CN113705601A - Method for identifying running state of electric smelting magnesium furnace based on random forest - Google Patents
Method for identifying running state of electric smelting magnesium furnace based on random forest Download PDFInfo
- Publication number
- CN113705601A CN113705601A CN202110555009.9A CN202110555009A CN113705601A CN 113705601 A CN113705601 A CN 113705601A CN 202110555009 A CN202110555009 A CN 202110555009A CN 113705601 A CN113705601 A CN 113705601A
- Authority
- CN
- China
- Prior art keywords
- fused magnesia
- furnace
- data
- fused
- magnesia furnace
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 34
- FYYHWMGAXLPEAU-UHFFFAOYSA-N Magnesium Chemical compound [Mg] FYYHWMGAXLPEAU-UHFFFAOYSA-N 0.000 title claims abstract description 31
- 229910052749 magnesium Inorganic materials 0.000 title claims abstract description 31
- 239000011777 magnesium Substances 0.000 title claims abstract description 31
- 238000003723 Smelting Methods 0.000 title claims abstract description 30
- 238000007637 random forest analysis Methods 0.000 title claims abstract description 26
- CPLXHLVBOLITMK-UHFFFAOYSA-N Magnesium oxide Chemical compound [Mg]=O CPLXHLVBOLITMK-UHFFFAOYSA-N 0.000 claims abstract description 174
- 239000000395 magnesium oxide Substances 0.000 claims abstract description 89
- 238000003066 decision tree Methods 0.000 claims abstract description 22
- 238000012549 training Methods 0.000 claims abstract description 17
- 238000012360 testing method Methods 0.000 claims abstract description 11
- 238000004458 analytical method Methods 0.000 claims abstract description 10
- 238000002844 melting Methods 0.000 claims description 12
- 230000008018 melting Effects 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 7
- 238000004519 manufacturing process Methods 0.000 claims description 5
- 238000005070 sampling Methods 0.000 claims description 5
- 238000004088 simulation Methods 0.000 claims description 3
- 238000010891 electric arc Methods 0.000 claims description 2
- 238000007781 pre-processing Methods 0.000 claims description 2
- 238000004422 calculation algorithm Methods 0.000 description 4
- AXZKOIWUVFPNLO-UHFFFAOYSA-N magnesium;oxygen(2-) Chemical compound [O-2].[Mg+2] AXZKOIWUVFPNLO-UHFFFAOYSA-N 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- ZLNQQNXFFQJAID-UHFFFAOYSA-L magnesium carbonate Chemical compound [Mg+2].[O-]C([O-])=O ZLNQQNXFFQJAID-UHFFFAOYSA-L 0.000 description 2
- 239000001095 magnesium carbonate Substances 0.000 description 2
- 235000014380 magnesium carbonate Nutrition 0.000 description 2
- 229910000021 magnesium carbonate Inorganic materials 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 239000004568 cement Substances 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 239000013078 crystal Substances 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 239000011819 refractory material Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/259—Fusion by voting
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Manufacture And Refinement Of Metals (AREA)
- Vertical, Hearth, Or Arc Furnaces (AREA)
Abstract
A method for identifying the running state of an electric smelting magnesium furnace based on random forests comprises the following steps: collecting operation data of the electro-fused magnesia furnace, performing multi-time scale analysis on three-phase voltage electric flow data to determine that a minute level is used as a selected time scale, and randomly generating a plurality of electro-fused magnesia furnace data training sets for the obtained operation data of the electro-fused magnesia furnace; generating a corresponding decision tree by using each training set, testing by using each decision tree to obtain the classification category of the corresponding operation state of the fused magnesia furnace, and finally taking the mode of the cast magnesia operation state obtained by voting as the final result of the identification of the fused magnesia operation state; and the obtained identification result of the state of the fused magnesia utilizes the adjustment margin provided by the smelting stage of the fused magnesia furnace to obtain the adjustment quantity of the whole fused magnesia furnace group. The method has the advantages that the classification of the operation states of the fused magnesia furnace is realized based on the three-phase voltage and current data of the fused magnesia furnace, and a technical basis is provided for the fused magnesia furnace to participate in the load side regulation and control of the power system.
Description
Technical Field
The invention relates to the technical field of artificial intelligence and power system load control, in particular to a method for identifying the running state of an electric smelting magnesium furnace based on a random forest.
Background
Magnesium oxide is used as a high-temperature refractory material in the aerospace industry, cement industry, chemical industry, electronic industry and the like. In the process of producing magnesium oxide, magnesite is mainly used for high-temperature preparation, and the magnesite is heated to a molten state through an electric magnesium melting furnace, so that high-purity magnesium oxide crystals are obtained. At present, a plurality of expert and scholars at home and abroad carry out relevant research on the production and operation process of the fused magnesia furnace, and mainly focus on energy-saving and low-carbon operation and fault diagnosis of the fused magnesia furnace. In the process of preparing magnesium oxide, a large amount of electric energy is consumed. The electro-fused magnesia furnace is used as high-energy-consumption electrical equipment and can participate in load curve adjustment of a power system. And with the development of the intelligent electric meter, the operation data acquisition of the electric smelting magnesium furnace can be easily realized. Therefore, when the electric smelting magnesium load is used as an adjustable and controllable resource on the load side, the operation state of the electric smelting magnesium furnace needs to be analyzed in real time, and the adjustment and control capability of the electric smelting magnesium furnace group can be further evaluated.
Disclosure of Invention
In order to solve the technical problems provided by the background art, the invention provides a method for identifying the running state of an electro-fused magnesia furnace based on a random forest, and aims to solve the problem that the electro-fused magnesia furnace in a load side is considered as a system peak regulation resource in a power system, the running state of the electro-fused magnesia furnace is identified by collecting three-phase voltage and three-phase current data of the real-time running of the electro-fused magnesia furnace and utilizing a random forest algorithm.
In order to achieve the purpose, the invention adopts the following technical scheme:
a method for identifying the running state of an electro-fused magnesia furnace based on random forests comprises the following steps:
acquiring operation data of the electro-fused magnesia furnace through an intelligent ammeter, wherein the operation data mainly comprises three-phase voltage, three-phase current and other data of the electro-fused magnesia furnace, determining a minute level as a selected time scale by performing multi-time scale analysis on the three-phase voltage and current data, and processing the capacity process data of the whole electro-fused magnesia;
step two, randomly generating a plurality of electric smelting magnesium furnace data training sets according to the processed electric smelting magnesium furnace operation data obtained in the step one; generating a corresponding decision tree by using each training set, testing a test set sample by using each decision tree to obtain the classification category of the corresponding operation state of the fused magnesia furnace, and finally adopting a voting mode to take the mode of the operation state of the fused magnesia obtained by voting as the final result of the identification of the operation state of the fused magnesia;
and step three, obtaining the adjustment quantity of the whole fused magnesia furnace group by utilizing the adjustment margin provided by the smelting stage of the fused magnesia furnace according to the identification result of the fused magnesia state obtained in the step two, and providing a basis for power system scheduling.
Further, in the step one, the process of performing multi-time scale analysis on the three-phase voltage and current data of the electric arc furnace is as follows: acquiring operation data of a single electric magnesium melting furnace through an intelligent ammeter, performing data processing on three-phase voltage and three-phase current data by taking 1 second, 1 minute, 5 minutes and 30 minutes as time scales after second-level data of the whole production process are obtained, and determining the time scale of the data processing according to data characteristics and peak regulation requirements of an electric power system; and (3) preprocessing the three-phase voltage and current data by taking 1min as a time scale to obtain the characteristics of standard deviation, average value, worst value and the like of the data.
Further, in the second step, firstly, a Bootstrap method is used for sampling for multiple times to generate n training sets S1， S2，…，SnAnd the other data groups are used as test set data; generating a corresponding decision tree C by using a training set generated by voltage electrical data1，C2，…，Cn(ii) a Taking a plurality of characteristics of three-phase voltage electric current data within 1min as input of a model, and taking fused magnesium in a non-smelting stage and a smelting stage as output of the model; by analyzing the simulation result of the random forest classifier, the accuracy of the operation state of the fused magnesia furnace can be obtained, so that the feasibility of the classification method can be evaluated, and the accuracy of classification of the operation state of the fused magnesia furnace is respectively calculated when decision trees contained in random forest are different.
Further, in the third step, the proportion of the fused magnesia furnaces in the fused furnace state in the fused magnesia furnaces is determined, and the adjustment margin of the whole fused magnesia furnace group is obtained by combining the adjustment margins of the single fused magnesia furnace.
Compared with the prior art, the invention has the beneficial effects that:
1) the design of the invention definitely realizes the classification of the operation state of the fused magnesia furnace based on the three-phase voltage and current data of the fused magnesia furnace, and provides a technical basis for the fused magnesia furnace to participate in the load side regulation and control of the power system.
2) The method fully considers the influence of different decision trees on the performance of the random forest classifier while classifying the operation state of the fused magnesia furnace, and ensures the accuracy of the method.
Drawings
FIG. 1 is a three-phase current multi-time scale waveform of an electro-fused magnesia furnace;
FIG. 2 is a three-phase voltage multi-time scale waveform of the electro-fused magnesia furnace;
FIG. 3 is a schematic diagram of a concept of a random forest algorithm;
FIG. 4 is a performance analysis of a random forest classifier based on an electro-fused magnesia furnace;
FIG. 5 is a graph showing the influence of the number of decision trees on the accuracy of the state recognition of the electro-fused magnesia furnace.
Detailed Description
The following detailed description of the present invention will be made with reference to the accompanying drawings.
A method for identifying the running state of an electro-fused magnesia furnace based on random forests comprises the following steps:
the method comprises the following steps: the method comprises the steps that operation data of the electro-fused magnesia furnace are collected through an intelligent ammeter, wherein the operation data mainly comprise data such as three-phase voltage, three-phase current and the like of the electro-fused magnesia furnace, and generally, the three-phase voltage and the three-phase current can reflect the production process of the electro-fused magnesia furnace, so that the three-phase voltage and the three-phase current are selected for detailed analysis, as shown in fig. 1, the phase A current is shown in fig. 1(a), and the waveform of the phase A current sampling interval is 1s, 1min, 5min and 30min is sequentially selected from top to bottom. Fig. 1(B) and 1(C) show waveforms of phase B and phase C currents, respectively. As can be seen from FIG. 1, the current value fluctuates violently within 1h of furnace start, and the current waveform tends to a stable fluctuation state after about 1h of furnace start; the current is obviously reduced about 1h before the shutdown. As shown in fig. 2, the left side of fig. 2 is a waveform diagram of a phase voltage a, and waveforms of which sampling intervals are 1s, 1min, 5min and 30min are sequentially arranged from top to bottom. The middle of fig. 2 and the right side of fig. 2 are respectively the waveforms of phase B and phase C voltages. By carrying out multi-time scale analysis on three-phase voltage and current data, determining that 1 minute is used as a selected time scale, and processing the data in the whole capacity process of the fused magnesium, the average value, the standard deviation and the worst value of the voltage and the current are obtained by taking one minute as the time scale.
Step two: and (4) randomly generating a plurality of electric smelting magnesium furnace data training sets according to the processed electric smelting magnesium furnace operation data obtained in the step one. And finally, by adopting a voting mode, taking the mode of voting obtained by voting as a final result of the identification of the operation state of the fused magnesium. FIG. 3 is a process diagram of a random forest algorithm.
Firstly, a Bootstrap method is utilized to carry out multiple sampling to generate n training sets S1，S2，…，SnWhich isThe rest data group is used as test set data; generating a corresponding decision tree C by using a training set generated by voltage electrical data1，C2，…，Cn(ii) a Taking 6 characteristics of three-phase voltage electrical current data within 1min as input of a model, and taking fused magnesium in a non-melting stage (a furnace start stage and a finishing stage) and a melting stage as output of the model; by analyzing the simulation result of the random forest classifier, the accuracy of the operation state of the fused magnesia furnace can be obtained, so that the feasibility of the classification method can be evaluated, and the accuracy of classification of the operation state of the fused magnesia furnace is respectively calculated when decision trees contained in random forest are different.
Step three: and (4) obtaining the adjustment quantity of the whole fused magnesia furnace group by utilizing the adjustment margin provided by the smelting stage of the fused magnesia furnace according to the identification result of the fused magnesia state obtained in the step two, and providing a basis for power system scheduling. Setting the adjusting margin provided by the electric smelting magnesium load in the power system at the time t as delta P (t), and then
Wherein M1 is the number of the fused magnesia furnaces in a smelting state after the running state of the fused magnesia furnace group is identified; m is the total number of the electro-fused magnesia furnace group in a working state; p (t) is the total power consumed by the fused magnesia furnace group at the time t; eta is the adjustment margin provided by a single electric smelting magnesium furnace in a smelting state.
The invention comprises the following steps: the voltage and current data of the electro-fused magnesia furnace are preprocessed by carrying out multi-time scale analysis on the voltage and current data of the electro-fused magnesia furnace to determine that the time scale is minutes, so as to obtain the average value, the standard deviation and the worst value of the data; establishing a random forest classifier, randomly selecting a training set and a testing set, training the random forest classifier through the training set, testing by utilizing each decision tree to obtain the classification type of the corresponding operation state of the fused magnesia furnace, determining the final result of the operation state identification of the fused magnesia furnace by adopting a voting mode, and finally determining the adjustment margin of the whole fused magnesia furnace group.
The following examples were used to demonstrate the beneficial effects of the present invention:
the first embodiment is as follows: the method comprises the following steps of taking an electro-fused magnesia furnace of a certain electro-fused magnesia enterprise in the Anshan area of Liaoning as a research object, carrying out grouping pretreatment on data by collecting three-phase voltage and current data in the whole production process and taking 1min as a time scale, randomly extracting 500 groups from 566 groups of voltage and current data as a training set for no loss of generality, taking the rest voltage and current data as a test set as the accuracy for detecting the running state identification of the electro-fused magnesia furnace, and obtaining the state identification result of the electro-fused magnesia furnace with 1min as the time scale by program calculation, wherein the state identification result is shown in table 1:
TABLE 1 recognition results of the conditions of the fused magnesia furnace
As can be seen from the performance analysis of the random forest classifier mainly based on the electric magnesium melting furnace in fig. 4, the number of samples with wrong identification is small in the state identification of the electric magnesium melting furnace, and the samples are concentrated in the middle area, which shows that the state identification generalization capability of the electric magnesium melting furnace using voltage and current is high, and the classification performance is good.
Finally, the present example also discusses that the number of decision trees in the random forest algorithm has another influence on the operation state of the electric magnesium melting furnace, and discusses that the number of decision trees has an influence on the classification accuracy of the electric magnesium melting furnace when the number of decision trees is from 50 to 1000, as can be seen from fig. 5, when the number of decision trees is 100, a higher classification accuracy can be obtained, and although the number of decision trees is increased so that the state identification of the electric magnesium melting furnace can be kept at a better accuracy, since the number of decision trees is larger, the calculation amount is increased, and the calculation time is consumed, the number of decision trees is preferably selected to be 100 for the electric magnesium melting furnace operation state classifier using three-phase voltage and current as data.
The above embodiments are implemented on the premise of the technical solution of the present invention, and detailed embodiments and specific operation procedures are given, but the scope of the present invention is not limited to the above embodiments. The methods used in the above examples are conventional methods unless otherwise specified.
Claims (4)
1. A method for identifying the running state of an electro-fused magnesia furnace based on random forests is characterized by comprising the following steps:
acquiring operation data of the electro-fused magnesia furnace through an intelligent ammeter, wherein the operation data comprises three-phase voltage and three-phase current data of the electro-fused magnesia furnace, determining a minute level as a selected time scale by performing multi-time scale analysis on the three-phase voltage and current data, and processing the capacity process data of the whole electro-fused magnesia;
step two, randomly generating a plurality of electric smelting magnesium furnace data training sets according to the processed electric smelting magnesium furnace operation data obtained in the step one; generating a corresponding decision tree by using each training set, testing a test set sample by using each decision tree to obtain the classification category of the corresponding operation state of the fused magnesia furnace, and finally adopting a voting mode to take the mode of the operation state of the fused magnesia obtained by voting as the final result of the identification of the operation state of the fused magnesia;
and step three, obtaining the adjustment quantity of the whole fused magnesia furnace group by utilizing the adjustment margin provided by the smelting stage of the fused magnesia furnace according to the identification result of the fused magnesia state obtained in the step two, and providing a basis for power system scheduling.
2. The method for identifying the operation state of the electric smelting magnesia furnace based on the random forest as claimed in claim 1, wherein in the step one, the process of performing multi-time scale analysis on the three-phase voltage and current data of the electric arc furnace comprises the following steps: acquiring operation data of a single electric magnesium melting furnace through an intelligent ammeter, performing data processing on three-phase voltage and three-phase current data by taking 1 second, 1 minute, 5 minutes and 30 minutes as time scales after second-level data of the whole production process are obtained, and determining the time scale of the data processing according to data characteristics and peak regulation requirements of an electric power system; and (3) preprocessing the three-phase voltage and current data by taking 1min as a time scale to obtain the characteristics of standard deviation, average value, worst value and the like of the data.
3. The method for identifying the operation state of the electric smelting magnesia furnace based on the random forest as claimed in claim 1, wherein: in the second step, firstly, a Bootstrap method is used for sampling for multiple times to generate n training sets S1，S2，…，SnAnd the other data groups are used as test set data; generating a corresponding decision tree C by using a training set generated by voltage electrical data1，C2，…，Cn(ii) a Taking a plurality of characteristics of three-phase voltage electric current data within 1min as input of a model, and taking fused magnesium in a non-smelting stage and a smelting stage as output of the model; the simulation result of the random forest classifier is analyzed to obtain the accuracy of the operation state of the fused magnesia furnace, so that the feasibility of the classification method is evaluated, and the accuracy of classification of the operation state of the fused magnesia furnace is calculated respectively when decision trees contained in the random forest are different.
4. The method for identifying the operation state of the electric smelting magnesia furnace based on the random forest as claimed in claim 1, wherein: and in the third step, determining the proportion of the fused magnesia furnaces in the smelting furnace state in the fused magnesia furnaces, and combining the adjustment margins of each single fused magnesia furnace to obtain the adjustment margin of the whole fused magnesia furnace group.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110555009.9A CN113705601A (en) | 2021-05-21 | 2021-05-21 | Method for identifying running state of electric smelting magnesium furnace based on random forest |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110555009.9A CN113705601A (en) | 2021-05-21 | 2021-05-21 | Method for identifying running state of electric smelting magnesium furnace based on random forest |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113705601A true CN113705601A (en) | 2021-11-26 |
Family
ID=78647987
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110555009.9A Pending CN113705601A (en) | 2021-05-21 | 2021-05-21 | Method for identifying running state of electric smelting magnesium furnace based on random forest |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113705601A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104331044A (en) * | 2014-10-17 | 2015-02-04 | 东北大学 | Electro-fused magnesia furnace power consumption remote monitoring system and method |
| CN104459306A (en) * | 2014-12-18 | 2015-03-25 | 东北大学 | Power demand quantity remote monitoring system and method for magnesium electrical smelting group furnaces |
| CN106959662A (en) * | 2017-05-10 | 2017-07-18 | 东北大学 | A kind of electric melting magnesium furnace unusual service condition identification and control method |
| CN107273920A (en) * | 2017-05-27 | 2017-10-20 | 西安交通大学 | A kind of non-intrusion type household electrical appliance recognition methods based on random forest |
| CN109634114A (en) * | 2018-11-28 | 2019-04-16 | 北京和隆软件有限公司 | A kind of metallurgy gas fired-boiler steam pipe network and gaspipe network control method for coordinating |
| US20190213446A1 (en) * | 2016-06-30 | 2019-07-11 | Intel Corporation | Device-based anomaly detection using random forest models |
| CN110533089A (en) * | 2019-08-19 | 2019-12-03 | 三峡大学 | Adaptive non-intrusion type load recognition methods based on random forest |
| CN112561176A (en) * | 2020-12-21 | 2021-03-26 | 深圳供电局有限公司 | Early warning method for online running state of electric power metering device |
-
2021
- 2021-05-21 CN CN202110555009.9A patent/CN113705601A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104331044A (en) * | 2014-10-17 | 2015-02-04 | 东北大学 | Electro-fused magnesia furnace power consumption remote monitoring system and method |
| CN104459306A (en) * | 2014-12-18 | 2015-03-25 | 东北大学 | Power demand quantity remote monitoring system and method for magnesium electrical smelting group furnaces |
| US20190213446A1 (en) * | 2016-06-30 | 2019-07-11 | Intel Corporation | Device-based anomaly detection using random forest models |
| CN106959662A (en) * | 2017-05-10 | 2017-07-18 | 东北大学 | A kind of electric melting magnesium furnace unusual service condition identification and control method |
| CN107273920A (en) * | 2017-05-27 | 2017-10-20 | 西安交通大学 | A kind of non-intrusion type household electrical appliance recognition methods based on random forest |
| CN109634114A (en) * | 2018-11-28 | 2019-04-16 | 北京和隆软件有限公司 | A kind of metallurgy gas fired-boiler steam pipe network and gaspipe network control method for coordinating |
| CN110533089A (en) * | 2019-08-19 | 2019-12-03 | 三峡大学 | Adaptive non-intrusion type load recognition methods based on random forest |
| CN112561176A (en) * | 2020-12-21 | 2021-03-26 | 深圳供电局有限公司 | Early warning method for online running state of electric power metering device |
Non-Patent Citations (3)
| Title |
|---|
| JIE MEI 等: "Random Forest Based Adaptive Non-Intrusive Load Identification", 《2014 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS》 * |
| 李鸿鑫等: "基于随机森林的三相不平衡配电网损耗计算研究", 《自动化与仪表》 * |
| 邢伟 等: "IMBSE融合AFS-DBN模型的高压断路器故障诊断", 《组合机床与自动化加工技术》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109185917B (en) | Boiler combustion state online diagnosis method and system based on flame intensity signal | |
| CN106992551B (en) | Photovoltaic inversion controller parameter discrimination method based on fuzzy C-mean algorithm and differential evolution hybrid algorithm | |
| CN109376944A (en) | The construction method and device of intelligent electric meter prediction model | |
| CN113076985A (en) | Power consumer load identification method and device and computer readable medium | |
| CN113627671A (en) | SOH prediction calculation method for single battery in energy storage scene | |
| CN111275204B (en) | Transformer state identification method based on hybrid sampling and ensemble learning | |
| CN109342279A (en) | Mixing flexible measurement method based on grinding mechanism and neural network | |
| CN106835200A (en) | Aluminum electrolysis cell region control system | |
| CN109921462B (en) | New energy consumption capability assessment method and system based on LSTM | |
| CN101598927B (en) | Control system of soda carbonization technique based on neural network and control method thereof | |
| CN107679615A (en) | Transformer Method of Sample Selection based on improved adaptive GA-IAGA | |
| CN113705601A (en) | Method for identifying running state of electric smelting magnesium furnace based on random forest | |
| CN111416165B (en) | Liquid metal battery charging method and system | |
| CN112364941A (en) | New energy station frequency characteristic detection method, device and system | |
| CN111965442A (en) | Energy internet fault diagnosis method and device under digital twin environment | |
| CN112260650A (en) | Photovoltaic panel fault detection method based on difference characteristic analysis technology | |
| CN116561692A (en) | Dynamic update real-time measurement data detection method | |
| Zeng et al. | Diagnosis System for Alumina Reduction Based on BP Neural Network. | |
| CN110415769A (en) | The design method of the low activation steel of lower machine learning is instructed based on physical metallurgy | |
| Peng et al. | Grade Prediction of Froth Flotation Based on Multistep Fusion Transformer Model | |
| CN112686443A (en) | Photovoltaic power generation prediction method based on artificial intelligence | |
| CN112488410A (en) | Production equipment performance optimization method and device based on equipment comprehensive efficiency | |
| Chao et al. | CNN-LSTM-based Prediction of the Anode Effect in Aluminum Electrolytic Cell | |
| CN114861808B (en) | Intelligent sorting method for variable load test data of hydroelectric generating set | |
| Yang et al. | Data-driven Method of Renewable Energy Based on Generative Adversarial Networks and EnergyPLAN |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211126 |
|
| RJ01 | Rejection of invention patent application after publication |