, pressure difference, comprehensive energy consumption of unit liquid amount, provided pressure energy, daily infusion amount, unit liquid amount gas transmission consumption, unit liquid amount power transmission consumption, pressure energy absorbed by the oil product, heat energy absorbed by the oil product, specific heat capacity, temperature difference, density, electric energy utilization rate, fuel heating value, and heat energy utilization rate. At this time, the irrelevant variable and the target variable are deleted, and the data set with the characteristics is selected.
Step four: the new data date2 is divided reasonably. To ensure adequate training and efficient testing of the learning model, 70% of the data set is used as the training set and 30% as the testing set.
Step five: and establishing a carbon emission prediction model based on a decision tree by using a python library function, and putting the processed input and output data into the prediction model based on the decision tree for training to obtain the trained carbon emission prediction model.
Step six: firstly, a grid search method is utilized to exhaust hyper-parameters, and an absolute coefficient R is adopted 2 As a criterion for evaluating the model, as shown in formula 1:
where n is the number of samples, pre y To predict data, y is actual data.
Step seven: on the basis, a genetic algorithm is adopted to optimize grid search, so that the global optimization effect is further achieved, a prediction model based on a decision tree established in the step five is loaded, a training set is used as input, the average value of three score obtained by three-fold cross validation is used as a fitness function (the fitness function is established by three-fold cross validation), an initialized population P (t) is obtained, then population selection iteration is carried out through the fitness function, the selected genetic operator adopts a roulette method, and the specific expression is as follows:
wherein P is the number of groups, in which
Fitness j Is the total fitness value of the population. And generating a new population P (t + 1) through the selection of the fitness function, continuing genetic operator operation on the basis of the population, and operating according to the sequence of selection, intersection and variation. The selection is mainly operated in a roulette mode, the individuals with high fitness are left with high probability, and the individuals with low fitness are eliminated; the crossing is to carry out the following operation on individuals in the population according to a certain probability:
in the formula x n Is the nth individual, and b is a random number between 0 and 1. Mutation is the operation of mutating a certain gene of a certain individual according to a certain probability. Through the operations of the three genetic operators, a new population P (t + 2) is obtained, and it is worth pointing out that the population is based on the hyper-parameters of the decision tree prediction model, and then the triple-fold cross validation is carried out to verify whether the termination condition is met (if 10 continuous cycles are carried out, the model has no obvious optimization promotion, early stop is set or the population iteration is carried out for 100 generations), and if the termination condition is not met, the seventh operation is carried out again to continue updating the population iteration. The specific flow is shown in FIG. 4The relevant parameters for the grid search and genetic algorithm are given in table 1 as follows:
TABLE 1 grid parameters
Step eight: and returning the optimal result found by the genetic algorithm and the grid search global optimization to the carbon emission prediction model based on the decision tree, and updating the prediction model to obtain the optimal decision tree carbon emission prediction model based on the genetic algorithm optimization. It is worth pointing out that decision tree based carbon emission prediction model refers to a carbon emission prediction model that is optimized based on genetic algorithm, without being optimized by genetic algorithm model hyper-parameters, and is the optimal carbon emission prediction model, the hyper-parameters of the two models are different.
Step nine: performing cross validation on the data, wherein part of the training process is shown in FIG. 5; the optimal error ratio of the model prediction results is shown in table 2, the prediction results are shown in fig. 6, the prediction curve of the decision tree carbon emission prediction model based on genetic algorithm optimization is highly consistent with the actual curve, the model accuracy is high, and the application requirements are met.
TABLE 2 error comparison of results
A large amount of data can be trained based on machine learning model prediction, a training model generated by the mapping relation between input data and output data can obtain a corresponding prediction result after the input data is trained by the training model. The model has high prediction precision, short time and high efficiency, is beneficial to developing various works of carbon accounting and energy and carbon saving for the oil field transfer station system, and makes up the deficiency of the oil field transfer station system in the research of carbon emission prediction of energy internet projects.
Claims (3)
1. A carbon emission prediction method for an oil field transfer station system is characterized by comprising the following steps:
the method comprises the following steps: acquiring total historical carbon emission data of an oil field transfer station system;
step two: preprocessing the carbon emission data of the oil field transfer station system to process invalid data;
step three: analyzing the characteristic value of the data preprocessed in the step two, drawing a characteristic variable correlation heat map, screening out influencing characteristic variables to obtain a data set with selected characteristics, and dividing the data set into a training set and a testing set;
step four: establishing a carbon emission prediction model based on a decision tree, putting a training set into the decision tree-based prediction model for training to obtain a trained carbon emission prediction model;
step five: the grid search method is used for exhaustion of the hyperparameter, and an absolute coefficient R is adopted 2 As criteria for the evaluation model:
where n is the number of samples, pre y Y is actual data;
step six: optimizing grid search by adopting a genetic algorithm to achieve global optimization, loading a carbon emission prediction model which is trained and processed in the fourth step, taking a training set as input, taking the average value of three scores obtained by three-fold cross validation as a fitness function to obtain an initialized population P (t), and then carrying out selective population iteration by the fitness function to obtain a new population P (t + 2);
step seven: transmitting the optimal result found by the genetic algorithm and the grid search global optimization back to the decision tree-based carbon emission prediction model, and updating the model to obtain the optimal decision tree carbon emission prediction model based on the genetic algorithm optimization;
step eight: training a decision tree carbon emission prediction model optimized based on a genetic algorithm, cross-verifying the standard deviation of the calculation accuracy, adjusting grid parameters, and training to obtain a training result; analyzing the training result, if the effect is converged, ending the training, if the effect is not converged, adjusting the parameters until the prediction requirement is met;
step nine: and outputting data, and predicting the carbon emission of the oil field transfer station system by using a decision tree carbon emission prediction model optimized based on a genetic algorithm.
2. The method of predicting carbon emissions of an oilfield transfer station system of claim 1, wherein: the method for drawing the characteristic variable correlation heat map specifically comprises the following steps: utilizing feature selection () function to screen out the factors influencing the characteristic variables, such as daily gas consumption, energy utilization rate of a metering and transferring station, daily power consumption, provided heat energy, pressure difference, comprehensive energy consumption of unit liquid amount, provided pressure energy, daily liquid amount, unit liquid amount set gas transmission consumption, unit liquid amount set power transmission consumption, pressure energy absorbed by oil, heat energy absorbed by oil, specific heat capacity, temperature difference, density, electric energy utilization rate, fuel heating value and heat energy utilization rate, judging the magnitude of the correlation among the variables according to the magnitude of the correlation coefficient in a correlation coefficient graph, wherein the higher the correlation coefficient is, the higher the linear correlation degree among the variables is, the irrelevant variables and the target variables are deleted, and the data set after the characteristic is selected.
3. The method of predicting carbon emissions of an oilfield transfer station system of claim 2, wherein: the concrete method of the sixth step is as follows:
taking a training set as input, taking an average value of three score obtained by three-fold cross validation as a fitness function to obtain an initialized population P (t), and then carrying out population selection iteration through the fitness function, wherein a roulette method is adopted for a selected genetic operator, and a specific expression is as follows:
wherein P is the number of groups, in which
Is the total fitness value of the population. Generating a new population P (t + 1) through the selection of the fitness function, continuing genetic operator operation on the basis of the population, and operating according to the sequence of selection, intersection and variation; the selection is operated in a roulette mode, individuals with high fitness are left with high probability, and conversely, the individuals with low fitness are eliminated; the crossing is to carry out the following operation on individuals in the population according to a certain probability:
in the formula x n Is the nth individual, and b is a random number between 0 and 1; the mutation is to perform mutation operation on a certain gene of a certain individual according to a certain probability; and obtaining a new population P (t + 2) through the operation of the three genetic operators, wherein the population is a hyper-parameter based on a decision tree prediction model, and then carrying out three-fold cross validation to verify whether a termination condition is met, if the model is not obviously optimized and promoted for 10 continuous periods, setting early stop or 100 generations of population iteration, and if the termination condition is not met, continuing updating the population iteration again.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211721961.2A CN115879638B (en) | 2022-12-30 | 2022-12-30 | Carbon emission prediction method for oilfield transfer station system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211721961.2A CN115879638B (en) | 2022-12-30 | 2022-12-30 | Carbon emission prediction method for oilfield transfer station system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115879638A true CN115879638A (en) | 2023-03-31 |
| CN115879638B CN115879638B (en) | 2023-06-09 |
Family
ID=85757463
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211721961.2A Active CN115879638B (en) | 2022-12-30 | 2022-12-30 | Carbon emission prediction method for oilfield transfer station system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115879638B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116720058A (en) * | 2023-04-28 | 2023-09-08 | 贵研铂业股份有限公司 | Method for realizing key feature combination screening of machine learning candidate features |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108876054A (en) * | 2018-07-06 | 2018-11-23 | 国网河南省电力公司郑州供电公司 | Short-Term Load Forecasting Method based on improved adaptive GA-IAGA optimization extreme learning machine |
| CN109828532A (en) * | 2019-01-29 | 2019-05-31 | 贵州大学 | A kind of Prediction of Surface Roughness method and process parameter optimizing method based on GA-GBRT |
| CN111027733A (en) * | 2018-10-10 | 2020-04-17 | 中国石油化工股份有限公司 | Petrochemical device product yield optimization method based on big data technology |
| CN111445060A (en) * | 2020-03-06 | 2020-07-24 | 华南理工大学珠海现代产业创新研究院 | Community carbon emission monitoring and predicting system and method |
| US20210117803A1 (en) * | 2019-10-16 | 2021-04-22 | SparkCognition, Inc. | Executing a genetic algorithm on a low-power controller |
| CN115310664A (en) * | 2022-07-01 | 2022-11-08 | 中国石油大学(华东) | RBF neural network training method and prediction system based on gene regulation genetic algorithm |
-
2022
- 2022-12-30 CN CN202211721961.2A patent/CN115879638B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108876054A (en) * | 2018-07-06 | 2018-11-23 | 国网河南省电力公司郑州供电公司 | Short-Term Load Forecasting Method based on improved adaptive GA-IAGA optimization extreme learning machine |
| CN111027733A (en) * | 2018-10-10 | 2020-04-17 | 中国石油化工股份有限公司 | Petrochemical device product yield optimization method based on big data technology |
| CN109828532A (en) * | 2019-01-29 | 2019-05-31 | 贵州大学 | A kind of Prediction of Surface Roughness method and process parameter optimizing method based on GA-GBRT |
| US20210117803A1 (en) * | 2019-10-16 | 2021-04-22 | SparkCognition, Inc. | Executing a genetic algorithm on a low-power controller |
| CN111445060A (en) * | 2020-03-06 | 2020-07-24 | 华南理工大学珠海现代产业创新研究院 | Community carbon emission monitoring and predicting system and method |
| CN115310664A (en) * | 2022-07-01 | 2022-11-08 | 中国石油大学(华东) | RBF neural network training method and prediction system based on gene regulation genetic algorithm |
Non-Patent Citations (1)
| Title |
|---|
| 刘志刚: ""基于离散过程神经网络页岩油气储层有机碳含量预测"", 《中国石油大学学报》, vol. 41, no. 2, pages 80 - 83 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116720058A (en) * | 2023-04-28 | 2023-09-08 | 贵研铂业股份有限公司 | Method for realizing key feature combination screening of machine learning candidate features |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115879638B (en) | 2023-06-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108596212B (en) | Transformer fault diagnosis method based on improved cuckoo search optimization neural network | |
| CN111861774B (en) | Oil reservoir production machine learning method based on parallel agent model | |
| CN114692265B (en) | Zero-carbon building optimization design method based on deep reinforcement learning | |
| WO2020047653A1 (en) | System and method for anaerobic digestion process assessment, optimization and/or control | |
| CN114035468B (en) | Method and system for predictively monitoring overhaul flow of fan based on XGBoost algorithm | |
| CN115879638A (en) | Carbon emission prediction method for oil field transfer station system | |
| Ning et al. | GA-BP air quality evaluation method based on fuzzy theory. | |
| CN115860173A (en) | Construction and prediction method and medium of carbon emission prediction model based on Stacking algorithm | |
| CN111695288B (en) | Transformer fault diagnosis method based on Apriori-BP algorithm | |
| Tan et al. | A methodology for augmenting sparse pairwise comparison matrices in AHP: applications to energy systems | |
| CN110059938B (en) | Power distribution network planning method based on association rule driving | |
| CN113706328A (en) | Intelligent manufacturing capability maturity evaluation method based on FASSA-BP algorithm | |
| CN109214500A (en) | A kind of transformer fault recognition methods based on integrated intelligent algorithm | |
| CN115994459B (en) | Method, system and equipment for optimizing construction time sequence of mass power grid infrastructure projects | |
| CN115407053B (en) | Symptom optimization method, computer device, and readable storage medium | |
| CN115700363B (en) | Method and system for diagnosing faults of rolling bearing of coal mining machine, electronic equipment and storage medium | |
| CN116258234A (en) | BP neural network model-based energy enterprise carbon emission measuring and predicting method | |
| Li et al. | Influential Factor Analysis and Projection of Industrial CO 2 Emissions in China Based on Extreme Learning Machine Improved by Genetic Algorithm. | |
| Hengyan et al. | The study of optimizing circulating fluidized bed boiler operational parameters based on neural network and genetic algorithm | |
| Sheng | Lateral Collision Model and Parameter Analysis of Bridge Structure Based on Sensor Array | |
| CN115983089A (en) | Transformer cost-sensitive fault diagnosis method considering important grade division | |
| Zhou et al. | Prediction Model of Coal Consumption Based on Random Forest Variable Selection and Random-Grid Hyperparametric Optimization Algorithm | |
| CN116701429B (en) | Public query method based on batch historical task fuzzification | |
| Zhao et al. | Optimization of Process Control Parameters for Fully Mechanized Mining Face Based on ANN and GA | |
| CN117435877A (en) | Online prediction method for carbon emission of coal-fired power plant |
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 |