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
Target made of 2519-T87 aluminum alloy was obliquely impacted by a projectile. Microstructural evolution around the crater was investigated by optical microscopy （OM）, transmission electron microscopy （TEM）, and e...Target made of 2519-T87 aluminum alloy was obliquely impacted by a projectile. Microstructural evolution around the crater was investigated by optical microscopy （OM）, transmission electron microscopy （TEM）, and electron backscattered diffraction （EBSD）. The micro-hardness distribution near the crater after impact was studied. The results indicate that at the entering stage, the amount of adiabatic shear band （ASB） is the most, and the precipitates are as fine as those of the target material; the micro-hardness is higher than that at the other stages. At the stable-running stage, the amount of ASB reduces as the micro-bands increase; the precipitates tend to coarsen, which leads to the decrease of the micro-hardness. At the leaving stage, there is a large amount of micro-bands; the precipitates are refined, and the micro-hardness is higher than that at the stable-running stage. The difference in the micro-hardness of the impact stages is due to work hardening and precipitate coarsening, which is caused by adiabatic temperature rise in the alloy.展开更多
Tungsten inert gas （TIG） welded joints for 2219-T87 aluminum alloy are often used in the fuel tanks of large launch vehicles. Because of the massive loads these vehicles carry, dealing with weld reinforcement on TIG...Tungsten inert gas （TIG） welded joints for 2219-T87 aluminum alloy are often used in the fuel tanks of large launch vehicles. Because of the massive loads these vehicles carry, dealing with weld reinforcement on TIG joints represents an important issue in their manufacturing and strength evaluation. Experimental and numerical simulation methods were used to investigate the effects of weld toe shape and weld toe position on the tensile behavior and mechanical properties of these joints. The simulation results indicated that the relative difference in elongation could be as large as 96.9% caused by the difference in weld toe shape. The joints with weld toes located in the weld metal or in the partially melted zone （PMZ） exhibited larger elongation than joints with weld toes located at the juncture of the weld metal and the PMZ.展开更多
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Project (201191107) supported by Science and Technology Plan of Xinjiang,China
文摘Target made of 2519-T87 aluminum alloy was obliquely impacted by a projectile. Microstructural evolution around the crater was investigated by optical microscopy （OM）, transmission electron microscopy （TEM）, and electron backscattered diffraction （EBSD）. The micro-hardness distribution near the crater after impact was studied. The results indicate that at the entering stage, the amount of adiabatic shear band （ASB） is the most, and the precipitates are as fine as those of the target material; the micro-hardness is higher than that at the other stages. At the stable-running stage, the amount of ASB reduces as the micro-bands increase; the precipitates tend to coarsen, which leads to the decrease of the micro-hardness. At the leaving stage, there is a large amount of micro-bands; the precipitates are refined, and the micro-hardness is higher than that at the stable-running stage. The difference in the micro-hardness of the impact stages is due to work hardening and precipitate coarsening, which is caused by adiabatic temperature rise in the alloy.
文摘Tungsten inert gas （TIG） welded joints for 2219-T87 aluminum alloy are often used in the fuel tanks of large launch vehicles. Because of the massive loads these vehicles carry, dealing with weld reinforcement on TIG joints represents an important issue in their manufacturing and strength evaluation. Experimental and numerical simulation methods were used to investigate the effects of weld toe shape and weld toe position on the tensile behavior and mechanical properties of these joints. The simulation results indicated that the relative difference in elongation could be as large as 96.9% caused by the difference in weld toe shape. The joints with weld toes located in the weld metal or in the partially melted zone （PMZ） exhibited larger elongation than joints with weld toes located at the juncture of the weld metal and the PMZ.
