CN111582608A - Fly ash carbon content prediction method, device, equipment and readable storage medium - Google Patents
Fly ash carbon content prediction method, device, equipment and readable storage medium Download PDFInfo
- Publication number
- CN111582608A CN111582608A CN202010476946.0A CN202010476946A CN111582608A CN 111582608 A CN111582608 A CN 111582608A CN 202010476946 A CN202010476946 A CN 202010476946A CN 111582608 A CN111582608 A CN 111582608A
- Authority
- CN
- China
- Prior art keywords
- carbon content
- fly ash
- network model
- long
- memory network
- 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
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 title claims abstract description 196
- 229910052799 carbon Inorganic materials 0.000 title claims abstract description 196
- 239000010881 fly ash Substances 0.000 title claims abstract description 192
- 238000000034 method Methods 0.000 title claims abstract description 38
- 230000015654 memory Effects 0.000 claims abstract description 53
- 230000007787 long-term memory Effects 0.000 claims abstract description 38
- 230000006403 short-term memory Effects 0.000 claims abstract description 38
- 238000010219 correlation analysis Methods 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 11
- 238000012937 correction Methods 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 abstract description 4
- 239000011159 matrix material Substances 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 238000010248 power generation Methods 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 239000003245 coal Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Primary Health Care (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a method, a device, equipment and a computer readable storage medium for predicting carbon content in fly ash, wherein the method comprises the following steps: determining an influence parameter of the carbon content of the fly ash, and establishing a long-term and short-term memory network model according to historical operating data corresponding to the influence parameter and a corresponding historical fly ash carbon content value; acquiring operation data corresponding to the influence parameters at the current moment; and obtaining the fly ash carbon content value at the current moment according to the operation data and the long-term and short-term memory network model. According to the technical scheme disclosed by the application, the long-short term memory network model is a time cycle neural network and can help the current decision by using historical information, so that the dynamic prediction of the carbon content of the fly ash can be realized by the established long-short term memory network model and the operation data of the influence parameters at the current moment, and the accuracy of the prediction of the carbon content of the fly ash can be improved.
Description
Technical Field
The present application relates to the field of thermal power generation technologies, and in particular, to a method, an apparatus, a device, and a computer-readable storage medium for predicting carbon content in fly ash.
Background
With the increasingly prominent environmental and energy problems, people have increasingly strict requirements on green energy, energy conservation, emission reduction and the like, and the key to realizing sustainable development is how to improve the utilization rate of coal energy and reduce pollution. The carbon content of the fly ash is used as one of main indexes of economic operation of a thermal power plant, and plays a key guiding role in improving the power generation efficiency and reducing the production cost.
At present, fly ash carbon content models are established by methods such as BP neural networks and support vector machines, and the fly ash carbon content prediction is realized by using the models, but the model performs fitting prediction on the fly ash carbon content by using operation at a certain moment, and the fly ash carbon content is a result of operation within a period of time, so that the method is difficult to meet the dynamic prediction of the fly ash carbon content, and the accuracy of the fly ash carbon content prediction can be reduced.
In summary, how to improve the accuracy of predicting the carbon content in the fly ash is a technical problem to be solved urgently by those skilled in the art.
Disclosure of Invention
In view of the above, an object of the present application is to provide a method, an apparatus, a device and a computer readable storage medium for predicting carbon content in fly ash, which are used to improve the accuracy of carbon content prediction in fly ash.
In order to achieve the above purpose, the present application provides the following technical solutions:
a fly ash carbon content prediction method comprises the following steps:
determining an influence parameter of the carbon content of the fly ash, and establishing a long-term and short-term memory network model according to historical operating data corresponding to the influence parameter and a corresponding historical fly ash carbon content value;
acquiring operation data corresponding to the influence parameters at the current moment;
and obtaining the fly ash carbon content value at the current moment according to the operation data and the long-short term memory network model.
Preferably, determining the parameters of influence of the carbon content of fly ash comprises:
determining the relevant parameters of the carbon content of the fly ash;
performing grey correlation analysis on historical related data corresponding to the related parameters and corresponding historical fly ash carbon content values to obtain grey correlation degrees of the related parameters and the fly ash carbon content;
and determining the relevant parameters of which the grey correlation degrees are greater than a preset value as the influence parameters of the fly ash carbon content.
Preferably, the establishing of the long-short term memory network model according to the historical operation data corresponding to the influence parameters and the corresponding historical fly ash carbon content value includes:
inputting the historical operating data into the long-short term memory network model to obtain a calculated value of the carbon content of the fly ash corresponding to the historical operating data;
and correcting the parameter values in the long-short term memory network model by using a gradient descent algorithm according to the calculated value of the carbon content of the fly ash and the carbon content value of the historical fly ash corresponding to the historical operating data until the precision of the long-short term memory network model reaches the preset precision.
Preferably, the modifying the parameter values in the long-short term memory network model by using a gradient descent algorithm comprises:
and correcting the parameter values in the long-term and short-term memory network model by using a BPTT gradient descent algorithm.
A fly ash carbon content prediction device comprises:
the establishing module is used for determining an influence parameter of the carbon content of the fly ash and establishing a long-term and short-term memory network model according to historical operating data corresponding to the influence parameter and a corresponding historical fly ash carbon content value;
the acquisition module is used for acquiring the operation data corresponding to the influence parameters at the current moment;
and the fly ash carbon content value obtaining module is used for obtaining the fly ash carbon content value at the current moment according to the operation data and the long-short term memory network model.
Preferably, the establishing module includes:
the determining unit is used for determining related parameters of the carbon content of the fly ash;
the grey correlation analysis unit is used for carrying out grey correlation analysis on historical related data corresponding to the related parameters and corresponding historical fly ash carbon content values to obtain grey correlation degrees of the related parameters and the fly ash carbon content;
and the influence parameter determining unit is used for determining the relevant parameters of which the grey correlation degrees are greater than the preset values as the influence parameters of the carbon content of the fly ash.
Preferably, the establishing module includes:
the input unit is used for inputting the historical operating data into the long-short term memory network model to obtain a calculated value of the carbon content of the fly ash corresponding to the historical operating data;
and the correction unit is used for correcting the parameter values in the long-short term memory network model by using a gradient descent algorithm according to the calculated value of the carbon content of the fly ash and the historical value of the carbon content of the fly ash corresponding to the historical operating data until the precision of the long-short term memory network model reaches the preset precision.
Preferably, the correction unit includes:
and the correcting subunit is used for correcting the parameter values in the long-term and short-term memory network model by using a BPTT gradient descent algorithm.
A fly ash carbon content prediction apparatus comprising:
a memory for storing a computer program;
a processor for implementing the steps of the fly ash carbon content prediction method according to any one of the above when executing the computer program.
A computer-readable storage medium, in which a computer program is stored, which computer program, when being executed by a processor, carries out the steps of the fly ash carbon content prediction method according to any one of the preceding claims.
The application provides a method, a device, equipment and a computer readable storage medium for predicting carbon content in fly ash, wherein the method comprises the following steps: determining an influence parameter of the carbon content of the fly ash, and establishing a long-term and short-term memory network model according to historical operating data corresponding to the influence parameter and a corresponding historical fly ash carbon content value; acquiring operation data corresponding to the influence parameters at the current moment; and obtaining the fly ash carbon content value at the current moment according to the operation data and the long-term and short-term memory network model.
According to the technical scheme disclosed by the application, a long-short term memory network model is established according to historical operating data corresponding to the influence parameters of the carbon content of the fly ash and the carbon content value of the historical fly ash, the carbon content value of the fly ash at the current moment is obtained according to the corresponding operating data of the influence parameters of the carbon content of the fly ash at the current moment and the proposed long-short term memory network model, and as the long-short term memory network model is a time cycle neural network, the long-short term memory network model is not only relevant to the operating data at the current moment when the carbon content of the fly ash is predicted by using the model, but also relevant to the operating data a period of time before the current moment, namely the carbon content of the fly ash at the current moment obtained by the long-short term memory network model is the result of operation within a period, therefore, compared with the existing method that the dynamic prediction of the fly ash carbon content cannot meet the requirement due to the fact that the carbon content of, therefore, the problem of prediction accuracy can be reduced, the dynamic prediction of the carbon content of the fly ash can be realized through the established long-short term memory network model and the operation data of the influence parameters at the current moment, and the accuracy of the prediction of the carbon content of the fly ash can be improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a flow chart of a method for predicting carbon content in fly ash according to an embodiment of the present disclosure;
fig. 2 is a schematic structural diagram of a device for predicting carbon content in fly ash according to an embodiment of the present disclosure;
fig. 3 is a schematic structural diagram of a fly ash carbon content prediction device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, 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 application.
Referring to fig. 1, which shows a flowchart of a method for predicting carbon content in fly ash provided in an embodiment of the present application, a method for predicting carbon content in fly ash provided in an embodiment of the present application may include:
s11: determining the influence parameters of the carbon content of the fly ash, and establishing a long-term and short-term memory network model according to the historical operating data corresponding to the influence parameters and the corresponding historical carbon content value of the fly ash.
When the fly ash carbon content is predicted, considering that a plurality of related parameters of the fly ash carbon content exist in the whole field, and the influence parameter which really influences the fly ash carbon content is only one part of the related parameters, therefore, in order to improve the accuracy of the prediction of the fly ash carbon content, the related parameters of the fly ash carbon content can be preliminarily determined through investigation and analysis of the influence factors of the fly ash carbon content, the influence parameter of the fly ash carbon content is determined from the related parameters, then, historical operation data corresponding to the influence parameters and corresponding historical fly ash carbon content values can be obtained, and a long-term and short-term memory network model can be established according to the historical operation data corresponding to the influence parameters and the corresponding historical carbon content values.
Therefore, in the application, the established long-short term memory network model can use historical operation data corresponding to the influence parameters to help predict the carbon content value of the fly ash at the current moment, so that the prediction of the carbon content of the fly ash is not only related to the operation at the current moment, but also related to the operation at the time before the current moment, thereby facilitating the dynamic prediction of the carbon content of the fly ash and further facilitating the improvement of the accuracy of the prediction of the carbon content of the fly ash.
S12: and acquiring the operation data corresponding to the influence parameters at the current moment.
After determining the influence parameters of the carbon content of the fly ash and establishing the long-term and short-term memory network model, the operation data corresponding to the determined influence parameters at the current moment can be obtained through measurement and other modes.
S13: and obtaining the fly ash carbon content value at the current moment according to the operation data and the long-term and short-term memory network model.
After the step S12 is completed, the operation data corresponding to the acquired influence parameters at the current time may be input into the established long-short term memory network model, so as to obtain a specific value corresponding to the carbon content of the fly ash at the current time through the long-short term memory network model, that is, the carbon content value of the fly ash at the current time.
According to the technical scheme disclosed by the application, a long-short term memory network model is established according to historical operating data corresponding to the influence parameters of the carbon content of the fly ash and the carbon content value of the historical fly ash, the carbon content value of the fly ash at the current moment is obtained according to the corresponding operating data of the influence parameters of the carbon content of the fly ash at the current moment and the proposed long-short term memory network model, and as the long-short term memory network model is a time cycle neural network, the long-short term memory network model is not only relevant to the operating data at the current moment when the carbon content of the fly ash is predicted by using the model, but also relevant to the operating data a period of time before the current moment, namely the carbon content of the fly ash at the current moment obtained by the long-short term memory network model is the result of operation within a period, therefore, compared with the existing method that the dynamic prediction of the fly ash carbon content cannot meet the requirement due to the fact that the carbon content of, therefore, the problem of prediction accuracy can be reduced, the dynamic prediction of the carbon content of the fly ash can be realized through the established long-short term memory network model and the operation data of the influence parameters at the current moment, and the accuracy of the prediction of the carbon content of the fly ash can be improved.
The method for predicting the carbon content of the fly ash provided by the embodiment of the application determines the influence parameters of the carbon content of the fly ash, and comprises the following steps:
determining the relevant parameters of the carbon content of the fly ash;
performing grey correlation analysis on historical related data corresponding to the related parameters and corresponding historical fly ash carbon content values to obtain grey correlation degrees of the related parameters and the fly ash carbon content;
and determining the relevant parameters of which the grey correlation degrees are greater than the preset values as the influence parameters of the carbon content of the fly ash.
The influence parameters of the carbon content of the fly ash can be screened from the related parameters by utilizing a grey correlation analysis method so as to reduce the input of noise and improve the accuracy of determining the influence parameters, thereby being convenient for improving the accuracy of predicting the carbon content of the fly ash. The specific process for determining the influence parameters of the carbon content of the fly ash comprises the following steps:
1) determining parameters relevant to the carbon content of fly ash, i.e. determining input parameters of a grey correlation analysis model
Preliminarily determining relevant parameters influencing the carbon content of the fly ash through investigation and analysis of factors influencing the carbon content of the fly ash, and taking historical relevant data corresponding to the relevant parameters and corresponding carbon content values of the historical fly ash as input parameters of a grey correlation analysis model;
2) performing grey correlation analysis on the determined input parameters to obtain grey correlation degree of each relevant parameter and fly ash carbon content
Forming a two-dimensional matrix by using the carbon content of the fly ash and historical data (including historical related data corresponding to the related parameters and corresponding historical fly ash carbon content values) of the related parameters in a period of time, wherein each row of the two-dimensional matrix is provided with a number of columns XiFor historical related data of the same related parameter in the time period, a first row number sequence X of the two-dimensional matrix0The first row of the two-dimensional matrix is a parameter array and the rest rows are comparison arrays for historical fly ash carbon content data corresponding to fly ash carbon content, and the data of the ith row and the kth column can be expressed as Xi(k)，k＝1,2,...,n；i＝1,2,...,m；
For each row and column X of the two-dimensional matrixiUtilization of each data in
Carrying out normalization processing; wherein the content of the first and second substances,
for each row and column XiNormalized result, Xi,min、Xi,maxThe minimum value and the maximum value in the corresponding row number sequence are obtained;
by using
Obtain the correlation coefficient ξ of each piece of datai(k) Wherein, P is a resolution coefficient, generally set to 0.5;
by using
Obtaining grey correlation degrees of all relevant parameters and fly ash carbon content;
3) determining influencing parameters of fly ash carbon content
According to the calculated grey correlation degree of each correlation parameter and the fly ash carbon content, the correlation parameters are screened, the correlation parameters with the grey correlation degree larger than a preset value are determined as the influence parameters of the fly ash carbon content, or the correlation parameters with the grey correlation degree in a preset percentage (specifically, the preset percentage when the grey correlation degrees are arranged in a descending order, for example, 40% or other percentages set according to actual conditions or experience) in a preset sequence are taken as the influence parameters of the fly ash carbon content.
Of course, besides screening the influence parameters of the fly ash carbon content from the relevant parameters by using a grey correlation analysis method, the influence parameters of the fly ash carbon content from the relevant parameters can be screened by using other correlation analysis methods.
The method for predicting carbon content in fly ash provided by the embodiment of the application establishes a long-term and short-term memory network model according to historical operating data corresponding to the influence parameters and corresponding historical fly ash carbon content values, and may include:
inputting historical operating data into the long-term and short-term memory network model to obtain a calculated value of the carbon content of the fly ash corresponding to the historical operating data;
and correcting parameter values in the long-short term memory network model by using a gradient descent algorithm according to the calculated value of the carbon content of the fly ash and the historical value of the carbon content of the fly ash corresponding to the historical operating data until the precision of the long-short term memory network model reaches the preset precision.
In the method for predicting the carbon content of the fly ash, the establishment process of the long-short term memory network model is as follows:
forgetting gate f for constructing long-short term memory network modeltIf the sigmoid function is selected as the activation function and is recorded as sigma, the expression of forgetting to record the gate is as follows:
ft＝σ(Wf·[ht-1,xt]+bf)
wherein, WfTo forget to remember the weight of the door, bfTo forget the offset value of the gate, ht-1Hidden state at time t-1, xtInput at time t;
the information adding door for constructing the long and short term memory network model comprises an input door layer itAnd a vector of candidate values
Two parts, selecting the tanh function as
Activation function of (2):
it＝σ(Wi·[ht-1,xt]+bi)
wherein, WiIs the weight of the input gate layer, biFor inputting the offset value of the gate layer, WCAs a weight of the candidate vector, bCAn offset value which is a candidate value vector;
renewal of cell state Ct：
An output gate for constructing a long-short term memory network model, comprising an output otAnd hidden state h at time tt：
ot＝σ(Wo·[ht-1,xt]+bo)
ht＝ot*tanh(Ct)
Wherein, WoAs a weight of the output gate, boIs the offset value of the output gate;
after the long-short term memory network model is constructed, historical operation data corresponding to the influence parameters and corresponding historical fly ash carbon content values are input into the constructed long-short term memory network model to establish a long-short term memory network modelShort term memory network model, specifically, with the first piece of data as t0Time data x0Carry into long and short term memory network model, for WC、Wi、WfCarrying out initialization assignment on h0Substituting the value of 0 into a long-short term memory network model, and calculating to obtain C0，h0And bring in t1Calculating the next moment at the moment, and repeating the steps to calculate the carbon content of the fly ash at each moment (specifically, o is the carbon content of the fly ash at each moment)t) And comparing the carbon content value with the carbon content value of the historical fly ash, and correcting the weight and the bias (namely the parameter values in the long-term and short-term memory network model) of each layer by using a gradient descent method until the precision of the long-term and short-term memory network model reaches the preset precision, so that the long-term and short-term memory network model for realizing the prediction of the carbon content of the fly ash can be obtained. The above-mentioned predetermined accuracy may be set according to experience or prediction of carbon content in fly ash.
After the long and short term memory network model for realizing the carbon content prediction of the fly ash is obtained, the operation data corresponding to the influence parameters at the current moment can be input into the obtained long and short term memory network model, so that the carbon content value o of the fly ash at the current moment can be obtained through the long and short term memory network modelt。
The method for predicting the carbon content of the fly ash provided by the embodiment of the application, which corrects the parameter values in the long-term and short-term memory network model by using the gradient descent algorithm, can comprise the following steps:
and correcting parameter values in the long-term and short-term memory network model by using a BPTT gradient descent algorithm.
When the parameter values of the long and short term memory network model are corrected, the parameter values in the long and short term memory network model can be corrected by using a Back Propagation Through Time (BPTT) gradient descent algorithm, so that the accuracy of the finally determined parameter values is improved, and the accuracy of the fly ash carbon content prediction is improved. Of course, other gradient descent algorithms may be used to correct the parameter values of the long-term and short-term network models.
An embodiment of the present application further provides a device for predicting carbon content in fly ash, see fig. 2, which shows a schematic structural diagram of the device for predicting carbon content in fly ash provided in the embodiment of the present application, and the device may include:
the establishing module 21 is used for determining an influence parameter of the carbon content of the fly ash, and establishing a long-term and short-term memory network model according to historical operating data corresponding to the influence parameter and a corresponding historical fly ash carbon content value;
the obtaining module 22 is configured to obtain operation data corresponding to the influence parameter at the current time;
and the fly ash carbon content value obtaining module 23 is used for obtaining the fly ash carbon content value at the current moment according to the operation data and the long-short term memory network model.
In the device for predicting carbon content in fly ash provided by the embodiment of the present application, the establishing module 21 may include:
the determining unit is used for determining related parameters of the carbon content of the fly ash;
the grey correlation analysis unit is used for carrying out grey correlation analysis on historical related data corresponding to the related parameters and corresponding historical fly ash carbon content values to obtain grey correlation degrees of the related parameters and fly ash carbon content;
and the influence parameter determining unit is used for determining the relevant parameters of which the grey correlation degrees are greater than the preset values as the influence parameters of the carbon content of the fly ash.
In the device for predicting carbon content in fly ash provided by the embodiment of the present application, the establishing module 21 may include:
the input unit is used for inputting the historical operating data into the long-term and short-term memory network model to obtain a calculated value of the carbon content of the fly ash corresponding to the historical operating data;
and the correction unit is used for correcting the parameter values in the long-short term memory network model by using a gradient descent algorithm according to the calculated value of the carbon content of the fly ash and the carbon content value of the historical fly ash corresponding to the historical operating data until the precision of the long-short term memory network model reaches the preset precision.
The device for predicting carbon content in fly ash provided by the embodiment of the application, the correction unit may include:
and the correcting subunit is used for correcting the parameter values in the long-term and short-term memory network model by using the BPTT gradient descent algorithm.
An embodiment of the present application further provides a device for predicting carbon content in fly ash, see fig. 3, which shows a schematic structural diagram of the device for predicting carbon content in fly ash provided in the embodiment of the present application, and the device may include:
a memory 31 for storing a computer program;
the processor 32, when executing the computer program stored in the memory 31, may implement the following steps:
determining an influence parameter of the carbon content of the fly ash, and establishing a long-term and short-term memory network model according to historical operating data corresponding to the influence parameter and a corresponding historical fly ash carbon content value; acquiring operation data corresponding to the influence parameters at the current moment; and obtaining the fly ash carbon content value at the current moment according to the operation data and the long-term and short-term memory network model.
An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored, and when the computer program is executed by a processor, the following steps may be implemented:
determining an influence parameter of the carbon content of the fly ash, and establishing a long-term and short-term memory network model according to historical operating data corresponding to the influence parameter and a corresponding historical fly ash carbon content value; acquiring operation data corresponding to the influence parameters at the current moment; and obtaining the fly ash carbon content value at the current moment according to the operation data and the long-term and short-term memory network model.
For a description of relevant parts in the device, the apparatus, and the computer-readable storage medium for predicting carbon content in fly ash provided in the embodiments of the present application, reference may be made to the detailed description of corresponding parts in the method for predicting carbon content in fly ash provided in the embodiments of the present application, and details are not repeated here.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Furthermore, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include elements inherent in the list. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element. In addition, parts of the above technical solutions provided in the embodiments of the present application, which are consistent with the implementation principles of corresponding technical solutions in the prior art, are not described in detail so as to avoid redundant description.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A fly ash carbon content prediction method is characterized by comprising the following steps:
determining an influence parameter of the carbon content of the fly ash, and establishing a long-term and short-term memory network model according to historical operating data corresponding to the influence parameter and a corresponding historical fly ash carbon content value;
acquiring operation data corresponding to the influence parameters at the current moment;
and obtaining the fly ash carbon content value at the current moment according to the operation data and the long-short term memory network model.
2. The method for predicting carbon content in fly ash according to claim 1, wherein determining the parameters affecting the carbon content in fly ash comprises:
determining the relevant parameters of the carbon content of the fly ash;
performing grey correlation analysis on historical related data corresponding to the related parameters and corresponding historical fly ash carbon content values to obtain grey correlation degrees of the related parameters and the fly ash carbon content;
and determining the relevant parameters of which the grey correlation degrees are greater than a preset value as the influence parameters of the fly ash carbon content.
3. The method of claim 2, wherein the step of building a long-term and short-term memory network model according to the historical operating data corresponding to the impact parameters and the corresponding historical fly ash carbon content values comprises:
inputting the historical operating data into the long-short term memory network model to obtain a calculated value of the carbon content of the fly ash corresponding to the historical operating data;
and correcting the parameter values in the long-short term memory network model by using a gradient descent algorithm according to the calculated value of the carbon content of the fly ash and the carbon content value of the historical fly ash corresponding to the historical operating data until the precision of the long-short term memory network model reaches the preset precision.
4. The method for predicting fly ash carbon content according to claim 3, wherein the step of modifying the parameter values in the long-short term memory network model by using a gradient descent algorithm comprises:
and correcting the parameter values in the long-term and short-term memory network model by using a BPTT gradient descent algorithm.
5. A fly ash carbon content prediction device is characterized by comprising:
the establishing module is used for determining an influence parameter of the carbon content of the fly ash and establishing a long-term and short-term memory network model according to historical operating data corresponding to the influence parameter and a corresponding historical fly ash carbon content value;
the acquisition module is used for acquiring the operation data corresponding to the influence parameters at the current moment;
and the fly ash carbon content value obtaining module is used for obtaining the fly ash carbon content value at the current moment according to the operation data and the long-short term memory network model.
6. The fly ash carbon content prediction apparatus according to claim 5, wherein the establishing module comprises:
the determining unit is used for determining related parameters of the carbon content of the fly ash;
the grey correlation analysis unit is used for carrying out grey correlation analysis on historical related data corresponding to the related parameters and corresponding historical fly ash carbon content values to obtain grey correlation degrees of the related parameters and the fly ash carbon content;
and the influence parameter determining unit is used for determining the relevant parameters of which the grey correlation degrees are greater than the preset values as the influence parameters of the carbon content of the fly ash.
7. The fly ash carbon content prediction apparatus according to claim 6, wherein the establishing module comprises:
the input unit is used for inputting the historical operating data into the long-short term memory network model to obtain a calculated value of the carbon content of the fly ash corresponding to the historical operating data;
and the correction unit is used for correcting the parameter values in the long-short term memory network model by using a gradient descent algorithm according to the calculated value of the carbon content of the fly ash and the historical value of the carbon content of the fly ash corresponding to the historical operating data until the precision of the long-short term memory network model reaches the preset precision.
8. The fly ash carbon content prediction apparatus according to claim 7, wherein the correction unit includes:
and the correcting subunit is used for correcting the parameter values in the long-term and short-term memory network model by using a BPTT gradient descent algorithm.
9. An apparatus for predicting carbon content in fly ash, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the fly ash carbon content prediction method according to any one of claims 1 to 4 when executing the computer program.
10. A computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, carries out the steps of the fly ash carbon content prediction method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010476946.0A CN111582608A (en) | 2020-05-29 | 2020-05-29 | Fly ash carbon content prediction method, device, equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010476946.0A CN111582608A (en) | 2020-05-29 | 2020-05-29 | Fly ash carbon content prediction method, device, equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111582608A true CN111582608A (en) | 2020-08-25 |
Family
ID=72122087
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010476946.0A Pending CN111582608A (en) | 2020-05-29 | 2020-05-29 | Fly ash carbon content prediction method, device, equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111582608A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112465241A (en) * | 2020-12-03 | 2021-03-09 | 华润电力技术研究院有限公司 | Thermal power generation fire coal heat loss prediction, device, equipment and storage medium |
| CN116992265A (en) * | 2023-09-22 | 2023-11-03 | 卡奥斯工业智能研究院(青岛)有限公司 | Carbon emission estimation method, apparatus, device, and storage medium |
| CN117849302A (en) * | 2024-03-08 | 2024-04-09 | 深圳市朗石科学仪器有限公司 | Multi-parameter water quality on-line monitoring method |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109670629A (en) * | 2018-11-16 | 2019-04-23 | 浙江蓝卓工业互联网信息技术有限公司 | Coal-burning boiler thermal efficiency forecast method based on shot and long term Memory Neural Networks |
-
2020
- 2020-05-29 CN CN202010476946.0A patent/CN111582608A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109670629A (en) * | 2018-11-16 | 2019-04-23 | 浙江蓝卓工业互联网信息技术有限公司 | Coal-burning boiler thermal efficiency forecast method based on shot and long term Memory Neural Networks |
Non-Patent Citations (3)
| Title |
|---|
| 崔锐等: "基于L-M算法优化BP神经网络的飞灰含碳量测量", 《山西电力》 * |
| 李佳鹤等: "基于LSTM神经网络的燃煤锅炉热效率预测方法", 《智能物联技术》 * |
| 许宁等: "改进型LSTM变形预测模型研究", 《江西理工大学学报》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112465241A (en) * | 2020-12-03 | 2021-03-09 | 华润电力技术研究院有限公司 | Thermal power generation fire coal heat loss prediction, device, equipment and storage medium |
| CN116992265A (en) * | 2023-09-22 | 2023-11-03 | 卡奥斯工业智能研究院(青岛)有限公司 | Carbon emission estimation method, apparatus, device, and storage medium |
| CN116992265B (en) * | 2023-09-22 | 2024-01-09 | 卡奥斯工业智能研究院(青岛)有限公司 | Carbon emission estimation method, apparatus, device, and storage medium |
| CN117849302A (en) * | 2024-03-08 | 2024-04-09 | 深圳市朗石科学仪器有限公司 | Multi-parameter water quality on-line monitoring method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111582608A (en) | Fly ash carbon content prediction method, device, equipment and readable storage medium | |
| CN111260030B (en) | A-TCN-based power load prediction method and device, computer equipment and storage medium | |
| JP5888640B2 (en) | Photovoltaic power generation prediction apparatus, solar power generation prediction method, and solar power generation prediction program | |
| CN111625516B (en) | Method, apparatus, computer device and storage medium for detecting data state | |
| CN110910004A (en) | Reservoir dispatching rule extraction method and system with multiple uncertainties | |
| CN112363896B (en) | Log abnormality detection system | |
| CN111461463B (en) | Short-term load prediction method, system and equipment based on TCN-BP | |
| CN110619389A (en) | Load prediction method and system of combined cooling heating and power system based on LSTM-RNN | |
| CN113852432B (en) | Spectrum Prediction Sensing Method Based on RCS-GRU Model | |
| CN112381673B (en) | Park electricity utilization information analysis method and device based on digital twin | |
| CN111030889B (en) | Network traffic prediction method based on GRU model | |
| CN110727593A (en) | Intelligent test case generation method and medium based on historical demand data mining | |
| CN110210656B (en) | Shared bicycle flow prediction method and system based on station behavior analysis | |
| CN113988477A (en) | Photovoltaic power short-term prediction method and device based on machine learning and storage medium | |
| CN113191564A (en) | Photovoltaic power prediction method and device and server | |
| CN112733997A (en) | Hydrological time series prediction optimization method based on WOA-LSTM-MC | |
| CN114282646B (en) | Optical power prediction method and system based on two-stage feature extraction and BiLSTM improvement | |
| CN114065653A (en) | Construction method of power load prediction model and power load prediction method | |
| CN116861793B (en) | Method for modeling thermal error of pelican algorithm optimized long-term and short-term memory network main shaft | |
| CN111985719A (en) | Power load prediction method based on improved long-term and short-term memory network | |
| CN114861980A (en) | BP-LSTM model-based carbon prediction method | |
| CN116960978A (en) | Offshore wind power prediction method based on wind speed-power combination decomposition reconstruction | |
| CN111984514B (en) | Log anomaly detection method based on Prophet-bLSTM-DTW | |
| CN117150409A (en) | Power consumption abnormality detection method | |
| CN116347504A (en) | Communication base station flow prediction method based on EMD-MWOA-LSTM |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200825 |