This study aims to predict ground surface settlement due to shallow tunneling and introduce the most affecting parameters on this phenomenon.Based on data collected from Shanghai LRT Line 2 project undertaken by TBM-E...This study aims to predict ground surface settlement due to shallow tunneling and introduce the most affecting parameters on this phenomenon.Based on data collected from Shanghai LRT Line 2 project undertaken by TBM-EPB method,this research has considered the tunnel's geometric,strength,and operational factors as the dependent variables.At first,multiple regression(MR) method was used to propose equations based on various parameters.The results indicated the dependency of surface settlement on many parameters so that the interactions among different parameters make it impossible to use MR method as it leads to equations of poor accuracy.As such,adaptive neuro-fuzzy inference system(ANFIS),was used to evaluate its capabilities in terms of predicting surface settlement.Among generated ANFIS models,the model with all input parameters considered produced the best prediction,so as its associated R^2 in the test phase was obtained to be 0.957.The equations and models in which operational factors were taken into consideration gave better prediction results indicating larger relative effect of such factors.For sensitivity analysis of ANFIS model,cosine amplitude method(CAM) was employed; among other dependent variables,fill factor of grouting(n) and grouting pressure(P) were identified as the most affecting parameters.展开更多
In order to solve the non-linear and high-dimensional optimization problems more effectively, an improved self-adaptive membrane computing(ISMC) optimization algorithm was proposed. The proposed ISMC algorithm applied...In order to solve the non-linear and high-dimensional optimization problems more effectively, an improved self-adaptive membrane computing(ISMC) optimization algorithm was proposed. The proposed ISMC algorithm applied improved self-adaptive crossover and mutation formulae that can provide appropriate crossover operator and mutation operator based on different functions of the objects and the number of iterations. The performance of ISMC was tested by the benchmark functions. The simulation results for residue hydrogenating kinetics model parameter estimation show that the proposed method is superior to the traditional intelligent algorithms in terms of convergence accuracy and stability in solving the complex parameter optimization problems.展开更多
In order to study the bending behavior of aluminum alloy 7050 thick plate during snake hot rolling, several coupled thermo-mechanical finite element(FE) models were established. Effects of different initial thicknesse...In order to study the bending behavior of aluminum alloy 7050 thick plate during snake hot rolling, several coupled thermo-mechanical finite element(FE) models were established. Effects of different initial thicknesses, pass reductions, speed ratios and offset distances on the bending value of the plate were analyzed. ‘Quasi smooth plate' and optimum offset distance were defined and quasi smooth plate could be acquired by adjusting offset distance, and then bending control equation was fitted. The results show that bending value of the plate as well as the extent of the increase grows with the increase of pass reduction and decrease of initial thickness; the bending value firstly increases and then keeps steady with the ascending speed ratio; the bending value can be reduced by enlarging the offset distance. The optimum offset distance varies for different rolling parameters and it is augmented with the increase of pass reduction and speed ratio and the decrease of initial thickness. A proper offset distance for different rolling parameters can be calculated by the bending control equation and this equation can be a guidance to acquire a quasi smooth plate. The FEM results agree well with experimental results.展开更多
The inner relationship between Markov random field(MRF) and Markov chain random field(MCRF) is discussed. MCRF is a special MRF for dealing with high-order interactions of sparse data. It consists of a single spatial ...The inner relationship between Markov random field(MRF) and Markov chain random field(MCRF) is discussed. MCRF is a special MRF for dealing with high-order interactions of sparse data. It consists of a single spatial Markov chain(SMC) that can move in the whole space. Generally, the theoretical backbone of MCRF is conditional independence assumption, which is a way around the problem of knowing joint probabilities of multi-points. This so-called Naive Bayes assumption should not be taken lightly and should be checked whenever possible because it is mathematically difficult to prove. Rather than trap in this independence proving, an appropriate potential function in MRF theory is chosen instead. The MCRF formulas are well deduced and the joint probability of MRF is presented by localization approach, so that the complicated parameter estimation algorithm and iteration process can be avoided. The MCRF model is then applied to the lithofacies identification of a region and compared with triplex Markov chain(TMC) simulation. Analyses show that the MCRF model will not cause underestimation problem and can better reflect the geological sedimentation process.展开更多
Variations between earthquakes result in many factors that influence post-earthquake building damage(e.g.,ground motion parameters,building structure,site information,and quality of construction).Consequently,it is ne...Variations between earthquakes result in many factors that influence post-earthquake building damage(e.g.,ground motion parameters,building structure,site information,and quality of construction).Consequently,it is necessary to develop an appropriate building damage-rate estimation model.The building damage survey data were recorded and constructed into files by the Architecture and Building Research Institute(ABRI),Taiwan for the 1999 Chi-Chi earthquake in the Nantou region as a basis for developing a building damage rate estimation model by applying fuzzy theory to express the fragility curves of buildings as a membership function.Empirical verification was performed using post-earthquake building damage data in the Taichung city that suffered relatively severe damage.Results indicate that fuzzy theory can be applied to predict building damage rates and that the estimated results are similar to actual disaster figures.Prediction of disaster damage using building damage rates can provide a reference for immediate disaster response during earthquakes and for regular disaster prevention and rescue planning.展开更多
文摘This study aims to predict ground surface settlement due to shallow tunneling and introduce the most affecting parameters on this phenomenon.Based on data collected from Shanghai LRT Line 2 project undertaken by TBM-EPB method,this research has considered the tunnel's geometric,strength,and operational factors as the dependent variables.At first,multiple regression(MR) method was used to propose equations based on various parameters.The results indicated the dependency of surface settlement on many parameters so that the interactions among different parameters make it impossible to use MR method as it leads to equations of poor accuracy.As such,adaptive neuro-fuzzy inference system(ANFIS),was used to evaluate its capabilities in terms of predicting surface settlement.Among generated ANFIS models,the model with all input parameters considered produced the best prediction,so as its associated R^2 in the test phase was obtained to be 0.957.The equations and models in which operational factors were taken into consideration gave better prediction results indicating larger relative effect of such factors.For sensitivity analysis of ANFIS model,cosine amplitude method(CAM) was employed; among other dependent variables,fill factor of grouting(n) and grouting pressure(P) were identified as the most affecting parameters.
基金Projects(61203020,61403190)supported by the National Natural Science Foundation of ChinaProject(BK20141461)supported by the Jiangsu Province Natural Science Foundation,China
文摘In order to solve the non-linear and high-dimensional optimization problems more effectively, an improved self-adaptive membrane computing(ISMC) optimization algorithm was proposed. The proposed ISMC algorithm applied improved self-adaptive crossover and mutation formulae that can provide appropriate crossover operator and mutation operator based on different functions of the objects and the number of iterations. The performance of ISMC was tested by the benchmark functions. The simulation results for residue hydrogenating kinetics model parameter estimation show that the proposed method is superior to the traditional intelligent algorithms in terms of convergence accuracy and stability in solving the complex parameter optimization problems.
基金Projects(2012CB619505,2010CB731703)supported by the National Basic Research Program of ChinaProject(CX2013B065)supported by Hunan Provincial Innovation Foundation for Postgraduate,China+1 种基金Project(51405520)supported by the National Natural Science Foundation of ChinaProject(zzyjkt2013-06B)supported by the State Key Laboratory of High Performance Complex Manufacturing(Central South University),China
文摘In order to study the bending behavior of aluminum alloy 7050 thick plate during snake hot rolling, several coupled thermo-mechanical finite element(FE) models were established. Effects of different initial thicknesses, pass reductions, speed ratios and offset distances on the bending value of the plate were analyzed. ‘Quasi smooth plate' and optimum offset distance were defined and quasi smooth plate could be acquired by adjusting offset distance, and then bending control equation was fitted. The results show that bending value of the plate as well as the extent of the increase grows with the increase of pass reduction and decrease of initial thickness; the bending value firstly increases and then keeps steady with the ascending speed ratio; the bending value can be reduced by enlarging the offset distance. The optimum offset distance varies for different rolling parameters and it is augmented with the increase of pass reduction and speed ratio and the decrease of initial thickness. A proper offset distance for different rolling parameters can be calculated by the bending control equation and this equation can be a guidance to acquire a quasi smooth plate. The FEM results agree well with experimental results.
基金Project(2011ZX05002-005-006) supported by the National Science and Technology Major Research Program during the Twelfth Five-Year Plan of China
文摘The inner relationship between Markov random field(MRF) and Markov chain random field(MCRF) is discussed. MCRF is a special MRF for dealing with high-order interactions of sparse data. It consists of a single spatial Markov chain(SMC) that can move in the whole space. Generally, the theoretical backbone of MCRF is conditional independence assumption, which is a way around the problem of knowing joint probabilities of multi-points. This so-called Naive Bayes assumption should not be taken lightly and should be checked whenever possible because it is mathematically difficult to prove. Rather than trap in this independence proving, an appropriate potential function in MRF theory is chosen instead. The MCRF formulas are well deduced and the joint probability of MRF is presented by localization approach, so that the complicated parameter estimation algorithm and iteration process can be avoided. The MCRF model is then applied to the lithofacies identification of a region and compared with triplex Markov chain(TMC) simulation. Analyses show that the MCRF model will not cause underestimation problem and can better reflect the geological sedimentation process.
基金Project(93-2625-Z-027-006)supported by the National Science Council of Taipei,China
文摘Variations between earthquakes result in many factors that influence post-earthquake building damage(e.g.,ground motion parameters,building structure,site information,and quality of construction).Consequently,it is necessary to develop an appropriate building damage-rate estimation model.The building damage survey data were recorded and constructed into files by the Architecture and Building Research Institute(ABRI),Taiwan for the 1999 Chi-Chi earthquake in the Nantou region as a basis for developing a building damage rate estimation model by applying fuzzy theory to express the fragility curves of buildings as a membership function.Empirical verification was performed using post-earthquake building damage data in the Taichung city that suffered relatively severe damage.Results indicate that fuzzy theory can be applied to predict building damage rates and that the estimated results are similar to actual disaster figures.Prediction of disaster damage using building damage rates can provide a reference for immediate disaster response during earthquakes and for regular disaster prevention and rescue planning.
