CN114239421A - Method and system for predicting coal powder combustion characteristic parameters based on BP neural network - Google Patents
Method and system for predicting coal powder combustion characteristic parameters based on BP neural network Download PDFInfo
- Publication number
- CN114239421A CN114239421A CN202210009292.XA CN202210009292A CN114239421A CN 114239421 A CN114239421 A CN 114239421A CN 202210009292 A CN202210009292 A CN 202210009292A CN 114239421 A CN114239421 A CN 114239421A
- Authority
- CN
- China
- Prior art keywords
- neural network
- training
- ignition
- characteristic parameters
- pulverized coal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
Abstract
The invention discloses a method and a system for predicting coal dust combustion characteristic parameters based on a BP neural network, wherein the method comprises the following steps: s1, establishing a single-particle ignition model by coupling a pulverized coal chemical infiltration pyrolysis model and a gas phase chemical reaction mechanism; s2, generating a plurality of different working condition groups within a certain reasonable range of each variable, and calculating ignition delay time and ignition modes corresponding to the working condition groups by adopting a single-particle ignition model; s3, taking data obtained by calculation of a plurality of working condition groups as a sample data set, dividing the sample data set into a training set, a verification set and a test set, and establishing a BP neural network; s4, training the BP neural network by using the training set to obtain a trained BP neural network; and S5, carrying out simulation prediction on the test set by using the trained BP neural network, and outputting the prediction result of the neural network. Based on a large amount of experimental and data simulation data, a BP neural network is trained, and the coal powder combustion process is quickly and accurately predicted.
Description
Technical Field
The invention relates to the technical field of combustion, in particular to a pulverized coal combustion characteristic parameter prediction method and a pulverized coal combustion characteristic parameter prediction system based on a BP neural network.
Background
The acquisition of the characteristic parameters of the pulverized coal combustion process plays a key role in further understanding the stability of the combustion process. On one hand, the development of the measurement technology provides a more advanced and reliable means for monitoring the coal powder combustion process, and on the other hand, the advanced numerical simulation calculation technology also provides a digital prediction way for coal powder combustion. However, since the pulverized coal combustion process is a transient, high-temperature, multi-phase, multi-component process, high computational cost is often required to achieve high prediction accuracy for the process.
With the development of data analysis means, advanced neural network analysis methods are widely applied to the fields of mathematics, engineering and the like. The data analysis method is applied to a complex pulverized coal combustion process, a BP neural network suitable for pulverized coal combustion characteristic parameter prediction is obtained through training based on a large amount of experiment and data simulation data, rapid and accurate prediction of the pulverized coal combustion process is achieved, and the method has important significance for achieving intelligentization and digitization of pulverized coal combustion.
Disclosure of Invention
The invention aims to provide a coal powder combustion characteristic parameter prediction method and system based on a BP neural network, which are used for simplifying a coal powder combustion stability prediction process, realizing intellectualization and digitalization of coal powder combustion and improving combustion efficiency.
In order to solve the technical problem, an embodiment of the present invention provides a pulverized coal combustion characteristic parameter prediction method based on a BP neural network, including:
s1, establishing a single-particle ignition model by coupling a pulverized coal chemical infiltration pyrolysis model and a gas phase chemical reaction mechanism;
s2, generating a plurality of different working condition groups within a certain reasonable range of each variable, and calculating ignition delay time and ignition modes corresponding to the working condition groups by adopting the single-particle ignition model;
s3, taking data obtained by calculation of the working condition groups as a sample data set, dividing the sample data set into a training set, a verification set and a test set, and establishing a BP neural network;
s4, training the BP neural network by using the training set to obtain a trained BP neural network;
and S5, performing simulation prediction on the test set by using the trained BP neural network, and outputting a prediction result of the neural network.
Wherein, after the S4, the method further comprises:
and S6, quantitatively analyzing the influence weight of each input variable by adopting a multi-factor weight analysis method, and obtaining and outputting the influence rule of each key influence factor on the coal powder combustion characteristic parameters.
Wherein the S6 includes:
and extracting the input-implicit matrix and the output-implicit matrix of the trained BP neural network, obtaining the influence proportion of different variables on the output parameters by utilizing a multi-factor weight analysis algorithm, and obtaining key parameters by comparing and selecting.
Wherein the S2 includes:
based on the single-particle pulverized coal ignition model, a variable control method is adoptedStudy on different ambient temperatures T and oxygen concentrations fO2Pressure p, carbon dioxide concentration fCO2Water vapor concentration fH2OThe turbulence intensity I, the volatile content V in the characteristics of the particles, and the particle size d, the ignition delay time of the pulverized coal particles and the change rule of the ignition mode characteristic parameters.
Wherein the variable is used as an input parameter of the network, and the ignition delay time t is usedigAnd the ignition mode delta t is used as a neural network output parameter, and the BP neural network is established by adopting a network structure of a single-layer hidden layer.
Wherein the S3 includes:
performing linear normalization processing on the sample data set;
and setting characteristic parameters of the BP neural network, wherein the characteristic parameters comprise training times, learning rate, training targets and momentum factors.
Wherein the S4 includes:
training the BP neural network by utilizing the training set based on a gradient search algorithm;
adjusting the number of nodes of the hidden layer, respectively training to obtain MSE and R values of a neural network verification set under different hidden layer node numbers, and selecting a network structure corresponding to the minimum mean square error MSE and the maximum multiple decision coefficient R value as the training completion BP neural network.
Besides, in an embodiment of the present application, a pulverized coal combustion characteristic parameter prediction system based on a BP neural network is further provided, including:
the model establishing module is used for establishing a single-particle ignition model by coupling a pulverized coal chemical infiltration pyrolysis model and a gas phase chemical reaction mechanism;
the sample data acquisition module is used for generating a plurality of different working condition groups within a certain reasonable range of each variable, and calculating ignition delay time and ignition modes corresponding to the working condition groups by adopting the single-particle ignition model;
the BP neural network establishing module is used for taking data obtained by calculation of the working condition groups as a sample data set, dividing the sample data set into a training set, a verification set and a test set, and establishing a BP neural network;
the training module is used for training the BP neural network by using the training set to obtain a trained BP neural network;
and the prediction module is used for carrying out simulation prediction on the test set by utilizing the trained BP neural network and outputting a prediction result of the neural network.
The system also comprises a characteristic parameter acquisition module connected with the training module and used for carrying out quantitative analysis on the influence weight of each input variable by adopting a multi-factor weight analysis method, and acquiring and outputting the influence rule of each key influence factor on the pulverized coal combustion characteristic parameter.
Compared with the prior art, the coal powder combustion characteristic parameter prediction method and the coal powder combustion characteristic parameter prediction system based on the BP neural network have the following advantages:
according to the coal powder combustion characteristic parameter prediction method and system based on the BP neural network, the data analysis method is applied to the complex coal powder combustion process, the BP neural network suitable for coal powder combustion characteristic parameter prediction is obtained through training based on a large amount of experiment and data simulation data, the coal powder combustion process is rapidly and accurately predicted, the method and system have important significance for achieving intelligentization and digitization of coal powder combustion, and the coal powder combustion efficiency is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a schematic step flow diagram of a coal dust combustion characteristic parameter prediction method based on a BP neural network according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of another embodiment of a pulverized coal combustion characteristic parameter prediction method based on a BP neural network according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a specific implementation of a pulverized coal combustion characteristic parameter prediction system based on a BP neural network according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-3, fig. 1 is a schematic flowchart illustrating steps of a coal powder combustion characteristic parameter prediction method based on a BP neural network according to an embodiment of the present invention; fig. 2 is a schematic structural diagram of another embodiment of a pulverized coal combustion characteristic parameter prediction method based on a BP neural network according to an embodiment of the present invention; fig. 3 is a schematic structural diagram of a specific implementation of a pulverized coal combustion characteristic parameter prediction system based on a BP neural network according to an embodiment of the present invention.
In a specific embodiment, the method for predicting the coal powder combustion characteristic parameters based on the BP neural network comprises the following steps:
s1, establishing a single-particle ignition model by coupling a pulverized coal chemical infiltration pyrolysis model and a gas phase chemical reaction mechanism;
s2, generating a plurality of different working condition groups within a certain reasonable range of each variable, and calculating ignition delay time and ignition modes corresponding to the working condition groups by adopting the single-particle ignition model;
s3, taking data obtained by calculation of the working condition groups as a sample data set, dividing the sample data set into a training set, a verification set and a test set, and establishing a BP neural network;
s4, training the BP neural network by using the training set to obtain a trained BP neural network;
and S5, performing simulation prediction on the test set by using the trained BP neural network, and outputting a prediction result of the neural network.
By applying the data analysis method to the complex pulverized coal combustion process and training to obtain the BP neural network suitable for pulverized coal combustion characteristic parameter prediction based on a large amount of experiments and data simulation data, the rapid and accurate prediction of the pulverized coal combustion process is realized, the method has important significance for realizing intelligentization and digitization of pulverized coal combustion, and is beneficial to improving the combustion efficiency of pulverized coal.
According to the method, the environmental characteristic conditions and the coal dust particle characteristic parameters are selected as input parameters, namely independent variables, according to model calculation results and experimental results. And selecting concerned coal powder combustion characteristic parameters as dependent variables, and establishing a mapping relation between the independent variables and the dependent variables through a BP neural network. Selecting characteristic parameters representing ignition stability based on literature research and experimental data: ignition delay time (t)ig) And an ignition pattern (Δ t) as a dependent variable, wherein tig＝min[thomo,thetero]，Δt＝thomo-thetero，thomoRepresents the calculated homogeneous (gas phase) ignition time based on the single particle model, and theteroIt represents a heterogeneous (particulate phase) ignition delay time.
Selecting an environment variable: temperature T (K), oxygen concentration fO2Pressure p (atm), carbon dioxide concentration fCO2Water vapor concentration fH2OTurbulence intensity I, and particle self characteristics: volatile content V (%), particle size d (. mu.m), as independent variables. The method is characterized in that due to the lack of detailed research on the influence of turbulence intensity on the ignition characteristic of the pulverized coal at present, only partial work compares the difference of ignition behaviors under laminar flow and turbulent flow working conditions, and the influence of turbulence degree on the difference is not deeply discussed, so that the switching value of 0 and 1 are adopted for quantifying the turbulence intensity in the invention, namely, in the laminar flow working condition, the value of the turbulence intensity variable is 0, and in the turbulent flow working condition, the value of the turbulence intensity variable is 1.
In order to further analyze the influence ratios of the input variables on the output variables, in an embodiment, after the step S4, the method further includes:
and S6, quantitatively analyzing the influence weight of each input variable by adopting a multi-factor weight analysis method, and obtaining and outputting the influence rule of each key influence factor on the coal powder combustion characteristic parameters.
Specifically, the S6 includes:
and extracting the input-implicit matrix and the output-implicit matrix of the trained BP neural network, obtaining the influence proportion of different variables on the output parameters by utilizing a multi-factor weight analysis algorithm, and obtaining key parameters by comparing and selecting.
In the application, the extraction mode of the key parameters and the pulverized coal combustion characteristic parameters is not limited, a multi-factor weight analysis method is not necessarily adopted, and other modes can be adopted.
The type of the variable is not limited in this application, and in one embodiment, the S2 includes:
based on the single-particle pulverized coal ignition model, different environmental temperatures T and oxygen concentrations f are researched by controlling a variable methodO2Pressure p, carbon dioxide concentration fCO2Water vapor concentration fH2OThe turbulent intensity I, the volatile content V (%) in the characteristics of the particles, the particle diameter d (mum), the ignition delay time of the pulverized coal particles and the change rule of the characteristic parameters of the ignition mode.
The parameters described above are included in this application but are not limited thereto.
In the application, the change rule of the ignition delay time of the pulverized coal particles and the change rule of the characteristic parameters of the ignition mode can adopt a curve, a chart or other modes, and the application does not limit the change rule.
In the present application, the establishment method of the BP neural network is not limited, and in one embodiment, the variable is used as an input parameter of the network, and the ignition delay time t is used as an input parameter of the networkigAnd the ignition mode delta t is used as a neural network output parameter, and the BP neural network is established by adopting a network structure of a single-layer hidden layer.
This application includes, but is not limited to, the use of the above-described BP neural network architecture.
To avoid instability in the network training process due to differences in the magnitude of each variable, in one embodiment, the S3 includes:
performing linear normalization processing on the sample data set;
and setting characteristic parameters of the BP neural network, wherein the characteristic parameters comprise training times, learning rate, training targets and momentum factors.
In the application, the normalization mode is not limited, and the type of the characteristic parameter is not limited.
In the present application, the training mode after creating the BP neural network obtains a final trained BP neural network, in an embodiment, the S4 includes:
training the BP neural network by utilizing the training set based on a gradient search algorithm;
adjusting the number of nodes of the hidden layer, respectively training to obtain MSE and R values of a neural network verification set under different hidden layer node numbers, and selecting a network structure corresponding to the minimum mean square error MSE and the maximum multiple decision coefficient R value as the training completion BP neural network.
The method includes, but is not limited to, training the BP neural network by using the training set based on a gradient search algorithm, and other algorithms may be adopted.
The application does not limit the specific process:
in one private situation, based on a gradient search algorithm, setting an initial hidden layer node number 3, training the neural network by using training set data, gradually increasing the hidden layer node number until the node number is 13 as an upper limit, and respectively obtaining the training effect of the neural network.
Besides, in an embodiment of the present application, a pulverized coal combustion characteristic parameter prediction system based on a BP neural network is further provided, including:
the model building module 10 builds a single-particle ignition model by coupling a pulverized coal chemical infiltration pyrolysis model and a gas phase chemical reaction mechanism;
the sample data acquisition module 20 is configured to generate a plurality of different working condition groups within a certain reasonable range of each variable, and calculate an ignition delay time and an ignition mode corresponding to each working condition group by using the single-particle ignition model;
the BP neural network establishing module 30 is configured to use data obtained by calculation of the plurality of working condition groups as a sample data set, divide the sample data set into a training set, a verification set and a test set, and establish a BP neural network;
the training module 40 is used for training the BP neural network by using the training set to obtain a trained BP neural network;
and the prediction module 50 is used for carrying out simulation prediction on the test set by utilizing the trained BP neural network and outputting a prediction result of the neural network.
Since the pulverized coal combustion characteristic parameter prediction system based on the BP neural network is a system corresponding to the pulverized coal combustion characteristic parameter prediction method based on the BP neural network, the same beneficial effects are achieved, and details are not repeated in the application.
In order to further analyze the influence proportion of each input variable on the output variable, in one embodiment, the pulverized coal combustion characteristic parameter prediction system based on the BP neural network further includes a characteristic parameter acquisition module connected to the training module, and configured to perform quantitative analysis on the influence weight of each input variable by using a multi-factor weight analysis method, so as to obtain and output the influence rule of each key influence factor on the pulverized coal combustion characteristic parameter.
In the application, the training mode of the training module is not limited, in one embodiment, based on a gradient search algorithm, an initial hidden layer node number 3 is set, the neural network is trained by using training set data, the hidden layer node number is gradually increased until the node number is 13 as an upper limit, the training effects of the neural network are respectively obtained, the training results of the neural network under different hidden layer conditions are compared, and a network structure corresponding to a minimum mean square error MSE and a maximum multiple decision coefficient R value is selected to serve as a final training-completed BP neural network.
In summary, the method and the system for predicting the coal powder combustion characteristic parameters based on the BP neural network provided by the embodiments of the present invention apply the data analysis method to the complicated coal powder combustion process, train to obtain the BP neural network suitable for predicting the coal powder combustion characteristic parameters based on a large amount of experimental and data simulation data, and implement the rapid and accurate prediction of the coal powder combustion process, have an important meaning for implementing the intelligentization and digitization of the coal powder combustion, and are beneficial to improving the combustion efficiency of the coal powder.
The method and the system for predicting the coal powder combustion characteristic parameters based on the BP neural network are described in detail above. The principles and embodiments of the present invention are explained herein using specific examples, which are presented only to assist in understanding the method and its core concepts. It should be noted that, for those skilled in the art, it is possible to make various improvements and modifications to the present invention without departing from the principle of the present invention, and those improvements and modifications also fall within the scope of the claims of the present invention.
Claims (9)
1. A coal powder combustion characteristic parameter prediction method based on a BP neural network is characterized by comprising the following steps:
s1, establishing a single-particle ignition model by coupling a pulverized coal chemical infiltration pyrolysis model and a gas phase chemical reaction mechanism;
s2, generating a plurality of different working condition groups within a certain reasonable range of each variable, and calculating ignition delay time and ignition modes corresponding to the working condition groups by adopting the single-particle ignition model;
s3, taking data obtained by calculation of the working condition groups as a sample data set, dividing the sample data set into a training set, a verification set and a test set, and establishing a BP neural network;
s4, training the BP neural network by using the training set to obtain a trained BP neural network;
and S5, performing simulation prediction on the test set by using the trained BP neural network, and outputting a prediction result of the neural network.
2. The method for predicting the coal powder combustion characteristic parameters based on the BP neural network as claimed in claim 1, wherein after the S4, the method further comprises:
and S6, quantitatively analyzing the influence weight of each input variable by adopting a multi-factor weight analysis method, and obtaining and outputting the influence rule of each key influence factor on the coal powder combustion characteristic parameters.
3. The method for predicting the pulverized coal combustion characteristic parameters based on the BP neural network as claimed in claim 2, wherein the S6 comprises:
and extracting the input-implicit matrix and the output-implicit matrix of the trained BP neural network, obtaining the influence proportion of different variables on the output parameters by utilizing a multi-factor weight analysis algorithm, and obtaining key parameters by comparing and selecting.
4. The method for predicting the pulverized coal combustion characteristic parameters based on the BP neural network as claimed in claim 3, wherein the S2 comprises:
based on the single-particle pulverized coal ignition model, different environmental temperatures T and oxygen concentrations f are researched by controlling a variable methodO2Pressure p, carbon dioxide concentration fCO2Water vapor concentration fH2OThe turbulence intensity I, the volatile content V in the characteristics of the particles, and the particle size d, the ignition delay time of the pulverized coal particles and the change rule of the ignition mode characteristic parameters.
5. The method for predicting the pulverized coal combustion characteristic parameters based on the BP neural network as claimed in claim 4, wherein the variables are used as input parameters of the network, and the ignition delay time t is usedigAnd the ignition mode delta t is used as a neural network output parameter, and the BP neural network is structurally established by adopting a network with a single hidden layer.
6. The method for predicting the pulverized coal combustion characteristic parameters based on the BP neural network as claimed in claim 5, wherein the S3 comprises:
performing linear normalization processing on the sample data set;
and setting characteristic parameters of the BP neural network, wherein the characteristic parameters comprise training times, learning rate, training targets and momentum factors.
7. The method for predicting the pulverized coal combustion characteristic parameters based on the BP neural network as claimed in claim 6, wherein the S4 comprises:
training the BP neural network by utilizing the training set based on a gradient search algorithm;
adjusting the number of nodes of the hidden layer, respectively training to obtain MSE and R values of a neural network verification set under different hidden layer node numbers, and selecting a network structure corresponding to the minimum mean square error MSE and the maximum multiple decision coefficient R value as the training completion BP neural network.
8. A pulverized coal combustion characteristic parameter prediction system based on a BP neural network is characterized by comprising:
the model establishing module is used for establishing a single-particle ignition model by coupling a pulverized coal chemical infiltration pyrolysis model and a gas phase chemical reaction mechanism;
the sample data acquisition module is used for generating a plurality of different working condition groups within a certain reasonable range of each variable, and calculating ignition delay time and ignition modes corresponding to the working condition groups by adopting the single-particle ignition model;
the BP neural network establishing module is used for taking data obtained by calculation of the working condition groups as a sample data set, dividing the sample data set into a training set, a verification set and a test set, and establishing a BP neural network;
the training module is used for training the BP neural network by using the training set to obtain a trained BP neural network;
and the prediction module is used for carrying out simulation prediction on the test set by utilizing the trained BP neural network and outputting a prediction result of the neural network.
9. The system for predicting the coal powder combustion characteristic parameters based on the BP neural network according to claim 8, further comprising a characteristic parameter obtaining module connected to the training module, wherein the characteristic parameter obtaining module is configured to perform quantitative analysis on the influence weight of each input variable by using a multi-factor weight analysis method, obtain an influence rule of each key influence factor on the coal powder combustion characteristic parameters, and output the influence rule.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210009292.XA CN114239421A (en) | 2022-01-05 | 2022-01-05 | Method and system for predicting coal powder combustion characteristic parameters based on BP neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210009292.XA CN114239421A (en) | 2022-01-05 | 2022-01-05 | Method and system for predicting coal powder combustion characteristic parameters based on BP neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114239421A true CN114239421A (en) | 2022-03-25 |
Family
ID=80745841
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210009292.XA Pending CN114239421A (en) | 2022-01-05 | 2022-01-05 | Method and system for predicting coal powder combustion characteristic parameters based on BP neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114239421A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115762653A (en) * | 2022-11-11 | 2023-03-07 | 哈尔滨工程大学 | Fuel combustion mechanism optimization method based on evolutionary algorithm and deep learning |
| CN117079737A (en) * | 2023-10-17 | 2023-11-17 | 深圳市永霖科技有限公司 | Polishing solution prediction method and device based on component analysis |
-
2022
- 2022-01-05 CN CN202210009292.XA patent/CN114239421A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115762653A (en) * | 2022-11-11 | 2023-03-07 | 哈尔滨工程大学 | Fuel combustion mechanism optimization method based on evolutionary algorithm and deep learning |
| CN115762653B (en) * | 2022-11-11 | 2023-08-11 | 哈尔滨工程大学 | Fuel combustion mechanism optimization method based on evolutionary algorithm and deep learning |
| CN117079737A (en) * | 2023-10-17 | 2023-11-17 | 深圳市永霖科技有限公司 | Polishing solution prediction method and device based on component analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114239421A (en) | Method and system for predicting coal powder combustion characteristic parameters based on BP neural network | |
| CN102663219B (en) | Fuel cell output prediction method and system based on mixing model | |
| CN108897286B (en) | Fault detection method based on distributed nonlinear dynamic relation model | |
| CN105784556B (en) | A kind of air fine particles PM based on Self-organized Fuzzy Neural Network2.5Flexible measurement method | |
| Aguirre et al. | On the interpretation and practice of dynamical differences between Hammerstein and Wiener models | |
| CN110957011B (en) | Online production parameter estimation method of continuous stirring reactor under unknown time-varying measurement noise | |
| CN112488145A (en) | NO based on intelligent methodxOnline prediction method and system | |
| CN106094526B (en) | A kind of Generalized Prediction engineering is applied to the method for denitration control system | |
| CN114583767A (en) | Data-driven wind power plant frequency modulation response characteristic modeling method and system | |
| CN110763830B (en) | Method for predicting content of free calcium oxide in cement clinker | |
| Ji et al. | Application of the improved the ELM algorithm for prediction of blast furnace gas utilization rate | |
| CN104865228A (en) | Quantitative laser-induced breakdown spectroscopy (LIBS) detecting method based on fusion entropy optimization | |
| CN113281229A (en) | Multi-model self-adaptive atmosphere PM based on small samples2.5Concentration prediction method | |
| KR102484587B1 (en) | Method to Build a Reduced Order Model based on Eigenmodes from Simulation and Eigenvalues based on Machine Learning by Measurement Data | |
| CN105241823A (en) | Thermal power plant flue gas spectral quantitative analysis method based on sparse representation | |
| CN108132399B (en) | Simplified interpolation method for improving electric energy quality analysis precision of digital substation | |
| CN113111588B (en) | NO of gas turbine X Emission concentration prediction method and device | |
| CN113628689A (en) | Intelligent prediction method and device for pulverized coal combustion characteristic parameters and storage medium | |
| CN106773712B (en) | Double feedback robust self-adaptation control methods and its Control system architecture | |
| CN113486553A (en) | Complex equipment reliability analysis method based on Thiessen polygon area division | |
| CN111507003A (en) | Method for predicting key variables of debutanizer based on quality-related dynamic characteristic extraction | |
| Jakubiec et al. | Error model application in neural reconstruction of nonlinear sensor input signal | |
| CN115938498A (en) | Multi-step prediction method for carbon oxide content of methanation furnace based on multivariable deep reconstruction neural network | |
| CN111144205B (en) | Method for identifying gap nonlinear system in spacecraft structure | |
| CN112784514B (en) | Equivalent circuit-based modeling method for nano gas sensor |
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 |