CN111257934B - Seismic oscillation peak acceleration prediction method based on second-order neuron deep neural network - Google Patents
Seismic oscillation peak acceleration prediction method based on second-order neuron deep neural network Download PDFInfo
- Publication number
- CN111257934B CN111257934B CN202010053228.2A CN202010053228A CN111257934B CN 111257934 B CN111257934 B CN 111257934B CN 202010053228 A CN202010053228 A CN 202010053228A CN 111257934 B CN111257934 B CN 111257934B
- Authority
- CN
- China
- Prior art keywords
- neural network
- deep neural
- peak acceleration
- order
- neuron
- 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
Links
- 210000002569 neuron Anatomy 0.000 title claims abstract description 64
- 230000001133 acceleration Effects 0.000 title claims abstract description 49
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 42
- 238000000034 method Methods 0.000 title claims abstract description 33
- 230000010355 oscillation Effects 0.000 title abstract description 10
- 238000003062 neural network model Methods 0.000 claims abstract description 28
- 238000012549 training Methods 0.000 claims abstract description 20
- 230000004913 activation Effects 0.000 claims abstract description 8
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 claims abstract description 7
- 238000005457 optimization Methods 0.000 claims abstract description 7
- 238000011156 evaluation Methods 0.000 claims abstract description 5
- 230000006870 function Effects 0.000 claims description 48
- 238000011425 standardization method Methods 0.000 claims description 4
- 230000003044 adaptive effect Effects 0.000 claims description 2
- 230000003213 activating effect Effects 0.000 claims 1
- 238000012360 testing method Methods 0.000 description 8
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 101100492445 Arabidopsis thaliana ASK14 gene Proteins 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V1/00—Seismology; Seismic or acoustic prospecting or detecting
- G01V1/28—Processing seismic data, e.g. for interpretation or for event detection
- G01V1/30—Analysis
- G01V1/307—Analysis for determining seismic attributes, e.g. amplitude, instantaneous phase or frequency, reflection strength or polarity
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- 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
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Remote Sensing (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Acoustics & Sound (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Environmental & Geological Engineering (AREA)
- Geology (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geophysics (AREA)
- Geophysics And Detection Of Objects (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a seismic oscillation peak acceleration prediction method based on a second-order neuron deep neural network, belongs to the field of seismic engineering, and aims to solve the technical problem of low accuracy of seismic oscillation prediction. The earthquake motion peak acceleration prediction method comprises the following steps: selecting a seismic magnitude, a projection distance, a shear wave velocity, an area, a covering layer thickness, a fault type and a period as input parameters in a data set, wherein the corresponding seismic oscillation peak acceleration is a target parameter; establishing a deep neural network comprising three hidden layers, wherein neurons are second-order elements, a hyperbolic tangent function is adopted as an activation function, a mean square error function and an Adam self-adaptive optimization function are adopted for back propagation, and an average absolute error function is taken as an evaluation function; thirdly, training a deep neural network model; and fourthly, predicting the peak acceleration. The invention adopts a multi-input structure and a second-order neural network, which can not only improve the precision of predicting the earthquake motion peak acceleration, but also ensure the applicability of a deep neural network model.
Description
Technical Field
The invention belongs to the field of seismic engineering, and particularly relates to a seismic oscillation peak acceleration prediction method based on a second-order neuron deep neural network.
Background
From ancient times to present, the loss of society caused by each major earthquake is immeasurable, in order to reduce and control the loss caused by the earthquake, the earthquake fortification of buildings is the most important measure, and the basis of the earthquake fortification is the earthquake danger analysis. In earthquake risk analysis, in order to evaluate earthquake intensity through different parameters, establishing an earthquake motion prediction equation is a very important link.
At present, the traditional prediction method is mainly to carry out empirical regression according to the existing seismic records, the method has good prediction precision and uniform residual distribution, but the seismic record applicable to the method is less due to the uncertainty of the height of each variable in an equation.
In recent years, with the development of computer technology, the deep neural network achieves better performance in data regression, and therefore a peak acceleration prediction method based on a second-order neuron deep neural network is provided.
Disclosure of Invention
The invention aims to solve the technical problem of low accuracy of seismic motion prediction, and provides a seismic motion peak acceleration prediction method based on a second-order neuron deep neural network.
The seismic oscillation peak acceleration prediction method based on the second-order neuron deep neural network is realized according to the following steps:
the method comprises the following steps: collecting seismic motion records, and establishing a data set:
selecting magnitude (M) and projection distance (R) in the data setJB) Shear wave velocity (V)S30) Region (Region), cover thickness (Z)1) The Fault Type (Fault Type) and the period (T) are used as input parameters, the corresponding earthquake motion peak acceleration is used as a target parameter, and the values of the input parameters and the target parameter are between-0.5 and 0.5 through a standardization method to obtain an earthquake motion data set;
step two: establishing a deep neural network with second-order neurons:
establishing a deep neural network comprising three hidden layers, wherein neurons are second-order elements, a hyperbolic tangent function (Tanh) is adopted as an activation function, a mean square error function (MSE) and an Adam self-adaptive optimization function are adopted for back propagation, and an average absolute error function (MAE) is adopted as an evaluation function to obtain a deep neural network model;
step three: deep neural network model training:
training the deep neural network model, ensuring the training precision through a mean square error function (MSE) and an average absolute error function (MAE), and enabling an attenuation curve to smoothly descend to obtain the trained deep neural network model;
step four: predicting the peak acceleration:
predicting earthquake motion input parameters and outputting earthquake motion peak acceleration by using the deep neural network model trained in the step three, so that the earthquake motion peak acceleration is predicted;
the operation formula in the second order element in the step two is as follows:
wherein: k is that the current neuron is positioned at the kth layer;
n is the number of neurons in the k-th layer network;
σ: an activation function, which adopts a hyperbolic tangent function (Tanh);
ωira first weight parameter corresponding to the ith neuron of the k-th layer network;
ωiga second weight parameter corresponding to the ith neuron of the k-th layer network;
ωiba third weight parameter corresponding to the ith neuron of the k-th layer network;
b1a first bias parameter corresponding to the k-th layer network;
b2a second bias parameter corresponding to the k-th layer network;
b3a third bias parameter corresponding to the k-th layer network;
xiinput parameters.
The invention selects more than 20900 earthquake motion records from the global scope (NGA-West2 database), adopts a multi-input structure and a second-order neuron network, can improve the prediction precision and ensure the applicability of a deep neural network model.
Compared with the traditional empirical formula, the seismic oscillation peak acceleration prediction method based on the second-order neuron deep neural network has the advantages of most data sets, higher precision, better applicability and the same simplicity and convenience in use.
Drawings
FIG. 1 is a general framework flowchart of an embodiment seismic peak acceleration prediction method based on a second-order neuron deep neural network;
FIG. 2 is a diagram of a second-order neuron deep neural network model according to an embodiment;
FIG. 3 is a test chart for predicting seismic peak acceleration by using ASK 14;
FIG. 4 is a test chart for predicting seismic peak acceleration using BSSA 14;
FIG. 5 is a test chart of seismic peak acceleration prediction by using CB 14;
FIG. 6 is a test chart for predicting seismic peak acceleration by using CY 14;
FIG. 7 is a test chart of seismic peak acceleration prediction using ANN;
FIG. 8 is a test chart of seismic peak acceleration prediction using an embodiment RSO-DNN;
fig. 9 is a graph of the peak acceleration decay curve of the embodiment compared to BSSA14 model, wherein the solid line represents RSO-DNN and the dashed line represents BSSA14, with sequential magnitudes of 4, 5, 6, 7, and 8 along arrow direction M.
Detailed Description
The first embodiment is as follows: the earthquake motion peak acceleration prediction method based on the second-order neuron deep neural network is implemented according to the following steps:
the method comprises the following steps: collecting seismic motion records, and establishing a data set:
selecting magnitude (M) and projection distance (R) in the data setJB) Shear wave velocity (V)S30) Region (Region), cover thickness (Z)1) The Fault Type (Fault Type) and the period (T) are input parameters, the corresponding earthquake motion peak acceleration is a target parameter, and the values of the input parameters and the target parameter are between-0.5 and 0.5 through a standardization method to obtain an earthquake motion data set;
step two: establishing a deep neural network with second-order neurons:
establishing a deep neural network comprising three hidden layers, wherein neurons are second-order elements, a hyperbolic tangent function (Tanh) is adopted as an activation function, a mean square error function (MSE) and an Adam self-adaptive optimization function are adopted for back propagation, and an average absolute error function (MAE) is adopted as an evaluation function to obtain a deep neural network model;
step three: deep neural network model training:
training the deep neural network model, ensuring the training precision through a mean square error function (MSE) and an average absolute error function (MAE), and enabling an attenuation curve to smoothly descend to obtain the trained deep neural network model;
step four: predicting the peak acceleration:
predicting earthquake motion input parameters by using the deep neural network model trained in the step three and outputting earthquake motion peak acceleration, thereby completing the earthquake motion peak acceleration prediction method based on the second-order neuron deep neural network;
the operation formula in the second order element in the step two is as follows:
wherein: k is that the current neuron is positioned at the kth layer;
n is the number of neurons in the k-th layer network;
σ: an activation function, which adopts a hyperbolic tangent function (Tanh);
ωira first weight parameter corresponding to the ith neuron of the k-th layer network;
ωiga second weight parameter corresponding to the ith neuron of the k-th layer network;
ωiba third weight parameter corresponding to the ith neuron of the k-th layer network;
b1a first bias parameter corresponding to the k-th layer network;
b2a second bias parameter corresponding to the k-th layer network;
b3a third bias parameter corresponding to the k-th layer network;
xiinput parameters.
The second embodiment is as follows: this embodiment differs from the embodiment in that the seismic record in step one is selected from the NGA-West2 database.
The third concrete implementation mode: the difference between this embodiment and the first or second embodiment is that the first step, the middle magnitude (M), is obtained from the natural logarithm, and the projection distance (R)JB) Taken from the natural log value.
The fourth concrete implementation mode: the difference between this embodiment and one of the first to third embodiments is that each hidden layer in step two includes 30 second-order neurons.
The fifth concrete implementation mode: the difference between this embodiment and one of the first to the fourth embodiments is that the deep neural network described in step two is a multi-input network, the input parameters are divided into four groups and respectively input into independent sub-networks, each independent sub-network includes 30 second-order neurons, the input parameters are subjected to four independent sub-network operations to obtain four groups of data, and the four groups of data are connected into one group by using a catenate function and then input into the next hidden layer.
The independent sub-network described in this embodiment is a hidden layer.
The sixth specific implementation mode: the third or fifth difference from the specific embodiment is that the input parameters are divided into A, B, C and D groups, wherein the A group takes the Fault Type (Fault Type) and the magnitude (M) as the input parameters, and the B group takes the magnitude (M) and the projection distance (R)JB) And Region (Region) as input parameters, and C group is the magnitude (M) and projection distance (R)JB) Region, shear wave velocity (V)S30) And the thickness (Z) of the covering layer1) As input parameters, the D group takes the period (T) as an input parameter.
The seventh embodiment: the difference between this embodiment and one of the first to sixth embodiments is that the expression of the mean square error function (MSE) in step two is as follows:
The specific implementation mode is eight: the difference between this embodiment and one of the first to seventh embodiments is that the algorithm of the Adam adaptive optimization function is as follows:
(1) calculating a first moment estimate and a second moment estimate of the gradient by the following formula:
mt=β1·mt-1+(1-β1)·gt,νt=β2·νt-1+(1-β2)·gt 2;
in the formula, gtIs a gradient in which mtIs the mean value of the gradient at time t, vtIs the non-central variance value, m, at time t of the gradientt-1Is the mean value at time t-1 of the gradient, Vt-1The exponential decay rate beta of the moment estimate, which is the non-central variance value at time t-1 of the gradient1And beta2Within the interval [0,1 ], beta1Take 0.9, beta2Taking 0.999;
(2) correcting the first order moment estimate and the second order moment estimate by calculating the formula:
(3) the final formula for parameter update is:
in the formula, thetatFor updated parameters, η is the learning rate, ε is a small constant for numerical stability, ε is taken to be 10-8。
The specific implementation method nine: the present embodiment is different from the first to eighth embodiments in that the batch size (batch size) of the deep neural network model after training in step three is 325, the training round (Epoch) is 15, and the learning rate is 0.001.
Example (b): the earthquake motion peak acceleration prediction method based on the second-order neuron deep neural network is implemented according to the following steps:
the method comprises the following steps: collecting seismic motion records, and establishing a data set:
selecting 20900 seismic records from the NGA-West2 database, and selecting the magnitude (M) and the projection distance (R) in the data setJB) Shear wave velocity (V)S30) Region (Region), cover thickness (Z)1) Fault Type and period (T) as input parameters, magnitude (M) is taken from natural logarithm value, projection distance (R)JB) Taking a natural logarithm value, taking the corresponding seismic oscillation peak acceleration as a target parameter, and enabling the values of the input parameter and the target parameter to be between-0.5 and 0.5 through a standardization method to obtain a seismic oscillation data set;
the formula of the normalization method is as follows:
wherein: x is the number of*Standardized data; x is the number ofmax: maximum value of data; x is the number ofmin: a data minimum value; x is data before standardization;
step two: dividing a data set;
randomly dividing the seismic data set into a training set, a verification set and a test set, wherein the proportion of the training set, the verification set and the test set is 8: 1: 1;
step three: establishing a deep neural network with second-order neurons:
establishing a deep neural network comprising three hidden layers, wherein the deep neural network is a multi-input network, input parameters are divided into four groups and are respectively input into independent sub-networks, the input parameters are divided into an A group, a B group, a C group and a D group, the A group takes a Fault Type (Fault Type) and a magnitude (M) as the input parameters, and the B group takes the magnitude (M) and a projection distance (R) as the input parametersJB) And Region (Region) as input parameters, and the C group is in magnitude(M), projection distance (R)JB) Region, shear wave velocity (V)S30) And the thickness (Z) of the covering layer1) The D group takes a period (T) as an input parameter, each independent sub-network comprises 30 second-order neurons, the input parameter is operated by four independent sub-networks to obtain four groups of data, the four groups of data are connected into a group by using a concatenate function and then input into a next hidden layer, each hidden layer comprises 30 second-order neurons, a hyperbolic tangent function (Tanh) is used as an activation function, a mean square error function (MSE) and an Adam self-adaptive optimization function are used for back propagation, and a mean absolute error function (MAE) is used as an evaluation function to obtain a deep neural network model;
step four: deep neural network model training:
training the deep neural network model, ensuring the training precision through a mean square error function (MSE) and a mean absolute error function (MAE), ensuring the applicability according to the shape of an attenuation curve, and obtaining the trained deep neural network model RSO-DNN, wherein the batch size (Batchsize) of the trained deep neural network model is 325, the training round (Epoch) is 15, and the learning rate is 0.001;
step five: predicting the peak acceleration:
and predicting the earthquake motion input parameters by using the trained deep neural network model trained in the step four and outputting earthquake motion peak acceleration, thereby completing the earthquake motion peak acceleration prediction method based on the second-order neuron deep neural network.
The network selected in this embodiment includes three hidden layers, all neurons are second-order elements, and the internal operation formula of the second-order elements is as follows:
wherein: k is that the current neuron is positioned at the kth layer;
n is the number of neurons in the k-th layer network;
σ: an activation function, which adopts a hyperbolic tangent function (Tanh);
ωira first weight parameter corresponding to the ith neuron of the k-th layer network;
ωiga second weight parameter corresponding to the ith neuron of the k-th layer network;
ωiba third weight parameter corresponding to the ith neuron of the k-th layer network;
b1a first bias parameter corresponding to the k-th layer network;
b2a second bias parameter corresponding to the k-th layer network;
b3a third bias parameter corresponding to the k-th layer network;
xiinput parameters.
With the development of computer technology and the amplification of data sets, neural networks are developed towards deep layers, and neurons are developed towards higher orders, but the contribution of the neural networks in the aspect of building earthquake motion prediction equations is very limited. Models established by traditional empirical regression methods, such as BSSA14, ASK14, CB14, CY14, I14, and Derras trained artificial neural networks, are very good in accuracy and applicability, but have room for improvement. Therefore, the present invention selects 5 empirical formulas to compare with 1 artificial neural network model (ANN), wherein in the conventional linear neural network (ANN), the operation formula inside each neuron is as follows:
wherein: k is that the current neuron is positioned at the kth layer;
n is the number of neurons in the k-th layer network;
ωithe weighting parameter corresponding to the ith neuron of the k-th layer network;
b, bias parameters corresponding to the k-th layer network;
xiinputting parameters;
σ: the function is activated.
The comparison results are shown in table 1, and the comparison graphs are shown in fig. 3 to 8. Through the calculation comparison of the peak acceleration prediction precision and the observation comparison of the gathering effect, the deep neural network model trained by the embodiment has the best performance.
TABLE 1 comparison of the present invention with empirical formulas and linear artificial neural network peak acceleration prediction results
Claims (9)
1. The earthquake motion peak acceleration prediction method based on the second-order neuron deep neural network is characterized by comprising the following steps of:
the method comprises the following steps: collecting seismic motion records, and establishing a data set:
selecting an earthquake magnitude, a projection distance, a shear wave velocity, an area, a covering layer thickness, a fault type and a period in the data set as input parameters, taking the corresponding earthquake motion peak acceleration as a target parameter, and enabling the values of the input parameters and the target parameter to be between-0.5 and 0.5 through a standardization method to obtain an earthquake motion data set;
step two: establishing a deep neural network with second-order neurons:
establishing a deep neural network comprising three hidden layers, wherein neurons are second-order elements, a hyperbolic tangent function is adopted as an activation function, a mean square error function and an Adam self-adaptive optimization function are adopted for back propagation, and an average absolute error function is adopted as an evaluation function to obtain a deep neural network model;
step three: deep neural network model training:
training the deep neural network model, ensuring the training precision through a mean square error function and an average absolute error function, and enabling an attenuation curve to smoothly descend to obtain the trained deep neural network model;
step four: predicting the peak acceleration:
predicting earthquake motion input parameters and outputting earthquake motion peak acceleration by using the deep neural network model trained in the step three, so that the earthquake motion peak acceleration is predicted;
the operation formula in the second order element in the step two is as follows:
wherein: k is that the current neuron is positioned at the kth layer;
n is the number of neurons in the k-th layer network;
σ: activating a function by adopting a hyperbolic tangent function;
ωira first weight parameter corresponding to the ith neuron of the k-th layer network;
ωiga second weight parameter corresponding to the ith neuron of the k-th layer network;
ωiba third weight parameter corresponding to the ith neuron of the k-th layer network;
b1a first bias parameter corresponding to the k-th layer network;
b2a second bias parameter corresponding to the k-th layer network;
b3a third bias parameter corresponding to the k-th layer network;
xiinput parameters.
2. The method for predicting earthquake peak acceleration based on the second-order neuron depth neural network as claimed in claim 1, wherein the earthquake record in the first step is selected from NGA-West2 database.
3. The method of claim 1, wherein the seismic peak acceleration prediction method based on the second-order neuron depth neural network is characterized in that in the first step, the seismic magnitude is a natural logarithm value, and the projection distance is a natural logarithm value.
4. The method of predicting earthquake peak acceleration based on the second-order neuron deep neural network as claimed in claim 1, wherein each hidden layer in the second step comprises 30 second-order neurons.
5. The method of predicting earthquake peak acceleration based on the quadratic neuron deep neural network of claim 1, wherein the deep neural network in the second step is a multi-input network, the input parameters are divided into four groups and respectively input into independent sub-networks, each independent sub-network comprises 30 quadratic neurons, the input parameters are subjected to four groups of data obtained by four independent sub-network operations, and the four groups of data are connected into one group by using a catenate function and then input into the next hidden layer.
6. The method of predicting earthquake peak acceleration based on the second-order neuron depth neural network as claimed in claim 3 or 5, wherein the input parameters are divided into A, B, C and D groups, wherein A group takes the fault type and the magnitude as input parameters, B group takes the magnitude, the projection distance and the area as input parameters, C group takes the magnitude, the projection distance, the area, the shear wave velocity and the cover layer thickness as input parameters, and D group takes the period as input parameters.
8. The seismic peak acceleration prediction method based on the second-order neuron depth neural network of claim 1, characterized in that the algorithm of the Adam adaptive optimization function is as follows:
(1) calculating a first moment estimate and a second moment estimate of the gradient by the following formula:
mt=β1·mt-1+(1-β1)·gt,νt=β2·νt-1+(1-β2)·gt 2;
in the formula, gtIs a gradient in which mtIs the mean value of the gradient at time t, vtIs the non-central variance value, m, at time t of the gradientt-1Is the mean value at time t-1 of the gradient, Vt-1The exponential decay rate beta of the moment estimate, which is the non-central variance value at time t-1 of the gradient1And beta2Within the interval [0,1 ], beta1Take 0.9, beta2Taking 0.999;
(2) correcting the first order moment estimate and the second order moment estimate by calculating the formula:
(3) the final formula for parameter update is:
in the formula, thetatFor updated parameters, η is the learning rate, ε is a small constant for numerical stability, ε is taken to be 10-8。
9. The method of predicting earthquake motion peak acceleration based on the second-order neuron deep neural network of claim 1, wherein the batch size of the deep neural network model after training in step three is 325, the training round is 15, and the learning rate is 0.001.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010053228.2A CN111257934B (en) | 2020-01-17 | 2020-01-17 | Seismic oscillation peak acceleration prediction method based on second-order neuron deep neural network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010053228.2A CN111257934B (en) | 2020-01-17 | 2020-01-17 | Seismic oscillation peak acceleration prediction method based on second-order neuron deep neural network |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111257934A CN111257934A (en) | 2020-06-09 |
CN111257934B true CN111257934B (en) | 2022-03-11 |
Family
ID=70947692
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010053228.2A Active CN111257934B (en) | 2020-01-17 | 2020-01-17 | Seismic oscillation peak acceleration prediction method based on second-order neuron deep neural network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111257934B (en) |
Families Citing this family (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112630827B (en) * | 2020-12-07 | 2024-02-02 | 中国地震局工程力学研究所 | Surface acceleration peak parameter prediction method and system |
CN113296147B (en) * | 2021-05-24 | 2022-09-09 | 中国科学技术大学 | Method and system for identifying earthquake finite fault fracture parameters |
CN113468466B (en) * | 2021-07-23 | 2022-04-15 | 哈尔滨工业大学 | One-dimensional wave equation solving method based on neural network |
CN114117617B (en) * | 2021-12-08 | 2022-05-31 | 哈尔滨工业大学 | Rapid prediction method for earthquake response of three-span gallery type RC frame building |
CN114966840B (en) * | 2022-05-24 | 2023-04-07 | 哈尔滨工业大学 | Model building method of three-dimensional seismic wave field based on general solution neural network |
CN115081274B (en) * | 2022-06-10 | 2023-05-30 | 哈尔滨工业大学 | Method for establishing gridless three-dimensional seismic wave field based on cyclic neural network |
CN115099523B (en) * | 2022-07-20 | 2023-10-24 | 哈尔滨工业大学 | Earthquake motion parameter prediction method based on artificial intelligence and earthquake motion experience model mixing |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103675914A (en) * | 2012-09-12 | 2014-03-26 | 林沛旸 | On-site earthquake real-time analysis system using artificial neural network and method thereof |
CN106646587A (en) * | 2016-12-29 | 2017-05-10 | 北京知觉科技有限公司 | Target detecting and identifying method and target detecting and identifying system based on sound vibration signal |
KR101901352B1 (en) * | 2017-06-30 | 2018-09-21 | 인천대학교 산학협력단 | Predicting System For Seismic Observation |
CN108596327A (en) * | 2018-03-27 | 2018-09-28 | 中国地质大学(武汉) | A kind of seismic velocity spectrum artificial intelligence pick-up method based on deep learning |
CN109799533A (en) * | 2018-12-28 | 2019-05-24 | 中国石油化工股份有限公司 | A kind of method for predicting reservoir based on bidirectional circulating neural network |
CN110488351A (en) * | 2019-08-15 | 2019-11-22 | 东北大学 | Seismic wave based on machine learning shakes property recognition methods |
CN110516735A (en) * | 2019-08-27 | 2019-11-29 | 天津科技大学 | A kind of natural gas line event category method based on LSTM network and Adam algorithm |
CN110631792A (en) * | 2019-10-11 | 2019-12-31 | 东南大学 | Seismic hybrid test model updating method based on convolutional neural network |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106405640B (en) * | 2016-08-26 | 2018-07-10 | 中国矿业大学(北京) | Microseismic signals based on depth conviction neural network then automatic pick method |
SG11202000350RA (en) * | 2017-08-25 | 2020-03-30 | Exxonmobil Upstream Res Co | Automated seismic interpretation using fully convolutional neural networks |
CN109002942A (en) * | 2018-09-28 | 2018-12-14 | 河南理工大学 | A kind of short-term load forecasting method based on stochastic neural net |
-
2020
- 2020-01-17 CN CN202010053228.2A patent/CN111257934B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103675914A (en) * | 2012-09-12 | 2014-03-26 | 林沛旸 | On-site earthquake real-time analysis system using artificial neural network and method thereof |
CN106646587A (en) * | 2016-12-29 | 2017-05-10 | 北京知觉科技有限公司 | Target detecting and identifying method and target detecting and identifying system based on sound vibration signal |
KR101901352B1 (en) * | 2017-06-30 | 2018-09-21 | 인천대학교 산학협력단 | Predicting System For Seismic Observation |
CN108596327A (en) * | 2018-03-27 | 2018-09-28 | 中国地质大学(武汉) | A kind of seismic velocity spectrum artificial intelligence pick-up method based on deep learning |
CN109799533A (en) * | 2018-12-28 | 2019-05-24 | 中国石油化工股份有限公司 | A kind of method for predicting reservoir based on bidirectional circulating neural network |
CN110488351A (en) * | 2019-08-15 | 2019-11-22 | 东北大学 | Seismic wave based on machine learning shakes property recognition methods |
CN110516735A (en) * | 2019-08-27 | 2019-11-29 | 天津科技大学 | A kind of natural gas line event category method based on LSTM network and Adam algorithm |
CN110631792A (en) * | 2019-10-11 | 2019-12-31 | 东南大学 | Seismic hybrid test model updating method based on convolutional neural network |
Non-Patent Citations (3)
Title |
---|
"NEURAL NETWORKS FOR QUICK EARTHQUAKE DAMAGE ESTIMATION";GILBERT L. MOLAS etc;《EARTHQUAKE ENGINEERING AND STRUCTURAL DYNAMICS》;19951231;第24卷;第508-509页 * |
"主余震地震动特征及结构地震反应分析";籍多发;《中国优秀博士学位论文全文数据库 工程科技II辑》;20190115;第C038-32页 * |
"基于改进AlexNet模型的肺癌辅助检测方法";傅磊 等;《莆田学院学报》;20191031;第26卷(第5期);第55-58页 * |
Also Published As
Publication number | Publication date |
---|---|
CN111257934A (en) | 2020-06-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111257934B (en) | Seismic oscillation peak acceleration prediction method based on second-order neuron deep neural network | |
CN108900346B (en) | Wireless network flow prediction method based on LSTM network | |
CN108038300B (en) | Optical fiber state evaluation method based on improved membership function combined with neural network | |
CN107730003A (en) | One kind supports more high-precision NILM implementation methods of appliance type | |
CN111539132B (en) | Dynamic load time domain identification method based on convolutional neural network | |
EP2672659A2 (en) | Method and device for artificial synthesis of network flow | |
CN111967679A (en) | Ionized layer total electron content forecasting method based on TCN model | |
CN114219139B (en) | DWT-LSTM power load prediction method based on attention mechanism | |
CN109101717A (en) | Solid propellant rocket Reliability Prediction Method based on reality with the study of fuzzy data depth integration | |
CN109599866B (en) | Prediction-assisted power system state estimation method | |
CN111324110A (en) | Fermentation process fault monitoring method based on multiple shrinkage automatic encoders | |
CN112307536B (en) | Dam seepage parameter inversion method | |
CN114169505A (en) | Method and system for training yield prediction model and related equipment | |
CN115982141A (en) | Characteristic optimization method for time series data prediction | |
CN115237878A (en) | Process database construction method and medium based on additive manufacturing | |
CN114692507A (en) | Counting data soft measurement modeling method based on stacking Poisson self-encoder network | |
CN108647817B (en) | Energy consumption load prediction method and system | |
CN113591957A (en) | Wind power output short-term rolling prediction and correction method based on LSTM and Markov chain | |
CN112348656A (en) | BA-WNN-based personal loan credit scoring method | |
CN108959721B (en) | Method for calculating reliability of long-span bridge member under action of windmill load | |
CN116522774A (en) | Soil slope stability prediction method and prediction platform based on transfer learning algorithm | |
CN108446506B (en) | Uncertain system modeling method based on interval feedback neural network | |
CN116304940A (en) | Analog circuit fault diagnosis method based on long-short-term memory neural network | |
CN115936176A (en) | Load prediction method based on data enhancement strategy and residual self-correction learning model | |
CN115496264A (en) | Method for predicting generated power of wind turbine generator |
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 | ||
CB03 | Change of inventor or designer information |
Inventor after: Ji Duofa Inventor after: Zhai Changhai Inventor after: Li Chenxi Inventor after: Wen Weiping Inventor before: Ji Duofa Inventor before: Li Chenxi Inventor before: Wen Weiping Inventor before: Zhai Changhai |
|
CB03 | Change of inventor or designer information | ||
GR01 | Patent grant | ||
GR01 | Patent grant |