Intelligent Displacement Back Analysis Method of Three-Dimension Applied in Unsymmetrical Pressure Tunnel with Shallow Depth

2011 ◽  
Vol 90-93 ◽  
pp. 2286-2291
Author(s):  
Liang Yong Wan ◽  
Xue Feng Zhang ◽  
Kai Yun Liu
Keyword(s):  
Back Analysis ◽  
Optimization Method ◽  
Small Sample ◽  
Shallow Depth ◽  
Support Vector ◽  
Three Dimension ◽  
Direct Optimization ◽  
Generalization Performance ◽  
Pressure Tunnel ◽  
Displacement Back Analysis

Artificial neural network has been widely used in displacement back analysis, but it has the problems of large sample, over-fitting, local optimization and poor generalization performance, so it has the poor adaptability in the Geotechnical Engineering. Support Vector Machines algorithm has the advantages of small sample, global optimization and generalization performance. A direct optimization method based on genetic algorithm and the improved support vector regression algorithm (GA-SVR) is applied in order to identify multinomial parameters intelligently and forecast displacements fast and exactly, combined with an unsymmetrical pressure tunnel with shallow depth section of the left line of import in BEIKOU Tunnel on Zhangjiakou-Shijiazhuang highway. The application result shows the new type of intelligent displacement back analysis could obtain accurately the parameters of rock mechanics and initial stress in limited monitoring data and provide parameters for ahead-forecast of rock deformation.

Study and Application of Slope Displacement Back Analysis Based on SVM-CTS

2013 ◽  
Vol 353-356 ◽  
pp. 163-166 ◽  
Author(s):  
Fei Xu ◽  
Bo Qin Huang ◽  
Ke Wang
Keyword(s):  
Soil Mechanics ◽  
Back Analysis ◽  
Support Vector ◽  
Local Optimum ◽  
Nonlinear Mapping ◽  
Measuring Point ◽  
Displacement Back Analysis ◽  
The One ◽  
Slope Displacement ◽  
Rock And Soil

A new method of displacement back analysis, named SVM-CTS, was proposed based on support vector machine (SVM) and continuous tabu search (CTS). On the one hand, SVM-CTS used SVM to build the nonlinear mapping relationship between the measuring point displacements and rock and soil mechanics parameters of positive analysis based on the study samples. On the other hand, SVM-CTS used the global optimization performance of CTS to catch the optimal rock and soil mechanics parameters in the global space. The nonlinear mapping relationship built by SVM can fit and forecast the measuring point displacements under different parameters with high accuracy. CTS can prevent object function from trapping in local optimum and improve precision of back analysis. Case study shows that SVM-CTS can be well applied to the displacement back analysis in geotechnical engineering.

The Viscoelastic-Plastic Displacement Back Analysis of Rock Mass with Non-Stationary Parameters

2012 ◽  
Vol 455-456 ◽  
pp. 1538-1544 ◽  
Author(s):  
Quan Sheng Liu ◽  
Jin Lan Li
Keyword(s):  
Rock Mass ◽  
Back Analysis ◽  
Optimization Method ◽  
Finite Element Program ◽  
Displacement Back Analysis ◽  
Element Program ◽  
Zone Development ◽  
Stationary Creep ◽  
Plastic Displacement ◽  
Creep Constitutive Model

The FEM positive analysis is made using H-K non-stationary creep constitutive model in this paper, the finite element program for non-stationary viscoelastic-plastic displacement back analysis is compiled combining the non-stationary viscoelastic-plastic program with the complex shape optimization method, and the displacement back analysis of soft tunnel engineering is conducted. The result indicates that the viscous aging characteristics of rock mass can be reflected objectively if rock mass is regarded as non-stationary viscoelastic-plastic model, and the plastic zone development of surrounding rock can be predicted considering the plastic flow of rock mass and regarding the back analysis results as the calculation parameters.

Study and Application of Displacement Back Analysis Based on CACA-SVM

2013 ◽  
Vol 353-356 ◽  
pp. 142-145
Author(s):  
Fei Xu ◽  
Bin Li ◽  
Ke Wang
Keyword(s):  
Ant Colony Algorithm ◽  
Back Analysis ◽  
Engineering Problem ◽  
Support Vector ◽  
Local Optimum ◽  
Nonlinear Mapping ◽  
Measuring Point ◽  
Displacement Back Analysis ◽  
The One

An new intelligent displacement back analysis, named as CACA-SVM, was proposed based on support vector machine (SVM) and Continuous Ant Colony Algorithm (CACA). On the one hand, CACA-SVM used SVM to build the nonlinear mapping relationship between them. On the other hand, CACA-SVM used the global optimization performance of CACA to search the optimal rock mechanics parameters in the global space. The nonlinear mapping relationship built by SVM can fit and forecast the measuring point displacements under different parameters with high accuracy, avoiding the complex numerical calculation. CACA can prevent object function from trapping in local optimum and improve precision of back analysis. Case study shows that the forecasting trend was in good agreement with the measured trend, which indicated that the model was suitable for solving the geotechnical engineering problem of nonlinearity and uncertainty and could well be applied to displacement back analysis.

Fault Diagnosis Method of Mine Motor Based on Support Vector Machine

2019 ◽  
Vol 13 ◽  
Author(s):  
Yan Zhang ◽  
Ren Sheng
Keyword(s):  
Support Vector Machine ◽  
Fault Diagnosis ◽  
Optimization Method ◽  
Support Vector ◽  
Optimal Parameters ◽  
Instantaneous Power ◽  
Practical Usefulness ◽  
Sample Data ◽  
Diagnosis Method ◽  
Fault Characteristic

Background: In order to improve the efficiency of fault treatment of mining motor, the method of model construction is used to construct the type of kernel function based on the principle of vector machine classification and the optimization method of parameters. Methodology: One-to-many algorithm is used to establish two kinds of support vector machine models for fault diagnosis of motor rotor of crusher. One of them is to obtain the optimal parameters C and g based on the input samples of the instantaneous power fault characteristic data of some motor rotors which have not been processed by rough sets. Patents on machine learning have also shows their practical usefulness in the selction of the feature for fault detection. Results: The results show that the instantaneous power fault feature extracted from the rotor of the crusher motor is obtained by the cross validation method of grid search k-weights (where k is 3) and the final data of the applied Gauss radial basis penalty parameter C and the nuclear parameter g are obtained. Conclusion: The model established by the optimal parameters is used to classify and diagnose the sample of instantaneous power fault characteristic measurement of motor rotor. Therefore, the classification accuracy of the sample data processed by rough set is higher.

scholarly journals G-computation and machine learning for estimating the causal effects of binary exposure statuses on binary outcomes

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Florent Le Borgne ◽  
Arthur Chatton ◽  
Maxime Léger ◽  
Rémi Lenain ◽  
Yohann Foucher
Keyword(s):  
Machine Learning ◽  
Support Vector Machine ◽  
Statistical Power ◽  
Small Sample ◽  
Causal Effects ◽  
Small Samples ◽  
Support Vector ◽  
Sample Sizes ◽  
Super Learner ◽  
Small Sample Sizes

AbstractIn clinical research, there is a growing interest in the use of propensity score-based methods to estimate causal effects. G-computation is an alternative because of its high statistical power. Machine learning is also increasingly used because of its possible robustness to model misspecification. In this paper, we aimed to propose an approach that combines machine learning and G-computation when both the outcome and the exposure status are binary and is able to deal with small samples. We evaluated the performances of several methods, including penalized logistic regressions, a neural network, a support vector machine, boosted classification and regression trees, and a super learner through simulations. We proposed six different scenarios characterised by various sample sizes, numbers of covariates and relationships between covariates, exposure statuses, and outcomes. We have also illustrated the application of these methods, in which they were used to estimate the efficacy of barbiturates prescribed during the first 24 h of an episode of intracranial hypertension. In the context of GC, for estimating the individual outcome probabilities in two counterfactual worlds, we reported that the super learner tended to outperform the other approaches in terms of both bias and variance, especially for small sample sizes. The support vector machine performed well, but its mean bias was slightly higher than that of the super learner. In the investigated scenarios, G-computation associated with the super learner was a performant method for drawing causal inferences, even from small sample sizes.

Well Placement Technique and Production Optimization for Mature Field - A Case Study of L-X Field

2020 ◽  
Vol 46 ◽  
pp. 168-179
Author(s):  
Patrick Nwafor ◽  
Kelani Bello
Keyword(s):  
Oil And Gas ◽  
Optimization Technique ◽  
Optimal Solution ◽  
Oil And Gas Industry ◽  
Optimization Method ◽  
Simulation Software ◽  
Production Optimization ◽  
Direct Optimization ◽  
Well Placement ◽  
Local Optimal Solution

A Well placement is a well-known technique in the oil and gas industry for production optimization and are generally classified into local and global methods. The use of simulation software often deployed under the direct optimization technique called global method. The production optimization of L-X field which is at primary recovery stage having five producing wells was the focus of this work. The attempt was to optimize L-X field using a well placement technique.The local methods are generally very efficient and require only a few forward simulations but can get stuck in a local optimal solution. The global methods avoid this problem but require many forward simulations. With the availability of simulator software, such problem can be reduced thus using the direct optimization method. After optimization an increase in recovery factor of over 20% was achieved. The results provided an improvement when compared with other existing methods from the literatures.

A novel sensor array and classifier optimization method of electronic nose based on enhanced quantum-behaved particle swarm optimization

Sensor Review ◽  
2014 ◽  
Vol 34 (3) ◽  
pp. 304-311 ◽  
Author(s):  
Pengfei Jia ◽  
Fengchun Tian ◽  
Shu Fan ◽  
Qinghua He ◽  
Jingwei Feng ◽  
...  
Keyword(s):  
Particle Swarm Optimization ◽  
Wound Infection ◽  
Electronic Nose ◽  
Classification Accuracy ◽  
Sensor Array ◽  
Particle Swarm ◽  
Optimization Method ◽  
Support Vector ◽  
Swarm Optimization ◽  
Content Type

Purpose – The purpose of the paper is to propose a new optimization algorithm to realize a synchronous optimization of sensor array and classifier, to improve the performance of E-nose in the detection of wound infection. When an electronic nose (E-nose) is used to detect the wound infection, sensor array’s optimization and parameters’ setting of classifier have a strong impact on the classification accuracy. Design/methodology/approach – An enhanced quantum-behaved particle swarm optimization based on genetic algorithm, genetic quantum-behaved particle swarm optimization (G-QPSO), is proposed to realize a synchronous optimization of sensor array and classifier. The importance-factor (I-F) method is used to weight the sensors of E-nose by its degree of importance in classification. Both radical basis function network and support vector machine are used for classification. Findings – The classification accuracy of E-nose is the highest when the weighting coefficients of the I-F method and classifier’s parameters are optimized by G-QPSO. All results make it clear that the proposed method is an ideal optimization method of E-nose in the detection of wound infection. Research limitations/implications – To make the proposed optimization method more effective, the key point of further research is to enhance the classifier of E-nose. Practical implications – In this paper, E-nose is used to distinguish the class of wound infection; meanwhile, G-QPSO is used to realize a synchronous optimization of sensor array and classifier of E-nose. These are all important for E-nose to realize its clinical application in wound monitoring. Originality/value – The innovative concept improves the performance of E-nose in wound monitoring and paves the way for the clinical detection of E-nose.

Back Analysis Methods in Geotechnical Engineering

2014 ◽  
Vol 1020 ◽  
pp. 423-428 ◽  
Author(s):  
Eva Hrubesova ◽  
Marek Mohyla
Keyword(s):  
Rock Mass ◽  
Geotechnical Engineering ◽  
Back Analysis ◽  
Rheological Parameters ◽  
Analysis Method ◽  
Direct Optimization ◽  
Initial Stress State ◽  
Analytical Functions ◽  
Is Evaluation

The paper deals with the back analysis method in geotechnical engineering, that goal is evaluation the more objective and reliable parameters of the rock mass on the basis of in-situ measurements. Stress, deformational, strength and rheological parameters of the rock mass are usually determined by some inaccuracies and errors arising from the complexity and variability of the rock mass. This higher or lower degree of imprecision is reflected in the reliability of the mathematical modelling results. The paper presents the utilization of direct optimization back analysis method, based on the theory of analytical functions of complex variable and Kolosov-Muschelischvili relations, to the evaluation of initial stress state inside the rock massif.

Multi-Objective Topology Optimization for Bevel Gear and Geometrical Reconstruction

2013 ◽  
Vol 278-280 ◽  
pp. 139-142
Author(s):  
Xiang Bian ◽  
Zong De Fang ◽  
Kun Qin ◽  
Lifei Lian ◽  
Bao Yu Zhang
Keyword(s):  
Topology Optimization ◽  
Optimization Method ◽  
Tooth Root ◽  
Multi Objective Optimization ◽  
Direct Optimization ◽  
Multi Objective ◽  
Gear Modification ◽  
Parametric Cad ◽  
Straight Lines ◽  
Root Stress

Usually the gear modification is a main measure to reduce the vibration and noise of the gears, but in view of the complexity of the gear modification, topology optimization method was used to optimize the structure of the gear. The minimum volume was set as the direct optimization goal. To achieve the target of reducing contact stress, tooth root bending stress and improving flexibility, the upper bound of the stress and lower bound of the flexibility were set appropriately, thus realizing multi-objective optimization indirectly. A method for converting topology result into parametric CAD model which can be modified was presented, by fitting the topology result with simple straight lines and arcs, the model can be smoothed automatically, after further regulating, the geometry reconstruction was finished. After topology optimization, the resulting structure and properties of the gear are consistent with cavity gear. While reducing the weight of the gear, the noise can be reduced and its life would be extended through increasing flexibility and reducing tooth root stress.

Sign in / Sign up

Export Citation Format

Share Document