CN115470887A - Coal mine tunneling working face gas emission quantity prediction method based on KPCA-POA-LSTM model - Google Patents
Coal mine tunneling working face gas emission quantity prediction method based on KPCA-POA-LSTM model Download PDFInfo
- Publication number
- CN115470887A CN115470887A CN202211014081.1A CN202211014081A CN115470887A CN 115470887 A CN115470887 A CN 115470887A CN 202211014081 A CN202211014081 A CN 202211014081A CN 115470887 A CN115470887 A CN 115470887A
- Authority
- CN
- China
- Prior art keywords
- coal mine
- peacock
- working face
- tunneling working
- mine tunneling
- 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
- 239000003245 coal Substances 0.000 title claims abstract description 85
- 230000005641 tunneling Effects 0.000 title claims abstract description 67
- 238000000034 method Methods 0.000 title claims abstract description 31
- 241000692870 Inachis io Species 0.000 claims abstract description 55
- 239000011159 matrix material Substances 0.000 claims abstract description 23
- 238000005457 optimization Methods 0.000 claims abstract description 14
- 230000006870 function Effects 0.000 claims abstract description 12
- 230000007787 long-term memory Effects 0.000 claims abstract description 12
- 230000006403 short-term memory Effects 0.000 claims abstract description 12
- 238000000513 principal component analysis Methods 0.000 claims abstract description 10
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 claims abstract description 5
- 238000013507 mapping Methods 0.000 claims abstract description 5
- 239000013598 vector Substances 0.000 claims description 28
- 230000008569 process Effects 0.000 claims description 11
- 230000006399 behavior Effects 0.000 claims description 10
- 238000009827 uniform distribution Methods 0.000 claims description 9
- 230000015654 memory Effects 0.000 claims description 7
- 230000007246 mechanism Effects 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 5
- 230000008034 disappearance Effects 0.000 claims description 4
- 238000013459 approach Methods 0.000 claims description 3
- 230000001939 inductive effect Effects 0.000 claims description 3
- 238000013178 mathematical model Methods 0.000 claims description 3
- 210000000689 upper leg Anatomy 0.000 claims description 2
- 230000009467 reduction Effects 0.000 abstract description 3
- 230000004913 activation Effects 0.000 abstract description 2
- 238000009826 distribution Methods 0.000 abstract description 2
- 230000001172 regenerating effect Effects 0.000 abstract description 2
- 238000004364 calculation method Methods 0.000 description 3
- 238000005065 mining Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 239000011435 rock Substances 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000003795 desorption Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 239000002356 single layer Substances 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009933 burial Methods 0.000 description 1
- 230000000739 chaotic effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000010410 layer Substances 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000003449 preventive effect Effects 0.000 description 1
- 238000012847 principal component analysis method Methods 0.000 description 1
- 238000000518 rheometry Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a coal mine tunneling working face gas emission quantity prediction method based on a KPCA-POA-LSTM model, and belongs to the technical field of coal mine tunneling working face gas prediction. The invention includes: performing dimensionality reduction and initialization on the gas outburst data of the coal mine driving face of the nonlinear coal mine driving face by using nuclear principal component analysis; optimizing nodes of the long-term and short-term memory network by using a peacock optimization algorithm, and regenerating continuous distribution of parameters of the nodes; constructing a multi-dimensional state matrix, performing feature mapping on the multi-dimensional state matrix by using a long and short term memory network, selecting sigmoid as an activation function, and using Adam as a solver; and predicting the gas data of the coal mine tunneling working face by using the optimized long-term and short-term memory network. The method can accurately predict the gas emission quantity of the coal mine tunneling working face, and the prediction speed is higher and the error rate is lower.
Description
Technical Field
The invention provides a coal mine tunneling working face gas emission quantity prediction method based on a KPCA-POA-LSTM model, and belongs to the technical field of coal mine tunneling working face gas prediction.
Background
In the coal industry, further research is yet to be carried out on a regional coal mine tunneling working face gas system. Besides rock deformation, stress concentration and stress superposition, a multilayer and multidirectional integrated coal mine tunneling working face gas emission quantity prediction model research should be carried out. The gas emission quantity of the coal mine tunneling working face has the characteristics of fuzziness, agnostic property, randomness and the like, and the traditional prediction method cannot accurately predict the gas emission quantity of the coal mine tunneling working face due to the characteristics. On the basis of the outbreak and complexity of gas accidents of the coal mine tunneling working face, how to accurately master the gas emission rule of the coal mine tunneling working face and carry out accurate and rapid prediction on the gas of the coal mine tunneling working face is the key for controlling the gas of the coal mine tunneling working face to emit in large scale in advance. Based on the storage condition of the gas on the coal mine tunneling working face, the gas on the coal mine tunneling working face has certain chaotic characteristics, and the geological system of the coal and the gas on the coal mine tunneling working face becomes a nonlinear system with an overlapping principle no longer established. The gas system of the coal mine tunneling working face is analyzed according to the original coal mine tunneling working face gas content, the burial depth, the coal thickness, the mining height, the mining rate, the adjacent layer coal mine tunneling working face gas content, the mining strength and other factors. On the basis of the gas extra-large accident of the coal mine driving face, domestic scholars analyze the essential reason of the gas accident of the coal mine driving face and the coal mine emergency model with other objective factor defects, and carry out detailed analysis according to each link of the system. And (4) analyzing and simulating the examples, providing preventive measures and establishing a system for predicting the gas emission quantity of the coal mine tunneling working face. And constructing a coal mine underground real-time coal mine tunneling working face gas monitoring system. And constructing a coal mine tunneling working face gas emission quantity prediction model. In the aspect of predicting the gas emission quantity of a coal mine tunneling working face, a plurality of scholars make certain contribution. The research on the multi-dimensional data matrix in the prediction of the gas emission quantity of the coal mine tunneling working face is little, and the coal mine tunneling working face gas single-layer feedforward neural network model is not trained. Therefore, the invention analyzes and establishes a model from the multi-dimensional state of the gas emission quantity of the coal mine tunneling working face and the angle of the single-layer feedforward neural network and predicts the model.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the invention provides a coal mine tunneling working face gas emission quantity prediction method based on a KPCA-POA-LSTM model, which can be used for predicting coal mine tunneling working face gas data more accurately.
The technical scheme of the invention is as follows: a coal mine tunneling working face gas emission quantity prediction method based on a KPCA-POA-LSTM model comprises the following specific steps:
step 1, initializing initial data by using kernel principal component analysis KPCA, setting radial basis kernel function parameters, calculating a characteristic vector and a characteristic value, and calculating an accumulated contribution rate;
step 2, constructing a POA-LSTM model, and optimizing a forgetting gate, an input node, an output gate, a middle output and state unit of the long-short term memory network by using a peacock optimization algorithm POA to reduce the problem of gradient disappearance;
and 3, constructing a multi-dimensional state matrix and selecting an inducing strategy, training the multi-dimensional state matrix by using the optimized long-term and short-term memory network, and predicting the gas result of the coal mine tunneling working face by using Adam to solve according to the original gas data of the coal mine tunneling working face.
Further, the specific steps of step 1 are:
step 1.1, constructing kernel principal component analysis, setting a matrix X and a sample point X i One sample X = [ X ] is represented by each column of X 1 ,x 2 …,x N ]Each sample point x i For K-dimensional column vectors, N samples in X are introduced into a symmetric matrix K, and the feature vectors form the whole input space K ij ＝φ(x i ) T [φ(x j )]Where φ (x) is a mapping, i, j represent matrix space rows and columns, respectively;
step 1.2, a kernel function is introduced, wherein x and y are low-dimensional vectors, sigma 1 ，γ 1 As a constant, map it to a radial basis function kernel for high-dimensional vectors
And obtaining a data norm and calculating a characteristic vector for the matrix.
Further, the specific steps of step 2 are:
step 2.1, adopting a self-adaptive search and approach mechanism of the female peacock to optimize; the following mathematical model was used to describe the femora proximity mechanism:
step 2.2, adopting the peacock cubs to adapt to the searching behavior for optimization; the location update of the finder is described as follows for each iteration: as follows:
Γ(x)＝(x-1)！ (4)
wherein r is 6 And r 7 Respectively represent a uniform distribution in [ -1,1 [ ]]And [0,1]Two different one-dimensional random vectors; gamma denotes a constant with a value set to 1.5! Represents a factorial; the specific behavior of each peacock cub was modeled as:
wherein r is 8 Represents a uniform distribution in [0,1 ]]A random number of (c); x SPc And X PcC Respectively selecting position vectors of peacocks and peacock cubs; α and δ represent two coefficient factors that vary dynamically with the number of iterations, and can be defined by the following equations:
the formulas (7) and (8) show that alpha is larger than delta at the beginning of iteration, and the peacock cubs are mainly randomly searched; when δ is greater than α at the end of the iteration, the peacock pups converge to the optimal five solutions, i.e. the optimal five peacock positions; alpha (alpha) ("alpha") 0 ＝0.9,α 1 1.4, and δ 0 And delta 1 Equal to 0.1 and 1, respectively, the output parameters are optimized by a peacock search behavior.
The beneficial effects of the invention are:
1. the method utilizes the nuclear principal component analysis to reduce the dimension and initialize the gas outburst data of the coal mine heading face of the nonlinear coal mine heading face; optimizing nodes of the long-term and short-term memory network by using a peacock optimization algorithm, and regenerating continuous distribution of parameters of the nodes; constructing a multi-dimensional state matrix, performing feature mapping on the multi-dimensional state matrix by using a long and short term memory network, selecting sigmoid as an activation function, and using Adam as a solver; predicting the gas data of the coal mine tunneling working face by using the optimized long-term and short-term memory network;
2. the method can accurately predict the gas emission quantity of the coal mine tunneling working face, the prediction speed of the prediction method is higher, the error rate is lower, an effective prediction method is provided for a coal mine tunneling working face gas monitoring system, and a key technical support is provided for building a mine coal mine tunneling working face gas digital monitoring system.
Drawings
FIG. 1 schematically illustrates a detailed flow diagram of the prediction algorithm of the present invention;
FIG. 2 schematically illustrates a flow chart of the prediction algorithm of the present invention;
FIG. 3 is a diagram illustrating an accumulated contribution of a coal mine heading face gas content base indicator according to an embodiment of the invention;
FIG. 4 illustrates an example of a comparison of prediction results for LSTM, POA-LSTM, PSO-LSTM prediction models in an embodiment of the present invention;
FIG. 5 illustrates, by way of example, the comparison of absolute errors of predicted results for LSTM, POA-LSTM and PSO-LSTM predictive models in an embodiment of the present invention.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to fig. 1 in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention. It should be noted that the embodiments and features of the embodiments in the present application may be arbitrarily combined with each other without conflict.
Embodiment 1, the method for predicting the gas emission quantity of the coal mine tunneling working face based on the KPCA-POA-LSTM model is implemented according to the following steps.
A coal mine tunneling working face gas emission quantity prediction method based on a KPCA-POA-LSTM model comprises the following specific steps:
step 1, initializing initial data by using kernel principal component analysis KPCA, setting radial basis kernel function parameters, calculating a characteristic vector and a characteristic value, and calculating an accumulated contribution rate;
step 2, constructing a POA-LSTM model, and optimizing a forgetting gate, an input node, an output gate, a middle output and state unit of the long-short term memory network by using a peacock optimization algorithm POA to reduce the problem of gradient disappearance;
and 3, constructing a multi-dimensional state matrix and selecting an inducing strategy, training the multi-dimensional state matrix by using the optimized long-term and short-term memory network, and predicting the gas result of the coal mine tunneling working face by using Adam to solve according to the original gas data of the coal mine tunneling working face.
Further, the specific steps of step 1 are:
step 1.1, constructing kernel principal component analysis, setting a matrix X and a sample point X i One sample X = [ X ] is represented by each column of X 1 ,x 2 …,x N ]Each sample point x i For K-dimensional column vectors, N samples in X are introduced into a symmetric matrix K, and the feature vectors form the whole input space K ij ＝φ(x i ) T [φ(x j )]Where φ (x) is a mapping, i, j represent matrix space rows and columns, respectively;
step 1.2, introducing a kernel function, wherein x and y are low-dimensional vectors and sigma 1 ，γ 1 As a constant, map it to a radial basis function kernel for high-dimensional vectors
And obtaining a data norm and calculating a characteristic vector for the matrix.
Further, the specific steps of step 2 are:
step 2.1, adopting a self-adaptive search and approach mechanism of the female peacock to optimize; the following mathematical model was used to describe the female peacock proximity mechanism:
step 2.2, adopting the peacock cubs to adapt to the searching behavior for optimization; the location update of the finder is described as follows for each iteration: as follows:
Γ(x)＝(x-1)！ (4)
wherein r is 6 And r 7 Respectively represent a uniform distribution in [ -1,1 [)]And [0,1]Two different one-dimensional random vectors; gamma denotes a constant whose value is set to 1.5! Represents a factorial; the specific behavior of each peacock cub was modeled as:
wherein r is 8 Represents a uniform distribution in [0,1 ]]A random number above; x SPc And X PcC Respectively indicating the position vectors of the selected peacocks and peacock cubs; α and δ represent two coefficient factors that vary dynamically with the number of iterations, and can be defined by the following equations:
the formulas (7) and (8) show that alpha is larger than delta at the beginning of iteration, and the peacock cubs are mainly randomly searched; when δ is greater than α at the end of the iteration, the peacock pup converges to the optimal five solutions, i.e., the optimal five peacock positions; alpha (alpha) ("alpha") 0 ＝0.9,α 1 1.4, and δ 0 And delta 1 Equal to 0.1 and 1, respectively, output parameters were optimized by peacock search behavior.
First, embodiment 1 of the present invention will be described with reference to fig. 1 and 2.
Due to the ground stress and the rheology of the gas on the coal mine tunneling working face, rock deformation, stress concentration, stress superposition, vibration waves and the like, the coal mine tunneling process is close to the high-structure strain energy containing the gas rock stratum and the coal bed of the coal mine tunneling working face, and the gas on the coal mine tunneling working face is overflowed due to special effects so that the gas on the coal mine tunneling working face is continuously gushed out; and the gas coal containing the coal mine tunneling working face has the spatial complexity of rheological behavior, and a complex nonlinear system is often formed in three areas of relaxation, stress concentration and original stress.
The coal mine tunneling working face gas data are selected as shown in table 1, and main influence factors comprise coal mine tunneling working face gas pressure, desorption coefficient, relative coal mine tunneling working face gas emission amount, coal mine tunneling working face gas trend peak-to-peak ratio, coal mine tunneling working face gas trend peak-to-average ratio, ground stress parameters and ground stress indexes.
TABLE 1 coal mine heading face gas data
And (3) performing dimensionality reduction on the gas data of the coal mine driving face in the table 1 by using a nuclear principal component analysis method, and calculating to obtain the accumulated contribution rate of the first 3 principal components of the data to reach more than 99%. As shown in fig. 3.
Wherein F 1 -F 6 The method comprises the steps of selecting the first three data as main data relative to the gas emission amount of a coal mine tunneling working face, the gas pressure of the coal mine tunneling working face, a desorption coefficient, the gas trend peak-to-peak ratio of the coal mine tunneling working face, the gas trend peak-to-average ratio of the coal mine tunneling working face, an earth stress parameter and an earth stress index.
Importing the test data after the kernel principal component analysis dimensionality reduction into a POA-LSTM, PSO-LSTM and LSTM prediction model, and comparing LSTM, PSO-LSTM and POA-LSTM prediction methods;
as can be seen from fig. 4, the predicted result of the conventional long and short term memory network has a large error, because the LSTM algorithm stores some information in the cell state and obtains new information through Sigmoid function calculation, and because the information calculation process depends on the offset vectors of each structure, abnormal data is generated in the cross calculation process. The maximum relative error of the LSTM algorithm in 30 sample data is 16.05%, the average relative error is 9.6%, and the root mean square error value is 36.64; the maximum relative error rate of gas prediction data of the coal mine tunneling working face obtained by the PSO-LSTM prediction model is 21.85%, and the average relative error rate is 8.22%; the maximum relative error rate of the coal mine tunneling working face gas prediction data obtained by the POA-LSTM prediction model is 5.8%, the average relative error rate is 1.93%, and the root mean square error value is 5.324, which is detailed in a table 2.
TABLE 2 prediction error comparison
Therefore, compared with the existing particle swarm long and short term memory network algorithm, the long and short term memory network algorithm is adopted. The algorithm precision after the peacock optimization algorithm is coupled is greatly improved, and the peacock optimization algorithm is self-adaptive to calculate, so that the convergence rate is improved, and the local optimization is avoided.
The POA-LSTM algorithm effectively reduces the values of RMSE and R-square.
Therefore, the precision of the long-short term memory network optimized by the peacock optimization algorithm and the kernel principal component analysis can be greatly improved. Plotting according to MATALB 2016A software: the prediction error results of POA-LSTM, PSO-LSTM and LSTM are shown in FIG. 5.
According to a drawing of a long-short term memory network model, a long-short term memory network model and a long-short term memory network error result graph optimized by a peacock optimization algorithm under particle swarm optimization, as shown in the graph in FIG. 5, the prediction result of the gas emission of the coal mine driving working face of the POA-LSTM prediction model is most coupled with the gas emission of the actual coal mine driving working face. The second time the PSO-LSTM model is, the LSTM model is farthest, and data outliers exist, indicating that the POA-LSTM prediction model is closest to the actual values.
In the 3 coal mine tunneling working face gas prediction models, the change range of the absolute error curve is that the LSTM coal mine tunneling working face gas prediction model has the largest change range, and the PSO-LSTM coal mine tunneling working face gas prediction model is inferior to the POA-LSTM, because the defect that the two LSTM algorithms are locally optimal is not solved. Because the local optimal value exists, a large error exists in the training process of the neural network; the PSO-LSTM model has unstable model, although the overall error is smaller than that of the LSTM, the common LSTM cannot guarantee that the problem of gradient disappearance in the training process can be effectively solved.
While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it will be understood by those of ordinary skill in the art that various changes in form and details may be made therein without departing from the spirit and scope of the present invention as defined by the appended claims.
Claims (3)
1. A coal mine tunneling working face gas emission quantity prediction method based on a KPCA-POA-LSTM model is characterized by comprising the following steps: the method comprises the following specific steps:
step 1, initializing initial data by using kernel principal component analysis KPCA, setting radial basis kernel function parameters, calculating a characteristic vector and a characteristic value, and calculating an accumulated contribution rate;
step 2, constructing a POA-LSTM model, and optimizing a forgetting gate, an input node, an output gate, a middle output and state unit of the long-short term memory network by using a peacock optimization algorithm POA to reduce the problem of gradient disappearance;
and 3, constructing a multi-dimensional state matrix and selecting an inducing strategy, training the multi-dimensional state matrix by using the optimized long-term and short-term memory network, and predicting the gas result of the coal mine tunneling working face by using Adam to solve according to the original gas data of the coal mine tunneling working face.
2. The method for predicting the gas emission quantity of the coal mine tunneling working face based on the KPCA-POA-LSTM model according to claim 1, wherein: the specific steps of the step 1 are as follows:
step 1.1, constructing kernel principal component analysis, setting a matrix X and a sample point X i One sample X = [ X ] is represented by each column of X 1 ,x 2 …,x N ]Each sample point x i For K-dimensional column vectors, N samples in X are introduced into a symmetric matrix K, and the feature vectors form the whole input space K ij ＝φ(x i ) T [φ(x j )]Where φ (x) is a mapping, i, j represent matrix space rows and columns, respectively;
step 1.2, introducing a kernel function, wherein x and y are low-dimensional vectors and sigma 1 ，γ 1 As a constant, map it to a radial basis function kernel for high-dimensional vectors
And obtaining a data norm and calculating a characteristic vector for the matrix.
3. The method for predicting the gas emission quantity of the coal mine tunneling working face based on the KPCA-POA-LSTM model according to claim 1, wherein: the specific steps of the step 2 are as follows:
step 2.1, adopting a self-adaptive search and approach mechanism of the female peacock to optimize; the following mathematical model was used to describe the femora proximity mechanism:
step 2.2, adopting the peacock cubs to adapt to the searching behavior for optimization; the location update of the finder is described as follows for each iteration: as follows:
Γ(x)＝(x-1)！ (4)
wherein r is 6 And r 7 Respectively represent a uniform distribution in [ -1,1 [)]And [0,1]Two different one-dimensional random vectors; gamma denotes a constant, the value of which is set1.5! Represents a factorial; the specific behavior of each peacock cub was modeled as:
wherein r is 8 Represents a uniform distribution in [0,1 ]]A random number of (c); x SPc And X PcC Respectively indicating the position vectors of the selected peacocks and peacock cubs; α and δ represent two coefficient factors that vary dynamically with the number of iterations, defined by the following equations:
the formulas (7) and (8) show that alpha is larger than delta at the beginning of iteration, and the peacock cubs are randomly searched; when δ is greater than α at the end of the iteration, the peacock pup converges to the optimal five solutions, i.e., the optimal five peacock positions; alpha (alpha) ("alpha") 0 ＝0.9,α 1 =1.4, and δ 0 And delta 1 Equal to 0.1 and 1, respectively, output parameters were optimized by peacock search behavior.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211014081.1A CN115470887A (en) | 2022-08-23 | 2022-08-23 | Coal mine tunneling working face gas emission quantity prediction method based on KPCA-POA-LSTM model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211014081.1A CN115470887A (en) | 2022-08-23 | 2022-08-23 | Coal mine tunneling working face gas emission quantity prediction method based on KPCA-POA-LSTM model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115470887A true CN115470887A (en) | 2022-12-13 |
Family
ID=84366161
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211014081.1A Pending CN115470887A (en) | 2022-08-23 | 2022-08-23 | Coal mine tunneling working face gas emission quantity prediction method based on KPCA-POA-LSTM model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115470887A (en) |
-
2022
- 2022-08-23 CN CN202211014081.1A patent/CN115470887A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20130124171A1 (en) | Systems and methods for predicting well performance | |
| CN110807544B (en) | Oil field residual oil saturation distribution prediction method based on machine learning | |
| WO2007089829A2 (en) | Methods, systems, and computer-readable media for fast updating of oil and gas field production models with physical and proxy simulators | |
| CN112363896B (en) | Log abnormality detection system | |
| CN105183928A (en) | Quick Analysis Of Residual Stress And Distortion In Cast Aluminum Components | |
| CN112633328A (en) | Dense oil reservoir transformation effect evaluation method based on deep learning | |
| KR102155101B1 (en) | System and method for predicting ground layer information, and a recording medium having computer readable program for executing the method | |
| KR101474874B1 (en) | computing system for well placement optimization developed by SA/ANN and well placement optimization method using Thereof | |
| CN113722997A (en) | New well dynamic yield prediction method based on static oil and gas field data | |
| CN116245013A (en) | Geological prediction model construction method, modeling method, equipment and storage medium | |
| Kolajoobi et al. | Investigating the capability of data-driven proxy models as solution for reservoir geological uncertainty quantification | |
| CN114611406A (en) | Coal bed gas emission quantity prediction method based on SSA-CIRCLE-ELM model | |
| Tang et al. | Well control optimization of waterflooding oilfield based on deep neural network | |
| CN104732067A (en) | Industrial process modeling forecasting method oriented at flow object | |
| CN110988997A (en) | Hydrocarbon source rock three-dimensional space distribution quantitative prediction technology based on machine learning | |
| CN115438897A (en) | Industrial process product quality prediction method based on BLSTM neural network | |
| CN114114414A (en) | Artificial intelligence prediction method for 'dessert' information of shale reservoir | |
| CN111984514B (en) | Log anomaly detection method based on Prophet-bLSTM-DTW | |
| CN113077091A (en) | Machine learning-based leakage rate probability distribution prediction method and system | |
| CN113095466A (en) | Algorithm of satisfiability model theoretical solver based on meta-learning model | |
| CN117150925A (en) | Reverse analysis method for rock mass mechanical parameters of high-steep slope of hydropower engineering | |
| CN115470887A (en) | Coal mine tunneling working face gas emission quantity prediction method based on KPCA-POA-LSTM model | |
| CN114676887A (en) | River water quality prediction method based on graph convolution STG-LSTM | |
| Gudmundsdottir et al. | Inferring interwell connectivity in fractured geothermal reservoirs using neural networks | |
| CN112926774A (en) | Geothermal energy production capacity prediction method and system based on long-time memory neural network |
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 |