Intelligent Parameter Inversion of Fractional-Order Model Based on BP Neural Network

Abstract To explore creep parameters and creep characteristics of salt rock, an Ansys numerical model of salt rock sample was established by using fractional creep constitutive model of salt rock, and an orthogonal test scheme was designed based on uniaxial compression test of salt rock samples. A large number of training data were obtained by combining the numerical model with the experimental scheme, and the model parameters were inverted by using the BP neural network. The model parameters are used for forwarding calculation, and the results are in good agreement with the measured strain data. This shows that the model parameter inversion method proposed in this paper can obtain reasonable parameter values and then accurately predict the creep behaviour of salt rock, which provides a good technical basis for related engineering practice and scientific research in the future.

Download Full-text

Creep Parameter Inversion for High CFRDs Based on Improved BP Neural Network Response Surface Method

10.21203/rs.3.rs-1133358/v1 ◽

2021 ◽

Author(s):

Xinjie Zhou ◽

Xinjian Sun ◽

Yongye Li ◽

Juntao Zhang ◽

Zhigang Li ◽

...

Keyword(s):

Neural Network ◽

Response Surface ◽

Response Surface Method ◽

Bp Neural Network ◽

Test Method ◽

Inversion Method ◽

Model Parameters ◽

Creep Parameter ◽

Parameter Inversion ◽

Surface Method

Abstract The creep parameters of rockfill materials obtained from engineering analogy method or indoor tests often cannot accurately reflect the long-term deformation of high Concrete Faced Rockfill Dams (CFRDs). This paper introduces an optimized inversion method based on Multi-population Genetic Algorithm improved BP Neural Network and Response Surface Method (MPGA-BPNN RSM). The parameters used for inversion are determined by parameter sensitivity analysis based on the statistical orthogonal test method. MPGA-BPNN RSM, validated by Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE) and squared correlation coefficient (R2), etc., completely reflects the response between the creep parameters and the settlement calculation values obtained by Finite Element Method (FEM). MPGA optimized the objective function to obtain the optimal creep parameters. The results show that the settlement values of Xujixia CFRD calculated by FEM using the inversion parameters has great consistency with the monitored values both in size and in distribution, suggesting that the model parameters obtained by the introduced creep parameter inversion method are feasible and effective. The introduced method can improve the inversion efficiency and the prediction accuracy in FEM applications.

Download Full-text

Thermal–Mechanical Coupling Evaluation of the Panel Performance of a Prefabricated Cabin-Type Substation Based on Machine Learning

Fire ◽

10.3390/fire4040093 ◽

2021 ◽

Vol 4 (4) ◽

pp. 93

Author(s):

Xiangsheng Lei ◽

Jinwu Ouyang ◽

Yanfeng Wang ◽

Xinghua Wang ◽

Xiaofeng Zhang ◽

...

Keyword(s):

Neural Network ◽

Machine Learning ◽

Numerical Simulation ◽

Fire Resistance ◽

Bp Neural Network ◽

Stress Test ◽

Normal Operation ◽

Model Parameters ◽

Mechanical Coupling ◽

The Impact

The panel performance of a prefabricated cabin-type substation under the impact of fires plays a vital role in the normal operation of the substation. However, current evaluations of the panel performance of substations under fire still focus on fire resistance tests, which seldom consider the relationship between fire behavior and the mechanical load of the panel under the impact of fires. Aiming at the complex and uncertain relationship between the thermal and mechanical performance of the substation panel under impact of fires, this paper proposes a machine learning method based on a BP neural network. First, the fire resistance test and the stress test of the panel is carried out, then a machine learning model is established based on the BP neural network. According to the collected data, the model parameters are obtained through a series of training and verification processes. Meanwhile, the correlation between the panel performance and fire resistance was obtained. Finally, related parameters are input into the thermal–mechanical coupling evaluation model for the substation panel performance to evaluate the fire resistance performance of the substation panel. To verify the correctness of the established model, numerical simulation of the fire test and stress test of the panel is conducted, and numerical simulation samples are predicted by the trained model. The results show that the prediction curve of neural network is closer to the real results compared with the numerical simulation, and the established model can accurately evaluate the thermal–mechanical coupling performance of the substation panel under fire.

Download Full-text

Resistivity-depth imaging of airborne transient electromagnetic method based on an artificial neural network

10.5194/egusphere-egu2020-1729 ◽

2020 ◽

Author(s):

Jifeng Zhang ◽

Bing Feng ◽

Dong Li

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Bp Neural Network ◽

Apparent Resistivity ◽

Electromagnetic Method ◽

Electromagnetic Response ◽

Model Parameters ◽

Transient Electromagnetic Method ◽

Transient Electromagnetic ◽

Artificial Neural

<p>An artificial neural network, which is an important part of artificial intelligence, has been widely used to many fields such as information processing, automation and economy, and geophysical data processing as one of the efficient tools. However, the application in geophysical electromagnetic method is still relatively few. In this paper, BP neural network was combined with airborne transient electromagnetic method for imaging subsurface geological structures.</p><p>We developed an artificial neural network code to map the distribution of geologic conductivity in the subsurface for the airborne transient electromagnetic method. It avoids complex derivation of electromagnetic field formula and only requires input and transfer functions to obtain the quasi-resistivity image section. First, training sample set, which is airborne transient electromagnetic response of homogeneous half-space models with the different resistivity, is formed and network model parameters include the flight altitude and the time constant, which were taken as input variables of the network, and pseudo-resistivity are taken as output variables. Then, a double hidden layer BP neural network is established in accordance with the mapping relationship between quasi-resistivity and airborne transient electromagnetic response. By analyzing mean square error curve, the training&#160;termination criterion of BP neural network is presented. Next, the trained BP neural network is used to interpret the airborne transient electromagnetic responses of various typical layered geo-electric models, and it is compared with those of the all-time apparent resistivity algorithm. After a lot of tests, reasonable BP neural network parameters were selected, and the mapping from airborne TEM quasi-resistivity was realized. The results show that the resistivity imaging from BP neural network approach is much closer to the true resistivity of model, and the response to anomalous bodies is better than that of all-time apparent resistivity numerical method. Finally, this imaging technique was use to process the field data acquired by the airborne transient method from Huayangchuan area. Quasi-resistivity depth section calculated by BP neural network and all-time apparent resistivity is in good agreement with the actual geological situation, which further verifies the effectiveness and practicability of this algorithm.</p>

Download Full-text

Back-Analysis of Indoor Test Parameters for Rock-Fill of Shui Bu Ya CFRD

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.243-249.4581 ◽

2011 ◽

Vol 243-249 ◽

pp. 4581-4586

Author(s):

Lei Ming He ◽

Li Hui Du ◽

Jian Yang

Keyword(s):

Neural Network ◽

Bp Neural Network ◽

Back Analysis ◽

Soil Parameters ◽

Model Parameters ◽

Analysis Method ◽

Filling Process ◽

Rock Fill ◽

Test Parameters ◽

Displacement Back Analysis

In the numerical calculation of geotechnical project, it’s difficult to confirm the parameters because of the complexity and the uncertainty of them as the time is changing. However, the back-analysis provides us an effective way. Based on the result of the triaxial test on rock-fill of Shui Bu Ya CFRD, the thesis adopts the direct back-analysis method which combines the BP Neural Network and Genetic Algorithm to calculate the Tsinghua non-linear K-G model parameters of the rock-fill. The back-analysis parameters are used to simulate the filling process of Shui Bu Ya CFRD and predict the displacement of the dam. The thesis provides a technical reference for displacement back-analysis of soil parameters for CFRD.

Download Full-text

Application of Hybrid Genetic Algorithm in Ground Stress Inversion

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.90-93.337 ◽

2011 ◽

Vol 90-93 ◽

pp. 337-341

Author(s):

Ran Gang Yu ◽

Yong Tian

Keyword(s):

Neural Network ◽

Genetic Algorithm ◽

Neural Networks ◽

Bp Neural Network ◽

Local Minimum ◽

Hybrid Genetic Algorithm ◽

Inversion Method ◽

Stress Inversion ◽

Neural Network Inversion ◽

Ground Stress

This paper propose genetic algorithm combined with neural networks, greatly improving the convergence rate of neural network aim at the disadvantage of the traditional BP neural network inversion method is easy to fall into local minimum and slow convergence.Finally, verified the feasibility and superiority of the above methods through the successful initial ground stress inversion of actual project.

Download Full-text

Short-Term Wind Power Dynamic Prediction Based on GA-BP Neural Network

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.986-987.524 ◽

2014 ◽

Vol 986-987 ◽

pp. 524-528 ◽

Cited By ~ 2

Author(s):

Ting Jing Ke ◽

Min You Chen ◽

Huan Luo

Keyword(s):

Neural Network ◽

Prediction Model ◽

Wind Power ◽

Bp Neural Network ◽

Prediction Models ◽

Model Parameters ◽

Short Term ◽

Dynamic Prediction ◽

Power Dynamic ◽

Prediction Approach

This paper proposes a short-term wind power dynamic prediction model based on GA-BP neural network. Different from conventional prediction models, the proposed approach incorporates a prediction error adjusting strategy into neural network based prediction model to realize the function of model parameters self-adjusting, thus increase the prediction accuracy. Genetic algorithm is used to optimize the parameters of BP neural network. The wind power prediction results from different models with and without error adjusting strategy are compared. The comparative results show that the proposed dynamic prediction approach can provide more accurate wind power forecasting.

Download Full-text

Predicting Freeway Travel Time Using Multiple- Source Heterogeneous Data Integration

Applied Sciences ◽

10.3390/app9010104 ◽

2018 ◽

Vol 9 (1) ◽

pp. 104 ◽

Cited By ~ 1

Author(s):

Kejun Long ◽

Wukai Yao ◽

Jian Gu ◽

Wei Wu ◽

Lee Han

Keyword(s):

Neural Network ◽

Travel Time ◽

Bp Neural Network ◽

Historical Data ◽

Multiple Source ◽

Function Parameter ◽

Support Vector ◽

Model Parameters ◽

Svm Model ◽

Adverse Weather

Freeway travel time is influenced by many factors including traffic volume, adverse weather, accidents, traffic control, and so on. We employ the multiple source data-mining method to analyze freeway travel time. We collected toll data, weather data, traffic accident disposal logs, and other historical data from Freeway G5513 in Hunan Province, China. Using the Support Vector Machine (SVM), we proposed the travel time predicting model founded on these databases. The new SVM model can simulate the nonlinear relationship between travel time and those factors. In order to improve the precision of the SVM model, we applied the Artificial Fish Swarm algorithm to optimize the SVM model parameters, which include the kernel parameter σ, non-sensitive loss function parameter ε, and penalty parameter C. We compared the new optimized SVM model with the Back Propagation (BP) neural network and a common SVM model, using the historical data collected from freeway G5513. The results show that the accuracy of the optimized SVM model is 17.27% and 16.44% higher than those of the BP neural network model and the common SVM model, respectively.

Download Full-text

Structural Damage Localization Based on AR Model and BP Neural Network

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.94-96.1211 ◽

2011 ◽

Vol 94-96 ◽

pp. 1211-1215

Author(s):

Yan Song Diao ◽

Fei Yu ◽

Dong Mei Meng

Keyword(s):

Neural Network ◽

Bp Neural Network ◽

Structural Damage ◽

Ar Model ◽

Model Parameters ◽

Damage Localization ◽

Modal Parameter ◽

Damage Location ◽

Simulation And Experiment ◽

Damage Characteristic

When the AR model is used to identify the structural damage, one problem is often met, that is the method can only make a decision whether the structure is damaged, however, the damage location can not be identified exactly. A structural damage localization method based on AR model in combination with BP neural network is proposed in this paper. The AR time series models are used to describe the acceleration responses. The changes of the first 3-order AR model parameters are extracted and composed as damage characteristic vectors which are put into BP neural network to identify the damage location. The effectiveness of the method is validated by the results of numerical simulation and experiment for a four-layer offshore platform. Only the acceleration responses can be used adequately to localize the structural damage, without the usage of modal parameter and excitation force. Thus the dependence on the modal parameter and excitation can be avoided in this method.

Download Full-text

Resistivity-depth Imaging with the Airborne Transient Electromagnetic Method Based on an Artificial Neural Network

Journal of Environmental and Engineering Geophysics ◽

10.32389/jeeg19-087 ◽

2020 ◽

Vol 25 (3) ◽

pp. 355-368

Author(s):

Bing Feng ◽

Ji-feng Zhang ◽

Dong Li ◽

Yang Bai

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Bp Neural Network ◽

Apparent Resistivity ◽

Electromagnetic Method ◽

Electromagnetic Response ◽

Model Parameters ◽

Transient Electromagnetic Method ◽

Transient Electromagnetic ◽

Artificial Neural

We developed an artificial neural network to map the distribution of geologic conductivity in the earth subsurface using the airborne transient electromagnetic method. The artificial neural network avoids the need for complex derivations of electromagnetic field formulas and requires only input and transfer functions to obtain a quasi-resistivity image. First, training sample set from the airborne transient electromagnetic response of homogeneous half-space models with different resistivities was formed, and network model parameters, including the flight altitude, time constant, and response amplitude, were determined. Then, a double-hidden-layer back-propagation (BP) neural network was established based on the mapping relationship between quasi-resistivity and airborne transient electromagnetic response. By analyzing the mean square error curve, the training termination criterion of the BP neural network was determined. Next, the trained BP neural network was used to interpret the airborne transient electromagnetic responses of various typical layered geo-electric models, and the results were compared with that from the all-time apparent resistivity algorithm. The comparison indicated that the resistivity imaging from the BP neural network approach was much closer to the true resistivity of the model, and the response to anomalous bodies was better than that from an all-time apparent resistivity. Finally, this imaging technique was used to process field data acquired by employing the airborne transient method from the HuaYin survey area. Quasi-resistivity depth sections calculated with the BP neural network and the actual geological situation were in good.

Download Full-text