Coordinate descent method is a unconstrained optimization technique. When it is applied to support vector machine （SVM）, at each step the method updates one component of w by solving a one-variable sub-problem while...Coordinate descent method is a unconstrained optimization technique. When it is applied to support vector machine （SVM）, at each step the method updates one component of w by solving a one-variable sub-problem while fixing other components. All components of w update after one iteration. Then go to next iteration. Though the method converges and converges fast in the beginning, it converges slow for final convergence. To improve the speed of final convergence of coordinate descent method, Hooke and Jeeves algorithm which adds pattern search after every iteration in coordinate descent method was applied to SVM and a global Newton algorithm was used to solve one-variable subproblems. We proved the convergence of the algorithm. Experimental results show Hooke and Jeeves＇ method does accelerate convergence specially for final convergence and achieves higher testing accuracy more quickly in classification.展开更多
Though the preferred welding process to weld aluminium alloy is frequently constant current gas tungsten arc welding (CCGTAW),it resulted in grain coarsening at the fusion zone and heat affected zone(HAZ).Hence,pulsed...Though the preferred welding process to weld aluminium alloy is frequently constant current gas tungsten arc welding (CCGTAW),it resulted in grain coarsening at the fusion zone and heat affected zone(HAZ).Hence,pulsed current gas tungsten arc welding(PCGTAW) was performed,to yield finer fusion zone grains,which leads to higher strength of AA6061 (Al-Mg-Si) aluminium alloy joints.In order to determine the most influential control factors which will yield minimum fusion zone grain size and maximum tensile strength of the joints,the traditional Hooke and Jeeves pattern search method was used.The experiments were carried out based on central composite design with 31 runs and an algorithm was developed to optimize the fusion zone grain size and the tensile strength of pulsed current gas tungsten arc welded AA6061 aluminium alloy joints.The results indicate that the peak current (Ip) and base current (IB) are the most significant parameters,to decide the fusion zone grain size and the tensile strength of the AA6061 aluminum alloy joints.展开更多
AISI 304L is an austenitic Chromium-Nickel stainless steel offering the optimum combination of corrosion resistance, strength and ductility. These attributes make it a favorite for many mechanical components. The pape...AISI 304L is an austenitic Chromium-Nickel stainless steel offering the optimum combination of corrosion resistance, strength and ductility. These attributes make it a favorite for many mechanical components. The paper focuses on developing mathematical models to predict grain size and hardness of pulsed current micro plasma arc welded AISI 304L joints. Four factors, five level, central composite rotatable design matrix is used to optimize the number of experiments. The mathematical models have been developed by Response Surface Method (RSM) and its adequacy is checked by Analysis of Variance (ANOVA) technique. By using the developed mathematical models, grain size and hardness of the weld joints can be predicted with 99% confidence level. The developed mathematical models have been optimized using Hooke and Jeeves algorithm to minimize grain size and maximize the hardness.展开更多
基金supported by the National Natural Science Foundation of China (6057407560705004)
文摘Coordinate descent method is a unconstrained optimization technique. When it is applied to support vector machine （SVM）, at each step the method updates one component of w by solving a one-variable sub-problem while fixing other components. All components of w update after one iteration. Then go to next iteration. Though the method converges and converges fast in the beginning, it converges slow for final convergence. To improve the speed of final convergence of coordinate descent method, Hooke and Jeeves algorithm which adds pattern search after every iteration in coordinate descent method was applied to SVM and a global Newton algorithm was used to solve one-variable subproblems. We proved the convergence of the algorithm. Experimental results show Hooke and Jeeves＇ method does accelerate convergence specially for final convergence and achieves higher testing accuracy more quickly in classification.
基金Naval Research Board (NRB),Ministry of Defence,New Delhi for the financial support to carry out this investigation through sponsored project No.DNRD/05/4003/NRB/67.
文摘Though the preferred welding process to weld aluminium alloy is frequently constant current gas tungsten arc welding (CCGTAW),it resulted in grain coarsening at the fusion zone and heat affected zone(HAZ).Hence,pulsed current gas tungsten arc welding(PCGTAW) was performed,to yield finer fusion zone grains,which leads to higher strength of AA6061 (Al-Mg-Si) aluminium alloy joints.In order to determine the most influential control factors which will yield minimum fusion zone grain size and maximum tensile strength of the joints,the traditional Hooke and Jeeves pattern search method was used.The experiments were carried out based on central composite design with 31 runs and an algorithm was developed to optimize the fusion zone grain size and the tensile strength of pulsed current gas tungsten arc welded AA6061 aluminium alloy joints.The results indicate that the peak current (Ip) and base current (IB) are the most significant parameters,to decide the fusion zone grain size and the tensile strength of the AA6061 aluminum alloy joints.
文摘AISI 304L is an austenitic Chromium-Nickel stainless steel offering the optimum combination of corrosion resistance, strength and ductility. These attributes make it a favorite for many mechanical components. The paper focuses on developing mathematical models to predict grain size and hardness of pulsed current micro plasma arc welded AISI 304L joints. Four factors, five level, central composite rotatable design matrix is used to optimize the number of experiments. The mathematical models have been developed by Response Surface Method (RSM) and its adequacy is checked by Analysis of Variance (ANOVA) technique. By using the developed mathematical models, grain size and hardness of the weld joints can be predicted with 99% confidence level. The developed mathematical models have been optimized using Hooke and Jeeves algorithm to minimize grain size and maximize the hardness.
