This paper shows a calculation model and a method for predicting the tensile strength of the random distributed short fiber composite.On the basis of Renjie Mao's model,the longitudinal tensile strength of the ali...This paper shows a calculation model and a method for predicting the tensile strength of the random distributed short fiber composite.On the basis of Renjie Mao's model,the longitudinal tensile strength of the aligned short fiber composite is formulated.Considering the transverse tensile strength and in plane shear strength of the unidirectional fiber composite,and the stress transformation relations of two couples of axes,the stress of the unidirectional fiber composite when it is loaded at an arbitrary angle is obtained.With the aid of an equivalence relation,the calculation formulation of the tensile strength of the random short fiber reinforced composite is deduced.展开更多
The ongoing effort to create methods for detecting and quantifying fatigue damage is motivated by the high levels of uncertainty in present fatigue-life prediction approaches and the frequently catastrophic nature of ...The ongoing effort to create methods for detecting and quantifying fatigue damage is motivated by the high levels of uncertainty in present fatigue-life prediction approaches and the frequently catastrophic nature of fatigue failure.The fatigue life of high strength aluminum alloy 2090-T83 is predicted in this study using a variety of artificial intelligence and machine learning techniques for constant amplitude and negative stress ratios(R?1).Artificial neural networks(ANN),adaptive neuro-fuzzy inference systems(ANFIS),support-vector machines(SVM),a random forest model(RF),and an extreme-gradient tree-boosting model(XGB)are trained using numerical and experimental input data obtained from fatigue tests based on a relatively low number of stress measurements.In particular,the coefficients of the traditional force law formula are found using relevant numerical methods.It is shown that,in comparison to traditional approaches,the neural network and neuro-fuzzy models produce better results,with the neural network models trained using the boosting iterations technique providing the best performances.Building strong models from weak models,XGB helps to predict fatigue life by reducing model partiality and variation in supervised learning.Fuzzy neural models can be used to predict the fatigue life of alloys more accurately than neural networks and traditional methods.展开更多
Cutterhead loads are the key mechanical parameters for the strength design of the full face hard rock tunnel boring machine(TBM).Due to the brittle rock-breaking mechanism,the excavation loads acting on cutters fluctu...Cutterhead loads are the key mechanical parameters for the strength design of the full face hard rock tunnel boring machine(TBM).Due to the brittle rock-breaking mechanism,the excavation loads acting on cutters fluctuate strongly and show some randomness.The conventional method that using combinations of some special static loads to perform the strength design of TBM cutterhead may lead to strength failure during working practice.In this paper,a three-dimensional finite element model for coupled Cutterhead–Rock is developed to determine the cutterhead loads.Then the distribution characteristics and the influence factors of cutterhead loads are analyzed based on the numerical results.It is found that,as time changes,the normal and tangential forces acting on cutters and the total torque acting on the cutterhead approximately distribute log normally,while the total thrusts acting on the cutterhead approximately show a normal distribution.Furthermore,the statistical average values of cutterhead loads are proportional to the uniaxial compressive strength(UCS)of cutting rocks.The values also change with the penetration and the diameter of cutterhead following a power function.Based on these findings,we propose a three-parameter model for the mean of cutterhead loads and a method of generating the random cutter forces.Then the strength properties of a typical cutterhead are analyzed in detail using loads generated by the new method.The optimized cutterhead has been successfully applied in engineering.The method in this paper may provide a useful reference for the strength design of TBM cutterhead.展开更多
文摘This paper shows a calculation model and a method for predicting the tensile strength of the random distributed short fiber composite.On the basis of Renjie Mao's model,the longitudinal tensile strength of the aligned short fiber composite is formulated.Considering the transverse tensile strength and in plane shear strength of the unidirectional fiber composite,and the stress transformation relations of two couples of axes,the stress of the unidirectional fiber composite when it is loaded at an arbitrary angle is obtained.With the aid of an equivalence relation,the calculation formulation of the tensile strength of the random short fiber reinforced composite is deduced.
文摘The ongoing effort to create methods for detecting and quantifying fatigue damage is motivated by the high levels of uncertainty in present fatigue-life prediction approaches and the frequently catastrophic nature of fatigue failure.The fatigue life of high strength aluminum alloy 2090-T83 is predicted in this study using a variety of artificial intelligence and machine learning techniques for constant amplitude and negative stress ratios(R?1).Artificial neural networks(ANN),adaptive neuro-fuzzy inference systems(ANFIS),support-vector machines(SVM),a random forest model(RF),and an extreme-gradient tree-boosting model(XGB)are trained using numerical and experimental input data obtained from fatigue tests based on a relatively low number of stress measurements.In particular,the coefficients of the traditional force law formula are found using relevant numerical methods.It is shown that,in comparison to traditional approaches,the neural network and neuro-fuzzy models produce better results,with the neural network models trained using the boosting iterations technique providing the best performances.Building strong models from weak models,XGB helps to predict fatigue life by reducing model partiality and variation in supervised learning.Fuzzy neural models can be used to predict the fatigue life of alloys more accurately than neural networks and traditional methods.
基金Supported by National Basic Research Program of China(973 Program,Grant No.2013CB035042)the National Natural Science Foundation of China(Grant No.11672202)
文摘Cutterhead loads are the key mechanical parameters for the strength design of the full face hard rock tunnel boring machine(TBM).Due to the brittle rock-breaking mechanism,the excavation loads acting on cutters fluctuate strongly and show some randomness.The conventional method that using combinations of some special static loads to perform the strength design of TBM cutterhead may lead to strength failure during working practice.In this paper,a three-dimensional finite element model for coupled Cutterhead–Rock is developed to determine the cutterhead loads.Then the distribution characteristics and the influence factors of cutterhead loads are analyzed based on the numerical results.It is found that,as time changes,the normal and tangential forces acting on cutters and the total torque acting on the cutterhead approximately distribute log normally,while the total thrusts acting on the cutterhead approximately show a normal distribution.Furthermore,the statistical average values of cutterhead loads are proportional to the uniaxial compressive strength(UCS)of cutting rocks.The values also change with the penetration and the diameter of cutterhead following a power function.Based on these findings,we propose a three-parameter model for the mean of cutterhead loads and a method of generating the random cutter forces.Then the strength properties of a typical cutterhead are analyzed in detail using loads generated by the new method.The optimized cutterhead has been successfully applied in engineering.The method in this paper may provide a useful reference for the strength design of TBM cutterhead.
