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
Duplex NiP/TiN coatings consisting of the electroless intermediate layers and the physical vapor deposition(PVD) top layers were fabricated on the AA6061 aluminum alloy in order to enhance the load bearing capacity. T...Duplex NiP/TiN coatings consisting of the electroless intermediate layers and the physical vapor deposition(PVD) top layers were fabricated on the AA6061 aluminum alloy in order to enhance the load bearing capacity. The main objective of this study was to model the load bearing based on the thickness, adhesion and elastic modulus of the coatings. For this purpose, partial least square(PLS) and support vector regression(SVR) approaches were employed.The results showed that both models had an acceptable performance;however, the PLS model outperformed SVR. The correlation coefficients between thickness, adhesion and elastic modulus with load bearing were 0.841, 0.8092 and 0.7657, respectively;so, thickness had the greatest effect on the load bearing capacity. The composition and structure of the samples were evaluated using XRD and SEM. The load capacity of the coated samples was also discussed based on the wear and adhesion evaluations. Dry sliding wear tests, under a load of 2 N and a sliding distance of 100 m,demonstrated the complete destruction of the coated specimens with low load capacity. The samples with high load capacity showed not only a superior tribological performance, but also a remarkable adhesion according to the Rockwell superficial hardness test.展开更多
Filament-induced breakdown spectroscopy(FIBS)combined with machine learning algorithms was used to identify five aluminum alloys.To study the effect of the distance between focusing lens and target surface on the iden...Filament-induced breakdown spectroscopy(FIBS)combined with machine learning algorithms was used to identify five aluminum alloys.To study the effect of the distance between focusing lens and target surface on the identification accuracy of aluminum alloys,principal component analysis(PCA)combined with support vector machine(SVM)and Knearest neighbor(KNN)was used.The intensity and intensity ratio of fifteen lines of six elements(Fe,Si,Mg,Cu,Zn,and Mn)in the FIBS spectrum were selected.The distances between the focusing lens and the target surface in the pre-filament,filament,and post-filament were 958 mm,976 mm,and 1000 mm,respectively.The source data set was fifteen spectral line intensity ratios,and the cumulative interpretation rates of PC1,PC2,and PC3 were 97.22%,98.17%,and 95.31%,respectively.The first three PCs obtained by PCA were the input variables of SVM and KNN.The identification accuracy of the different positions of focusing lens and target surface was obtained,and the identification accuracy of SVM and KNN in the filament was 100%and 90%,respectively.The source data set of the filament was obtained by PCA for the first three PCs,which were randomly selected as the training set and test set of SVM and KNN in 3:2.The identification accuracy of SVM and KNN was 97.5%and 92.5%,respectively.The research results can provide a reference for the identification of aluminum alloys by FIBS.展开更多
采用Gleeble-3500热物理模拟机对7050铝合金进行等温热压缩实验,获得了合金在变形温度为300~450℃以及应变速率为0.001~1 s^(-1)条件下的应力应变数据。在此基础上,建立了经灰狼优化算法(Grey wolf optimization,GWO)优化的反向传播神...采用Gleeble-3500热物理模拟机对7050铝合金进行等温热压缩实验,获得了合金在变形温度为300~450℃以及应变速率为0.001~1 s^(-1)条件下的应力应变数据。在此基础上,建立了经灰狼优化算法(Grey wolf optimization,GWO)优化的反向传播神经网络(BPNN)、支持向量机(SVR)和随机森林(RF)模型并验证其预测精度。结果表明:经过GWO优化的BPNN、SVR和RF模型预测精度高于原始模型;GWO-BPNN与GWO-RF模型的预测精度比较接近,且均高于GWO-SVR;在外推数据预测上,GWO-BPNN模型的预测精度更高,在内插数据预测上,GWO-RF模型的预测精度更高。不同机器学习模型对流动应力数据的拟合效果不同,其预测精度也存在差异。展开更多
The majority of this research has concentrated on developing the self-support friction stir welding（SSFSW） tool which consists of a big concave upper shoulder and a small convex lower shoulder, and procedures for ma...The majority of this research has concentrated on developing the self-support friction stir welding（SSFSW） tool which consists of a big concave upper shoulder and a small convex lower shoulder, and procedures for making reliable welds in aluminum hollow extrusion. The 5-mm-thick 6082-T6 aluminum alloy was self-support friction stir welded at a constant tool rotation speed of 800 r/min. The effect of welding speed on microstructure and mechanical properties was investigated. The results of transverse tensile test indicated that the tensile strength of joints increased and the elongation decreased with increasing welding speed. The whole values of microhardness of SSFSW joints increased with increasing welding speed from 10 to 200 mm/min. The defectfree joints were obtained at lower welding speeds and the tensile fracture was located at the heat-affected zone（HAZ） adjacent to the thermo-mechanically affected zone（TMAZ） on the advancing side. The investigation of the flow pattern of the softened metal around the SSFSW tool revealed that the flow pattern of the softened metal was driven by two shoulders and the stir pin. The failure of specimens in tension presented the ductile fracture mode.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.
文摘Duplex NiP/TiN coatings consisting of the electroless intermediate layers and the physical vapor deposition(PVD) top layers were fabricated on the AA6061 aluminum alloy in order to enhance the load bearing capacity. The main objective of this study was to model the load bearing based on the thickness, adhesion and elastic modulus of the coatings. For this purpose, partial least square(PLS) and support vector regression(SVR) approaches were employed.The results showed that both models had an acceptable performance;however, the PLS model outperformed SVR. The correlation coefficients between thickness, adhesion and elastic modulus with load bearing were 0.841, 0.8092 and 0.7657, respectively;so, thickness had the greatest effect on the load bearing capacity. The composition and structure of the samples were evaluated using XRD and SEM. The load capacity of the coated samples was also discussed based on the wear and adhesion evaluations. Dry sliding wear tests, under a load of 2 N and a sliding distance of 100 m,demonstrated the complete destruction of the coated specimens with low load capacity. The samples with high load capacity showed not only a superior tribological performance, but also a remarkable adhesion according to the Rockwell superficial hardness test.
基金Project supported by the Natural Science Foundation of Jilin Province,China(Grant No.2020122348JC)。
文摘Filament-induced breakdown spectroscopy(FIBS)combined with machine learning algorithms was used to identify five aluminum alloys.To study the effect of the distance between focusing lens and target surface on the identification accuracy of aluminum alloys,principal component analysis(PCA)combined with support vector machine(SVM)and Knearest neighbor(KNN)was used.The intensity and intensity ratio of fifteen lines of six elements(Fe,Si,Mg,Cu,Zn,and Mn)in the FIBS spectrum were selected.The distances between the focusing lens and the target surface in the pre-filament,filament,and post-filament were 958 mm,976 mm,and 1000 mm,respectively.The source data set was fifteen spectral line intensity ratios,and the cumulative interpretation rates of PC1,PC2,and PC3 were 97.22%,98.17%,and 95.31%,respectively.The first three PCs obtained by PCA were the input variables of SVM and KNN.The identification accuracy of the different positions of focusing lens and target surface was obtained,and the identification accuracy of SVM and KNN in the filament was 100%and 90%,respectively.The source data set of the filament was obtained by PCA for the first three PCs,which were randomly selected as the training set and test set of SVM and KNN in 3:2.The identification accuracy of SVM and KNN was 97.5%and 92.5%,respectively.The research results can provide a reference for the identification of aluminum alloys by FIBS.
文摘采用Gleeble-3500热物理模拟机对7050铝合金进行等温热压缩实验,获得了合金在变形温度为300~450℃以及应变速率为0.001~1 s^(-1)条件下的应力应变数据。在此基础上,建立了经灰狼优化算法(Grey wolf optimization,GWO)优化的反向传播神经网络(BPNN)、支持向量机(SVR)和随机森林(RF)模型并验证其预测精度。结果表明:经过GWO优化的BPNN、SVR和RF模型预测精度高于原始模型;GWO-BPNN与GWO-RF模型的预测精度比较接近,且均高于GWO-SVR;在外推数据预测上,GWO-BPNN模型的预测精度更高,在内插数据预测上,GWO-RF模型的预测精度更高。不同机器学习模型对流动应力数据的拟合效果不同,其预测精度也存在差异。
基金supported by the National Natural Science Foundation of China (Nos. 50904020 and 50974046)the Fundamental Research Funds for the Central Universities (No. HIT. NSRIF. 2012007)
文摘The majority of this research has concentrated on developing the self-support friction stir welding（SSFSW） tool which consists of a big concave upper shoulder and a small convex lower shoulder, and procedures for making reliable welds in aluminum hollow extrusion. The 5-mm-thick 6082-T6 aluminum alloy was self-support friction stir welded at a constant tool rotation speed of 800 r/min. The effect of welding speed on microstructure and mechanical properties was investigated. The results of transverse tensile test indicated that the tensile strength of joints increased and the elongation decreased with increasing welding speed. The whole values of microhardness of SSFSW joints increased with increasing welding speed from 10 to 200 mm/min. The defectfree joints were obtained at lower welding speeds and the tensile fracture was located at the heat-affected zone（HAZ） adjacent to the thermo-mechanically affected zone（TMAZ） on the advancing side. The investigation of the flow pattern of the softened metal around the SSFSW tool revealed that the flow pattern of the softened metal was driven by two shoulders and the stir pin. The failure of specimens in tension presented the ductile fracture mode.
