CN112784336A - Bridge static displacement prediction technology based on deep learning LSTM network - Google Patents
Bridge static displacement prediction technology based on deep learning LSTM network Download PDFInfo
- Publication number
- CN112784336A CN112784336A CN202011628545.9A CN202011628545A CN112784336A CN 112784336 A CN112784336 A CN 112784336A CN 202011628545 A CN202011628545 A CN 202011628545A CN 112784336 A CN112784336 A CN 112784336A
- Authority
- CN
- China
- Prior art keywords
- bridge
- data
- deflection
- deep learning
- lstm
- 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
- 230000003068 static effect Effects 0.000 title claims abstract description 20
- 238000006073 displacement reaction Methods 0.000 title claims abstract description 17
- 238000013135 deep learning Methods 0.000 title claims abstract description 16
- 238000005516 engineering process Methods 0.000 title claims abstract description 13
- 238000013528 artificial neural network Methods 0.000 claims abstract description 14
- 238000012544 monitoring process Methods 0.000 claims abstract description 10
- 238000003062 neural network model Methods 0.000 claims abstract description 10
- 238000007781 pre-processing Methods 0.000 claims abstract description 8
- 238000012549 training Methods 0.000 claims abstract description 7
- 230000004044 response Effects 0.000 claims abstract description 4
- 238000010606 normalization Methods 0.000 claims description 5
- 230000006870 function Effects 0.000 claims description 4
- 230000001419 dependent effect Effects 0.000 claims description 3
- 238000000034 method Methods 0.000 claims description 2
- 238000011156 evaluation Methods 0.000 abstract description 4
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 125000004122 cyclic group Chemical group 0.000 abstract description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000008034 disappearance Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000004880 explosion Methods 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 229910000831 Steel Inorganic materials 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/13—Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads
-
- 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
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Geometry (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Hardware Design (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Architecture (AREA)
- Civil Engineering (AREA)
- Structural Engineering (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention discloses a bridge static displacement prediction technology based on a deep learning LSTM network, which comprises the following steps: collecting static response monitoring data of bridge deflection; preprocessing the bridge deflection data; establishing an LSTM neural network for training; and predicting the bridge deflection by using the trained LSTM neural network model. The technical scheme is based on a deep learning artificial intelligence algorithm LSTM RNN and a long-short term memory cyclic neural network, sample data is obtained from deflection monitoring data of the bridge to conduct neural network model training, the deflection of the bridge is predicted through a neural network model trained through the past deflection information of the bridge, the purpose of predicting and early warning the deflection of the bridge is finally achieved, and the evaluation on the working performance of the bridge and the accurate judgment on the structure safety are achieved.
Description
Technical Field
The invention relates to the technical field of bridge structure safety, in particular to a bridge static displacement prediction technology based on a deep learning LSTM network.
Background
The static displacement of the bridge is an important monitoring content for monitoring the safety of the bridge structure, and the change of the deflection of the bridge can most directly reflect the change of the integral vertical rigidity and the bearing capacity of the bridge. The prediction of the deformation trend of the bridge structure can be helpful for the working performance evaluation of the bridge and the early warning of the structure safety.
The data shows that the commonly used prediction models have defects in some aspects, cannot well meet the precision requirement, and inevitably cause large errors, so that the prediction result is not credible. At present, the monitoring data of the bridge deflection has a large influence on a prediction result due to a large number of abnormal values of environmental interference, and finally the prediction result is greatly different from an actual situation.
Chinese patent document CN102635059B discloses a "bridge reconnaissance method". The following steps are adopted: 1) acquiring three-dimensional ground and geological data to generate DGSM; 2) generating DGESM; 3) generating a DBSM; 4) forming a bridge global three-dimensional entity curved surface model; 5) carrying out solid mechanical analysis on the bridge structure on the bridge global three-dimensional solid curved surface model, and selecting a route linear scheme and a bridge scheme; 6) establishing a geological entity section prediction model, and optimizing a route and bridge scheme; 7) generating a three-dimensional steel bar graph of the bridge structure by the bridge global three-dimensional entity curved surface model; 8) generating a structural diagram of the upper bridge structure and the lower bridge structure; 9) generating a lower and upper structural body of the bridge in the construction stage; 10) and comparing the built three-dimensional bridge entity model with the global three-dimensional entity curved surface model of the bridge before building to obtain parameters such as displacement, settlement, deformation and the like, and carrying out bridge detection. The technical scheme only carries out reconnaissance on the current situation of the bridge, lacks the prediction on the bridge and is difficult to meet the expected judgment on the safety of the bridge.
Disclosure of Invention
The invention mainly solves the technical problems that the original technical scheme has more abnormal values due to environmental interference and the deviation of a prediction result is larger, provides a bridge static displacement prediction technology based on a deep learning LSTM network, obtains sample data from deflection monitoring data of a bridge to carry out neural network model training based on a deep learning artificial intelligence algorithm LSTM RNN and a long-short term memory cyclic neural network, predicts the deflection of the bridge from a neural network model trained by the past deflection information of the bridge, finally achieves the aim of predicting and early warning the deflection of the bridge, and realizes the evaluation of the working performance of the bridge and the accurate judgment of the structural safety.
The technical problem of the invention is mainly solved by the following technical scheme: the invention comprises the following steps:
(1) collecting static response monitoring data of bridge deflection;
(2) preprocessing the bridge deflection data;
(3) establishing an LSTM neural network for training;
(4) and predicting the bridge deflection by using the trained LSTM neural network model.
Preferably, the preprocessing of step 2 adopts a zero-mean normalization method, and the specific formula is as follows:
wherein, x'i(ii) the prediction data normalized for the ith time instant; x is the number ofiThe data is predicted at the ith time, sigma is a data standard deviation, and u is a data average value.
Preferably, the LSTM neural network in step 3 is a modified RNN network, and the weight parameter of the self-loop is changed by adding an input gate, an output gate, a forgetting gate and a cell state. Under the condition that the model parameters are fixed, the problem of gradient disappearance or explosion can be effectively avoided. Wherein the input gate and the output gate control the flow-in and flow-out of information flow, and the forgetting gate selects how much the unit state at the previous time is stored until the previous time
Preferably, the output f of the forgetting gatetFrom the hidden layer state h at the previous momentt-1And input x of the current timetJointly determining:
ft=σ(Wfht-1+Ufxt+bf)
wherein, Wf、UfAnd bfTo forget the gate-related weights and bias matrices, σ is the sigmod function.
Preferably, the input gate controls the input of the current time, and comprises two parts:
it=σ(Wiht-1+Uixt+bi)
at=tanh(Waht-1+Uaxt+ba)
wherein, Wi、Wa、Ui、Ua、biAnd baThe gate dependent weights and bias matrices are input.
Preferably, the LSTM network propagates the state h of the hidden layer forward at time ttAnd cell state CtCell state CtThe updating of (1) consists of two results of an input gate and a forgetting gate:
Ct=Ct-1⊙ft+it⊙at
wherein, u is the Hadamard product.
Preferably, the output of the input gate in the LSTM neural network is:
ot=σ(Woht-1+Uoxt+bo)
the hidden layer ht is updated as follows:
ht=ot⊙tanh(Ct)。
preferably, the step 4 inputs data to obtain predicted preprocessed data, and performs inverse normalization on the data to obtain predicted bridge deflection data, so as to predict the static displacement of the bridge.
The invention has the beneficial effects that: based on a deep learning artificial intelligence algorithm LSTM RNN and a long-short term memory cyclic neural network, sample data is obtained from deflection monitoring data of a bridge for neural network model training, the deflection of the bridge is predicted from a neural network model trained by the previous deflection information of the bridge, the purpose of predicting and early warning the deflection of the bridge is finally achieved, and the evaluation on the working performance of the bridge and the accurate judgment on the structural safety are realized.
Drawings
FIG. 1 is a flow chart of the present invention.
FIG. 2 is a diagram of an LSTM neural network architecture of the present invention.
Detailed Description
The technical scheme of the invention is further specifically described by the following embodiments and the accompanying drawings.
Example (b): the bridge static displacement prediction technology based on the deep learning LSTM network of the embodiment, as shown in fig. 1, includes the following steps:
(1) collecting static response monitoring data of bridge deflection;
(2) preprocessing the bridge deflection data;
(3) establishing an LSTM neural network for training;
(4) and predicting the bridge deflection by using the trained LSTM neural network model.
And (3) preprocessing the bridge deflection data in the step (2), namely preprocessing the bridge deflection data by a zero-mean normalization method. The specific formula is as follows.
In the formula: x'i(ii) the prediction data normalized for the ith time instant; x is the number ofiThe data is predicted at the ith time, sigma is a data standard deviation, and u is a data average value.
The LSTM neural network in step 3 is an improved RNN network, and the self-loop weight parameters are changed by adding an input gate, an output gate, a forgetting gate, and a cell state (cell state), so that the problem of gradient "disappearance" or "explosion" can be effectively avoided under the condition that the model parameters are fixed. The input gate and the output gate control the inflow and outflow of information flow, and the forgetting gate selects how much of the unit state at the previous time is stored at the time. The network structure of the LSTM is shown in fig. 2.
Which propagates throughCompared with the traditional RNN network, the LSTM network propagates the state h except the hidden layer at the moment ttAlso, cell state C is addedt. The forgetting gate is used for controlling the state of the hidden layer at the last moment by a certain probability matrix. Output f of forgetting gatetFrom the hidden layer state h at the previous momentt-1And input x of the current timetJointly determining:
ft=σ(Wfht-1+Ufxt+bf)
wherein, Wf、UfAnd bfTo forget the gate-related weights and bias matrices, σ is the sigmod function. The input gate functions to control the input at the current time. The device consists of two parts:
it=σ(Wiht-1+Uixt+bi)
at=tanh(Waht-1+Uaxt+ba)
wherein, Wi、Wa、Ui、Ua、biAnd baThe gate dependent weights and bias matrices are input. Cell state C in LSTMtThe updating of (1) consists of two results of an input gate and a forgetting gate:
Ct=Ct-1⊙ft+it⊙at
wherein, u is the Hadamard product.
Finally, the output of the input gate in the LSTM is:
ot=σ(Woht-1+Uoxt+bo)
hidden layer htThe update of (1) is:
ht=ot⊙tanh(Ct)
the specific embodiments described herein are merely illustrative of the spirit of the invention. Various modifications or additions may be made to the described embodiments or alternatives may be employed by those skilled in the art without departing from the spirit or ambit of the invention as defined in the appended claims.
Although the terms bridge deflection, LSTM neural network, etc. are used more herein, the possibility of using other terms is not excluded. These terms are used merely to more conveniently describe and explain the nature of the present invention; they are to be construed as being without limitation to any additional limitations that may be imposed by the spirit of the present invention.
Claims (8)
1. A bridge static displacement prediction technology based on a deep learning LSTM network is characterized by comprising the following steps:
(1) collecting static response monitoring data of bridge deflection;
(2) preprocessing the bridge deflection data;
(3) establishing an LSTM neural network for training;
(4) and predicting the bridge deflection by using the trained LSTM neural network model.
2. The bridge static displacement prediction technology based on the deep learning LSTM network as claimed in claim 1, wherein the preprocessing of step 2 adopts a zero mean normalization method, and the concrete formula is as follows:
wherein, x'i(ii) the prediction data normalized for the ith time instant; x is the number ofiThe data is predicted at the ith time, sigma is a data standard deviation, and u is a data average value.
3. The technology for predicting static displacement of a bridge based on a deep learning LSTM network as claimed in claim 1, wherein the LSTM neural network in step 3 is a modified RNN network, and the weight parameters of the self-loop are changed by adding an input gate, an output gate, a forgetting gate and a cell state.
4. The technology of claim 3, wherein the output f of the forgetting gate is obtained by predicting the static displacement of the bridge based on the deep learning LSTM networktFrom the hidden layer state h at the previous momentt-1And input x of the current timetJointly determining:
ft=σ(Wfht-1+Ufxt+bf)
wherein, Wf、UfAnd bfTo forget the gate-related weights and bias matrices, σ is the sigmod function.
5. The bridge static displacement prediction technology based on the deep learning LSTM network as claimed in claim 3, wherein the input gate controls the input at the current time and consists of two parts:
it=σ(Wiht-1+Uixt+bi)
at=tanh(Waht-1+Uaxt+ba)
wherein, Wi、Wa、Ui、Ua、biAnd baThe gate dependent weights and bias matrices are input.
6. The technology of claim 3, wherein at time t the LSTM network propagates the state h of the hidden layer forwardtAnd cell state CtCell state CtThe updating of (1) consists of two results of an input gate and a forgetting gate:
Ct=Ct-1⊙ft+it⊙at
wherein, u is the Hadamard product.
7. The deep learning LSTM network-based bridge static displacement prediction technique of claim 6, wherein the output of the input gate in the LSTM neural network is:
ot=σ(Woht-1+Uoxt+bo)
the hidden layer ht is updated as follows:
ht=ot⊙tanh(Ct)。
8. the technology for predicting the static displacement of the bridge based on the deep learning LSTM network as claimed in claim 2, wherein the step 4 is to input data to obtain predicted preprocessed data, and perform inverse normalization on the data to obtain predicted bridge deflection data, so as to predict the static displacement of the bridge.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011628545.9A CN112784336A (en) | 2020-12-31 | 2020-12-31 | Bridge static displacement prediction technology based on deep learning LSTM network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011628545.9A CN112784336A (en) | 2020-12-31 | 2020-12-31 | Bridge static displacement prediction technology based on deep learning LSTM network |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112784336A true CN112784336A (en) | 2021-05-11 |
Family
ID=75754607
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011628545.9A Pending CN112784336A (en) | 2020-12-31 | 2020-12-31 | Bridge static displacement prediction technology based on deep learning LSTM network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112784336A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113656859A (en) * | 2021-07-05 | 2021-11-16 | 哈尔滨工业大学 | Different-appearance bridge self-excited vibration prediction modeling method based on deep learning |
CN113836783A (en) * | 2021-07-16 | 2021-12-24 | 东南大学 | Digital regression model modeling method for main beam temperature-induced deflection monitoring reference value of cable-stayed bridge |
CN114548375A (en) * | 2022-02-23 | 2022-05-27 | 合肥工业大学 | Cable-stayed bridge main beam dynamic deflection monitoring method based on bidirectional long-short term memory neural network |
CN114741976A (en) * | 2022-06-13 | 2022-07-12 | 西南交通大学 | Displacement prediction method, device and equipment and readable storage medium |
CN115114842A (en) * | 2022-04-27 | 2022-09-27 | 中国水利水电科学研究院 | Rainstorm waterlogging event prediction method based on small sample transfer learning algorithm |
CN115392142A (en) * | 2022-10-31 | 2022-11-25 | 深圳市城市交通规划设计研究中心股份有限公司 | Coastal environment simply supported beam elastic modulus prediction method, electronic equipment and storage medium |
CN116011125A (en) * | 2023-03-23 | 2023-04-25 | 成都理工大学 | Response prediction method for uncertain axle coupling system |
CN116046303A (en) * | 2023-03-30 | 2023-05-02 | 辽宁省交通规划设计院有限责任公司 | Deflection intelligent detection system, method and device |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018000561A1 (en) * | 2016-06-30 | 2018-01-04 | 东南大学 | Bridge testing and evaluation method and apparatus based on impact vibration |
CN110470259A (en) * | 2019-07-09 | 2019-11-19 | 西安工程大学 | Landslide displacement dynamic prediction method based on LSTM |
CN110598958A (en) * | 2019-10-10 | 2019-12-20 | 武汉科技大学 | Steel ladle grading management analysis method and system |
-
2020
- 2020-12-31 CN CN202011628545.9A patent/CN112784336A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018000561A1 (en) * | 2016-06-30 | 2018-01-04 | 东南大学 | Bridge testing and evaluation method and apparatus based on impact vibration |
CN110470259A (en) * | 2019-07-09 | 2019-11-19 | 西安工程大学 | Landslide displacement dynamic prediction method based on LSTM |
CN110598958A (en) * | 2019-10-10 | 2019-12-20 | 武汉科技大学 | Steel ladle grading management analysis method and system |
Non-Patent Citations (2)
Title |
---|
甘文娟;陈永红;韩静;王亚飞;: "基于正交参数优化的LSTM结构变形预测模型", 计算机系统应用, no. 09, 15 September 2020 (2020-09-15), pages 212 - 218 * |
郭挺;严万双;: "BP神经网络在连续梁桥线型控制中的应用", 工程与建设, no. 03, 15 June 2020 (2020-06-15), pages 560 - 562 * |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113656859A (en) * | 2021-07-05 | 2021-11-16 | 哈尔滨工业大学 | Different-appearance bridge self-excited vibration prediction modeling method based on deep learning |
CN113836783A (en) * | 2021-07-16 | 2021-12-24 | 东南大学 | Digital regression model modeling method for main beam temperature-induced deflection monitoring reference value of cable-stayed bridge |
CN113836783B (en) * | 2021-07-16 | 2022-11-18 | 东南大学 | Digital regression model modeling method for main beam temperature-induced deflection monitoring reference value of cable-stayed bridge |
CN114548375A (en) * | 2022-02-23 | 2022-05-27 | 合肥工业大学 | Cable-stayed bridge main beam dynamic deflection monitoring method based on bidirectional long-short term memory neural network |
CN114548375B (en) * | 2022-02-23 | 2024-02-13 | 合肥工业大学 | Cable-stayed bridge girder dynamic deflection monitoring method based on two-way long-short-term memory neural network |
CN115114842A (en) * | 2022-04-27 | 2022-09-27 | 中国水利水电科学研究院 | Rainstorm waterlogging event prediction method based on small sample transfer learning algorithm |
CN114741976A (en) * | 2022-06-13 | 2022-07-12 | 西南交通大学 | Displacement prediction method, device and equipment and readable storage medium |
CN114741976B (en) * | 2022-06-13 | 2022-09-23 | 西南交通大学 | Displacement prediction method, device and equipment and readable storage medium |
CN115392142A (en) * | 2022-10-31 | 2022-11-25 | 深圳市城市交通规划设计研究中心股份有限公司 | Coastal environment simply supported beam elastic modulus prediction method, electronic equipment and storage medium |
CN116011125A (en) * | 2023-03-23 | 2023-04-25 | 成都理工大学 | Response prediction method for uncertain axle coupling system |
CN116011125B (en) * | 2023-03-23 | 2023-06-06 | 成都理工大学 | Response prediction method for uncertain axle coupling system |
CN116046303A (en) * | 2023-03-30 | 2023-05-02 | 辽宁省交通规划设计院有限责任公司 | Deflection intelligent detection system, method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112784336A (en) | Bridge static displacement prediction technology based on deep learning LSTM network | |
CN106453293B (en) | A kind of network security situation prediction method based on improved BPNN | |
Jia et al. | Research on a mine gas concentration forecasting model based on a GRU network | |
CN111339712A (en) | Method for predicting residual life of proton exchange membrane fuel cell | |
CN113378939B (en) | Structure digital twin modeling and parameter identification method based on physical driving neural network | |
CN112182954B (en) | LSTM-based fluid simulation data prediction model | |
CN112000015A (en) | Intelligent BIT design method for heavy-duty gas turbine control system controller module based on LSTM and bio-excitation neural network | |
Asadi et al. | Development of optimal fuzzy models for predicting the strength of intact rocks | |
CN115271186B (en) | Reservoir water level prediction and early warning method based on delay factor and PSO RNN Attention model | |
CN111723523B (en) | Estuary surplus water level prediction method based on cascade neural network | |
US20040019469A1 (en) | Method of generating a multifidelity model of a system | |
CN113328908A (en) | Abnormal data detection method and device, computer equipment and storage medium | |
CN114548482A (en) | Creep type landslide kinetic energy change rate face-slip early warning method | |
CN113408190B (en) | Surrounding rock deformation prediction method for highway tunnel construction period based on Bayes-LSTM model | |
CN114897103A (en) | Industrial process fault diagnosis method based on neighbor component loss optimization multi-scale convolutional neural network | |
CN114692963A (en) | Landslide displacement prediction method based on long-term and short-term memory neural network | |
Aloisio et al. | Damage classification after the 2009 L’Aquila earthquake using multinomial logistic regression and neural networks | |
CN112307536B (en) | Dam seepage parameter inversion method | |
CN116303786B (en) | Block chain financial big data management system based on multidimensional data fusion algorithm | |
CN112926251A (en) | Landslide displacement high-precision prediction method based on machine learning | |
Zhao et al. | Determining geomechanical parameters and a deformation uncertainty analysis of the Longtan Hydropower Station slope, China | |
CN115563475A (en) | Pressure soft sensor of excavator hydraulic system | |
CN116415501A (en) | MGU-A thermal error prediction model creation method and thermal error control system based on digital twin | |
Jafari | System identification of a soil tunnel based on a hybrid artificial neural network–numerical model approach | |
CN108960406B (en) | MEMS gyroscope random error prediction method based on BFO wavelet 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 |