CN110763830B - Method for predicting content of free calcium oxide in cement clinker - Google Patents

Method for predicting content of free calcium oxide in cement clinker Download PDF

Info

Publication number
CN110763830B
CN110763830B CN201911232888.0A CN201911232888A CN110763830B CN 110763830 B CN110763830 B CN 110763830B CN 201911232888 A CN201911232888 A CN 201911232888A CN 110763830 B CN110763830 B CN 110763830B
Authority
CN
China
Prior art keywords
calcium oxide
free calcium
content
cement clinker
hidden layer
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201911232888.0A
Other languages
Chinese (zh)
Other versions
CN110763830A (en
Inventor
李凡军
李颖
王孝红
路士增
蒋萍
李实�
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
University of Jinan
Original Assignee
University of Jinan
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by University of Jinan filed Critical University of Jinan
Priority to CN201911232888.0A priority Critical patent/CN110763830B/en
Publication of CN110763830A publication Critical patent/CN110763830A/en
Application granted granted Critical
Publication of CN110763830B publication Critical patent/CN110763830B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • 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
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
    • G01N33/38—Concrete; ceramics; glass; bricks
    • G01N33/383—Concrete, cement
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
    • 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
    • G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
    • G06N3/061—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using biological neurons, e.g. biological neurons connected to an integrated circuit

Abstract

The invention discloses a method for predicting the content of free calcium oxide in cement clinker, which comprises the following steps: s1: collecting a cement clinker sample; s2: constructing a time sequence of free calcium oxide content of cement clinker; s3: performing time sequence decomposition on the time sequence of the content of free calcium oxide in the mud clinker based on an empirical mode decomposition method; s4: constructing input and output sample pairs required by a training feature extraction module; s5: training the feature extraction submodule, namely a modularized echo state neural network, and learning the multi-time scale features of the time sequence: s6: training the prediction module-echo state neural network: s7: and predicting the content of free calcium oxide in the clinker. The method predicts the content of free calcium oxide at the next moment based on off-line experimental data, and solves the problem of lag of laboratory measurement results; compared with the measurement method of an on-line analyzer, the method has low cost, and the measurement accuracy is less influenced by on-site smoke dust and actual working conditions.

Description

Method for predicting content of free calcium oxide in cement clinker
Technical Field
The invention relates to a method for predicting the content of free calcium oxide in cement clinker, and belongs to the technical field of cement production control.
Background
The content of clinker free calcium oxide in the cement calcination process is an important standard for measuring the cement quality, and the content of clinker free calcium oxide represents the residual degree after calcium oxide is combined with silicon oxide, aluminum oxide and iron oxide in the calcination of raw materials, and the strength of the cement clinker is directly influenced by the content of the calcium oxide. Free calcium oxide of cement clinker is one of important indexes for reflecting the quality of the cement clinker, and the content of the free calcium oxide in the clinker during the calcination process of the cement clinker needs to be controlled within a reasonable range. The real-time prediction of the content of free calcium oxide in clinker is crucial to the guarantee of the calcination quality of cement clinker and the optimization of the calcination process.
At present, most laboratories of cement factories manually measure the content of free calcium oxide in cement clinker, adopt a glycerol-mango alcohol system as an extraction solvent, generate alkaline glycerol with the free calcium, and titrate with a hexanol benzoate standard solution. The on-line analyzer measuring method utilizes the fact that after ethylene glycol reacts with free calcium oxide in cement clinker, the conductivity of a solution and the content of the free calcium oxide form a certain proportional relation, and the content of the free calcium oxide is indirectly obtained through conductivity measurement.
The chemical test method has large delay and cannot truly reflect the production condition in the rotary kiln, so that the quality of the clinker is difficult to be effectively controlled. The online analyzer measurement method has the advantages of high equipment cost and high maintenance cost, and the measurement accuracy is easily influenced by site smoke dust and actual working conditions.
Disclosure of Invention
Aiming at the defects of the method, the invention provides a method for predicting the content of free calcium oxide in cement clinker, which can accurately predict the free calcium oxide in cement clinker in real time.
The technical scheme adopted for solving the technical problems is as follows:
the embodiment of the invention provides a method for predicting the content of free calcium oxide in cement clinker, which comprises the following steps:
s1: collecting a cement clinker sample;
s2: constructing a time sequence of free calcium oxide content of cement clinker;
s3: performing time sequence decomposition on the time sequence of the content of free calcium oxide in the mud clinker based on an empirical mode decomposition method:
s4: constructing input and output sample pairs required by a training feature extraction module;
s5: training the feature extraction submodule, namely a modularized echo state neural network, and learning the multi-time scale features of the time sequence:
s6: training the prediction module-echo state neural network:
s7: and predicting the content of free calcium oxide in the clinker.
As a possible implementation manner of this embodiment, in step S1, the sampling period is 1 hour, n times of continuous sampling are performed to obtain cement clinker samples online, and laboratory offline detection is performed manually, and the content u of free calcium oxide in cement clinker is recorded1,u2,……,un。
As a possible implementation manner of this embodiment, in step S3, the process of performing time-series decomposition on the time series of the free calcium oxide content of the clinker includes the following steps:
s3.1: setting an initial characteristic sequence number p to be 0; let h0(t) U (t), U (t) is cement clinker free calcium oxide content time sequence, U (t) ut，t＝1,2,……,n；
S3.2: setting the initial cycle number q to be 0;
s3.3: updating the cycle number q to q + 1;
s3.4: finding out all extreme points of the time sequence U (t) of the content of free calcium oxide of the cement clinker;
s3.5: forming a lower envelope e for the minimum points by cubic spline interpolationmin(t) forming an upper envelope e for the maximamax(t)；
S3.6: calculating the mean of the extreme points:
Figure BDA0002302318500000021
s3.7: details of extraction:
dq(t)＝hp(t)-m(t)； (2)
s3.8: for detail signal dq(t) repeating steps S3.3 to S3.7 until a detail signal dq(t) has a mean value of 0;
s3.9: updating the characteristic sequence number p to p + 1;
s3.10: recording a feature sequence IMFp(t)；
S3.11: calculating a residual sequence:
hp(t)＝hp-1(t)-IMFp(t)； (3)
s3.12: to hp(t) repeating S3.2 to S3.11 until hp(t) is a monotonic function;
s3.13: let IMFp(t)＝hp(t)。
As a possible implementation manner of this embodiment, in step S4, the input/output sample pairs required for constructing the training feature extraction module are:
Ωi＝(U(t),IMFi(t)) (4)
wherein i is 1,2, …, p + 1; t is 1,2, …, n.
As a possible implementation manner of this embodiment, the step S5 specifically includes the following steps:
s5.1: setting an initial module number k to be 0;
s5.2: updating the number k of the modules to k + 1;
s5.3: setting module parameters: number of input neurons 1, number of output neurons 1, number of hidden layer neurons nkSpectral radius ρkDegree of sparsity spk；
S5.4: randomly generating a network input weight matrix with uniform distribution over an interval (-0.1,0.1)
Figure BDA0002302318500000031
S5.5: randomly generating sparsity sp with uniform distribution over the interval (-1,1)kOf (2) matrix
Figure BDA0002302318500000032
S5.6: computing matrices
Figure BDA0002302318500000033
Maximum eigenvalue of
Figure BDA0002302318500000034
S5.7: calculating hidden layer weight Wk：
Figure BDA0002302318500000035
S5.8: computing hidden layer neuron states:
Figure BDA0002302318500000041
where t is 1,2, L L, n, sk(0)＝0；
S5.9: constructing a hidden layer state matrix:
Figure BDA0002302318500000042
s5.10: calculating a network output weight matrix:
Figure BDA0002302318500000043
wherein
Figure BDA0002302318500000044
For the hidden layer state matrix HkThe transposed matrix of (2);
s5.11: and (3) calculating network output:
Figure BDA0002302318500000045
s5.12: repeating steps S5.2 to S5.11 until k ═ p + 1;
s5.13: collecting submodule output:
Figure BDA0002302318500000046
as a possible implementation manner of this embodiment, the step S6 includes the following steps:
s6.1: constructing network input I and reference output
Figure BDA0002302318500000047
Figure BDA0002302318500000048
Figure BDA0002302318500000049
S6.2: setting module parameters: number of input neurons p +1, number of output neurons 1, number of hidden layer neurons nRSpectral radius ρRDegree of sparsity spR；
S6.3: randomly generating a network input weight matrix with uniform distribution over an interval (-0.1,0.1)
Figure BDA00023023185000000410
S6.4: randomly generating sparsity sp with uniform distribution over the interval (-1,1)ROf (2) matrix
Figure BDA00023023185000000411
S6.5: computing matrices
Figure BDA00023023185000000412
Maximum eigenvalue of
Figure BDA00023023185000000413
S6.6: calculating hidden layer weight WR
Figure BDA0002302318500000051
S6.7: computing hidden layer neuron states sR(t)：
Figure BDA0002302318500000052
Wherein s isR(0)＝0；
S6.8: constructing a hidden layer state matrix HR：
Figure BDA0002302318500000053
S6.9: computing network output weight matrix
Figure BDA0002302318500000054
Figure BDA0002302318500000055
Wherein
Figure BDA0002302318500000056
For the hidden layer state matrix HRThe transposed matrix of (2).
As a possible implementation manner of this embodiment, the step S7 specifically includes: inputting the test sample into the trained feature extraction module, and outputting by the prediction module to obtain the free calcium oxide content of the cement clinker at the next moment.
The technical scheme of the embodiment of the invention has the following beneficial effects:
aiming at the problem of online prediction of the free calcium oxide content of the cement clinker, the invention designs an intelligent prediction method of the free calcium oxide content of the cement clinker based on time sequence decomposition and a neural network, and realizes accurate prediction of the free calcium oxide content of the cement clinker; the empirical mode decomposition and the modularized echo state are combined, a time series multi-time scale feature learning method is provided, the automatic extraction of the time series multi-time scale features is realized, and the free calcium oxide of the cement clinker can be accurately predicted in real time.
The method predicts the content of free calcium oxide at the next moment based on off-line experimental data, and solves the problem of lag of laboratory measurement results; compared with the measurement method of an on-line analyzer, the method has low cost, and the measurement accuracy is less influenced by on-site smoke dust and actual working conditions.
Description of the drawings:
FIG. 1 is a flow chart illustrating a method for predicting free calcium oxide content of cement clinker in accordance with an exemplary embodiment;
FIG. 2 is a diagram of a predictive model topology;
FIG. 3 is a comparison graph of predicted values and measured values;
fig. 4 is a prediction error map.
Detailed Description
The invention is further illustrated by the following examples in conjunction with the accompanying drawings:
in order to clearly explain the technical features of the present invention, the following detailed description of the present invention is provided with reference to the accompanying drawings. The following disclosure provides many different embodiments, or examples, for implementing different features of the invention. To simplify the disclosure of the present invention, the components and arrangements of specific examples are described below. Furthermore, the present invention may repeat reference numerals and/or letters in the various examples. This repetition is for the purpose of simplicity and clarity and does not in itself dictate a relationship between the various embodiments and/or configurations discussed. It should be noted that the components illustrated in the figures are not necessarily drawn to scale. Descriptions of well-known components and processing techniques and procedures are omitted so as to not unnecessarily limit the invention.
FIG. 1 is a flow chart illustrating a method for predicting free calcium oxide content of cement clinker according to an exemplary embodiment. As shown in fig. 1, a method for predicting the content of free calcium oxide in cement clinker provided by the embodiment of the present invention includes the following steps:
s1: collecting a cement clinker sample;
s2: constructing a time sequence of free calcium oxide content of cement clinker;
s3: performing time sequence decomposition on the time sequence of the content of free calcium oxide in the mud clinker based on an empirical mode decomposition method:
s4: constructing input and output sample pairs required by a training feature extraction module;
s5: training the feature extraction submodule, namely a modularized echo state neural network, and learning the multi-time scale features of the time sequence:
s6: training the prediction module-echo state neural network:
s7: and predicting the content of free calcium oxide in the clinker.
As a possible implementation manner of this embodiment, in step S1, the sampling period is 1 hour, n times of continuous sampling are performed to obtain cement clinker samples online, and laboratory offline detection is performed manually, and the content u of free calcium oxide in cement clinker is recorded1,u2,……,un。
As a possible implementation manner of this embodiment, in step S3, the process of performing time-series decomposition on the time series of the free calcium oxide content of the clinker includes the following steps:
s3.1: setting an initial characteristic sequence number p to be 0; let h0(t) U (t), U (t) is cement clinker free calcium oxide content time sequence, U (t) ut，t＝1,2,……,n；
S3.2: setting the initial cycle number q to be 0;
s3.3: updating the cycle number q to q + 1;
s3.4: finding out all extreme points of the time sequence U (t) of the content of free calcium oxide of the cement clinker;
s3.5: forming a lower envelope e for the minimum points by cubic spline interpolationmin(t) forming an upper envelope e for the maximamax(t)；
S3.6: calculating the mean of the extreme points:
Figure BDA0002302318500000071
s3.7: details of extraction:
dq(t)＝hp(t)-m(t)； (2)
s3.8: for detail signal dq(t) repeating steps S3.3 to S3.7 until a detail signal dq(t) has a mean value of 0;
s3.9: updating the characteristic sequence number p to p + 1;
s3.10: recording a feature sequence IMFp(t)；
S3.11: calculating a residual sequence:
hp(t)＝hp-1(t)-IMFp(t)； (3)
s3.12: to hp(t) repeating S3.2 to S3.11 until hp(t) is a monotonic function;
s3.13: let IMFp+1(t)＝hp(t)。
As a possible implementation manner of this embodiment, in step S4, the input/output sample pairs required for constructing the training feature extraction module are:
Ωi＝(U(t),IMFi(t)) (4)
wherein i is 1,2, …, p + 1; t is 1,2, …, n.
As a possible implementation manner of this embodiment, the step S5 specifically includes the following steps:
s5.1: setting an initial module number k to be 0;
s5.2: updating the number k of the modules to k + 1;
s5.3: setting module parameters: number of input neurons 1, number of output neurons 1, number of hidden layer neurons nkSpectral radius ρkDegree of sparsity spk；
S5.4: randomly generating a network input weight matrix with uniform distribution over an interval (-0.1,0.1)
Figure BDA0002302318500000081
S5.5: randomly generating sparsity sp with uniform distribution over the interval (-1,1)kOf (2) matrix
Figure BDA0002302318500000082
S5.6: computing matrices
Figure BDA0002302318500000083
Maximum eigenvalue of
Figure BDA0002302318500000084
S5.7: calculating hidden layer weight Wk：
Figure BDA0002302318500000085
S5.8: computing hidden layer neuron states:
Figure BDA0002302318500000086
wherein t is 1,2, … …, n; s, sk(0)＝0；
S5.9: constructing a hidden layer state matrix:
Figure BDA0002302318500000087
s5.10: calculating a network output weight matrix:
Figure BDA0002302318500000088
wherein
Figure BDA0002302318500000089
For the hidden layer state matrix HkThe transposed matrix of (2);
s5.11: and (3) calculating network output:
Figure BDA00023023185000000810
s5.12: repeating steps S5.2 to S5.11 until k ═ p + 1;
s5.13: collecting submodule output:
Figure BDA0002302318500000091
as a possible implementation manner of this embodiment, the step S6 includes the following steps:
s6.1: constructing network input I and reference output
Figure BDA0002302318500000092
Figure BDA0002302318500000093
Figure BDA0002302318500000094
S6.2: setting module parameters: number of input neurons p +1, number of output neurons 1, number of hidden layer neurons nRSpectral radius ρRDegree of sparsity spR；
S6.3: randomly generating a network input weight matrix with uniform distribution over an interval (-0.1,0.1)
Figure BDA0002302318500000095
S6.4: randomly generating sparsity sp with uniform distribution over the interval (-1,1)ROf (2) matrix
Figure BDA0002302318500000096
S6.5: computing matrices
Figure BDA0002302318500000097
Maximum eigenvalue of
Figure BDA0002302318500000098
S6.6: computing hidden layer weightsValue WR
Figure BDA0002302318500000099
S6.7: computing hidden layer neuron states sR(t)：
Figure BDA00023023185000000910
Wherein s isR(0)＝0；
S6.8: constructing a hidden layer state matrix HR：
Figure BDA00023023185000000911
S6.9: computing network output weight matrix
Figure BDA00023023185000000912
Figure BDA0002302318500000101
Wherein
Figure BDA0002302318500000102
For the hidden layer state matrix HRThe transposed matrix of (2).
As a possible implementation manner of this embodiment, the step S7 specifically includes: as shown in fig. 2, the test sample is input into the trained feature extraction module, and the output of the prediction module is the free calcium oxide content of the cement clinker at the next moment.
The present example employed 1000 sets of laboratory test data for a cement manufacturing enterprise, with the first 800 sets being used for training and the last 200 sets being used for testing. The test results are shown in fig. 3, X-axis: sample (one/hour), Y-axis: free calcium oxide content (%),. o is the predicted result, is the measured free calcium oxide content; the error between the model prediction result and the actually measured free calcium oxide content is shown in fig. 4, wherein the X axis: sample (one/hour), Y-axis: the difference between the model prediction result and the actually measured content of the free calcium oxide proves the effectiveness of the method.
The foregoing is only a preferred embodiment of the present invention, and it will be apparent to those skilled in the art that various modifications and improvements can be made without departing from the principle of the present invention, and these modifications and improvements are also considered to be within the scope of the present invention.

Claims (2)

1. A method for predicting the content of free calcium oxide in cement clinker is characterized by comprising the following steps:
s1: collecting a cement clinker sample;
s2: constructing a time sequence of free calcium oxide content of cement clinker;
s3: performing time sequence decomposition on the time sequence of the content of free calcium oxide in the cement clinker based on an empirical mode decomposition method:
s4: constructing input and output sample pairs required by a training feature extraction module;
s5: training the feature extraction submodule, namely a modularized echo state neural network, and learning the multi-time scale features of the time sequence:
s6: training the prediction module-echo state neural network:
s7: predicting the content of free calcium oxide in cement clinker;
in step S1, sampling period is 1 hour, continuously sampling n times to obtain cement clinker sample on line, and manually carrying out laboratory off-line detection, and recording cement clinker free calcium oxide content u1,u2,……,un；
In step S3, the process of performing time-series decomposition on the time series of the content of free calcium oxide in the clinker comprises the following steps:
s3.1: setting an initial characteristic sequence number p to be 0; let h0(t) U (t), U (t) is cement clinker free calcium oxide content time sequence, U (t) ut，t＝1,2,……,n；
S3.2: setting the initial cycle number q to be 0;
s3.3: updating the cycle number q to q + 1;
s3.4: finding out all extreme points of the time sequence U (t) of the content of free calcium oxide in the cement clinker;
s3.5: forming a lower envelope e for the minimum points by cubic spline interpolationmin(t) forming an upper envelope e for the maximamax(t)；
S3.6: calculating the mean of the extreme points:
Figure FDA0003445237560000021
s3.7: details of extraction:
dq(t)＝hp(t)-m(t)； (2)
s3.8: for detail signal dq(t) repeating steps S3.3 to S3.7 until the detail signal dq(t) has a mean value of 0;
s3.9: updating the characteristic sequence number p to p + 1;
s3.10: recording a feature sequence IMFp(t)；
S3.11: calculating a residual sequence:
hp(t)＝hp-1(t)-IMFp(t)； (3)
s3.12: to hp(t) repeating S3.2 to S3.11 until hp(t) is a monotonic function;
s3.13: let IMFp(t)＝hp(t)；
In step S4, the input/output sample pairs required for constructing the training feature extraction module are:
Ωi＝(U(t),IMFi(t)) (4)
wherein U (t) is a time series of the free calcium oxide content of the cement clinker, IMFi(t) is a signature sequence, i ═ 1,2, …, p + 1; t is 1,2, …, n;
the step S5 specifically includes the following steps:
s5.1: setting an initial module number k to be 0;
s5.2: updating the number k of the modules to k + 1;
s5.3: setting module parameters: number of input neurons 1, number of output neurons 1, number of hidden layer neurons nkSpectral radius ρkDegree of sparsity spk；
S5.4: randomly generating a network input weight matrix with uniform distribution over an interval (-0.1,0.1)
Figure FDA0003445237560000023
S5.5: randomly generating sparsity sp with uniform distribution over the interval (-1,1)kOf (2) matrix
Figure FDA0003445237560000022
S5.6: computing matrices
Figure FDA0003445237560000024
Maximum eigenvalue of
Figure FDA0003445237560000025
S5.7: calculating hidden layer weight Wk：
Figure FDA0003445237560000031
S5.8: computing hidden layer neuron states:
Figure FDA0003445237560000032
where t is 1,2, … …, n, sk(0)＝0；
S5.9: constructing a hidden layer state matrix:
Figure FDA0003445237560000033
s5.10: calculating a network output weight matrix:
Figure FDA0003445237560000034
wherein
Figure FDA0003445237560000039
For the hidden layer state matrix HkThe transposed matrix of (2);
s5.11: and (3) calculating network output:
Figure FDA00034452375600000310
s5.12: repeating steps S5.2 to S5.11 until k ═ p + 1;
s5.13: collecting submodule output:
Figure FDA0003445237560000035
the step S6 includes the steps of:
s6.1: constructing network input I and reference output
Figure FDA0003445237560000036
Figure FDA0003445237560000037
Figure FDA0003445237560000038
S6.2: setting module parameters: number of input neurons p +1, number of output neurons 1, number of hidden layer neurons nRSpectral radius ρRDegree of sparsity spR；
S6.3: in the interval (-0.1,0.1)Randomly generating the network input weight matrix in uniform distribution
Figure FDA0003445237560000041
S6.4: randomly generating sparsity sp with uniform distribution over the interval (-1,1)ROf (2) matrix
Figure FDA0003445237560000042
S6.5: computing matrices
Figure FDA0003445237560000043
Maximum eigenvalue of
Figure FDA0003445237560000044
S6.6: calculating hidden layer weight WR
Figure FDA0003445237560000045
S6.7: computing hidden layer neuron states sR(t)：
Figure FDA0003445237560000046
Wherein s isR(0)＝0；
S6.8: constructing a hidden layer state matrix HR：
Figure FDA0003445237560000047
S6.9: computing network output weight matrix
Figure FDA0003445237560000048
Figure FDA0003445237560000049
Wherein
Figure FDA00034452375600000410
For the hidden layer state matrix HRThe transposed matrix of (2).
2. The method for predicting the content of free calcium oxide in cement clinker according to claim 1, wherein the step S7 specifically comprises: inputting the test sample into the trained feature extraction module, and outputting by the prediction module to obtain the free calcium oxide content of the cement clinker at the next moment.
CN201911232888.0A 2019-12-04 2019-12-04 Method for predicting content of free calcium oxide in cement clinker Active CN110763830B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911232888.0A CN110763830B (en) 2019-12-04 2019-12-04 Method for predicting content of free calcium oxide in cement clinker

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911232888.0A CN110763830B (en) 2019-12-04 2019-12-04 Method for predicting content of free calcium oxide in cement clinker

Publications (2)

Publication Number Publication Date
CN110763830A CN110763830A (en) 2020-02-07
CN110763830B true CN110763830B (en) 2022-04-05

Family

ID=69340973

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911232888.0A Active CN110763830B (en) 2019-12-04 2019-12-04 Method for predicting content of free calcium oxide in cement clinker

Country Status (1)

Country Link
CN (1) CN110763830B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112712861A (en) * 2021-01-07 2021-04-27 北京明略软件***有限公司 Model construction method, device, equipment and computer readable medium
CN114236104A (en) * 2021-10-28 2022-03-25 阿里云计算有限公司 Method, device, equipment, medium and product for measuring free calcium oxide

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104537444A (en) * 2015-01-13 2015-04-22 安徽理工大学 Gas outburst predicting method based on EMD and ELM
CN104899656A (en) * 2015-06-05 2015-09-09 三峡大学 Wind power combined predication method based on ensemble average empirical mode decomposition and improved Elman neural network
CN105373856A (en) * 2015-11-23 2016-03-02 江苏省电力公司南通供电公司 Wind electricity power short-term combined prediction method considering run detection method reconstruction
CN106126896A (en) * 2016-06-20 2016-11-16 中国地质大学（武汉） The mixed model wind speed forecasting method learnt based on empirical mode decomposition and the degree of depth and system
CN106295798A (en) * 2016-08-29 2017-01-04 江苏省电力试验研究院有限公司 Empirical mode decomposition and Elman neural network ensemble wind-powered electricity generation Forecasting Methodology
CN107016453A (en) * 2016-12-08 2017-08-04 中国农业大学 A kind of aquaculture dissolved oxygen prediction method and device
CN109583566A (en) * 2018-11-20 2019-04-05 东北农业大学 Ammonia concentration prediction technique in a kind of cold ground pig house based on empirical mode decomposition and Elman neural network
CN110163433A (en) * 2019-05-21 2019-08-23 上海海事大学 A kind of ship method for predicting

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102147273B (en) * 2010-01-29 2012-11-28 大连理工大学 Data-based blast-furnace gas dynamic predication method for metallurgical enterprises
CN105930916A (en) * 2016-04-07 2016-09-07 大连理工大学 Parallel modular neural network-based byproduct gas real-time prediction method
CN106202946A (en) * 2016-07-18 2016-12-07 燕山大学 Clinker free calcium levels Forecasting Methodology based on degree of depth belief network model
US20190325862A1 (en) * 2018-04-23 2019-10-24 Eta Compute, Inc. Neural network for continuous speech segmentation and recognition
CN108804800A (en) * 2018-06-04 2018-11-13 桂林电子科技大学 Lithium ion battery SOC on-line prediction methods based on echo state network
CN109147878B (en) * 2018-10-08 2021-10-15 燕山大学 Soft measurement method for free calcium of cement clinker
CN109165798A (en) * 2018-10-19 2019-01-08 燕山大学 A kind of Free Calcium Oxide Contents in Cement Clinker on-line prediction method and system
CN110309979A (en) * 2019-07-09 2019-10-08 南方电网科学研究院有限责任公司 Methods of electric load forecasting, device and equipment based on echo state network
CN110517488A (en) * 2019-08-19 2019-11-29 南京理工大学 The Short-time Traffic Flow Forecasting Methods with Recognition with Recurrent Neural Network are decomposed based on timing

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104537444A (en) * 2015-01-13 2015-04-22 安徽理工大学 Gas outburst predicting method based on EMD and ELM
CN104899656A (en) * 2015-06-05 2015-09-09 三峡大学 Wind power combined predication method based on ensemble average empirical mode decomposition and improved Elman neural network
CN105373856A (en) * 2015-11-23 2016-03-02 江苏省电力公司南通供电公司 Wind electricity power short-term combined prediction method considering run detection method reconstruction
CN106126896A (en) * 2016-06-20 2016-11-16 中国地质大学（武汉） The mixed model wind speed forecasting method learnt based on empirical mode decomposition and the degree of depth and system
CN106295798A (en) * 2016-08-29 2017-01-04 江苏省电力试验研究院有限公司 Empirical mode decomposition and Elman neural network ensemble wind-powered electricity generation Forecasting Methodology
CN107016453A (en) * 2016-12-08 2017-08-04 中国农业大学 A kind of aquaculture dissolved oxygen prediction method and device
CN109583566A (en) * 2018-11-20 2019-04-05 东北农业大学 Ammonia concentration prediction technique in a kind of cold ground pig house based on empirical mode decomposition and Elman neural network
CN110163433A (en) * 2019-05-21 2019-08-23 上海海事大学 A kind of ship method for predicting

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
A Two-Stage Online Prediction Method for a Blast;Jun Zhao et al.;《IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY》;20110331;第19卷(第3期);全文 *
Growing Echo-State Network With;Junfei Qiao et al.;《IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS》;20170228;第28卷(第2期);全文 *

Also Published As

Publication number Publication date
CN110763830A (en) 2020-02-07

Similar Documents

Publication Publication Date Title
CN111804146B (en) Intelligent ammonia injection control method and intelligent ammonia injection control device
CN110378044B (en) Multi-time scale convolution neural network soft measurement method based on attention mechanism
CN110763830B (en) Method for predicting content of free calcium oxide in cement clinker
CN110807554B (en) Generation method and system based on wind power/photovoltaic classical scene set
CN103336107B (en) Soft measurement method for f-CaO content of cement clinker
CN108152235B (en) Heavy metal content inversion method combining soil indoor and outdoor spectra
WO2021093362A1 (en) Precision compensation method for discharge caustic alkali concentration measurement device during evaporation process
CN110701796B (en) Energy-saving control system of hot water system based on cloud prediction algorithm
CN113671394A (en) Lithium ion battery expected life prediction method and system
WO2022121932A1 (en) Adaptive deep learning-based intelligent forecasting method, apparatus and device for complex industrial system, and storage medium
CN114330647A (en) Model training method and device and silicon rod weight prediction method
CN103279030B (en) Dynamic soft measuring modeling method and device based on Bayesian frame
CN111580570A (en) Container liquid level monitoring method and system
CN101446828A (en) Nonlinear process quality prediction method
CN114239421A (en) Method and system for predicting coal powder combustion characteristic parameters based on BP neural network
CN106529680B (en) A kind of multiple dimensioned extreme learning machine integrated modelling approach based on empirical mode decomposition
CN117350897A (en) Method and system for predicting conversion power by considering air humidity
Selivanova et al. Intelligent information-measuring system for operational control of thermo-physical properties of heat insulating materials
CN110909492A (en) Sewage treatment process soft measurement method based on extreme gradient lifting algorithm
CN113707240B (en) Component parameter robust soft measurement method based on semi-supervised nonlinear variation Bayesian hybrid model
CN114368768B (en) LSTM-based aluminum hydroxide seed crystal granularity refinement burst prediction model and method
CN109613618B (en) Long-term drift error compensation method of gravity sensor
CN114239397A (en) Soft measurement modeling method based on dynamic feature extraction and local weighted deep learning
CN113419050A (en) Method and device for soft measurement of cement raw material components
CN113377075A (en) Method and device for optimizing rare earth extraction process in real time and computer readable storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant