Gaussian process(GP)has fewer parameters,simple model and output of probabilistic sense,when compared with the methods such as support vector machines.Selection of the hyper-parameters is critical to the performance o...Gaussian process(GP)has fewer parameters,simple model and output of probabilistic sense,when compared with the methods such as support vector machines.Selection of the hyper-parameters is critical to the performance of Gaussian process model.However,the common-used algorithm has the disadvantages of difficult determination of iteration steps,over-dependence of optimization effect on initial values,and easily falling into local optimum.To solve this problem,a method combining the Gaussian process with memetic algorithm was proposed.Based on this method,memetic algorithm was used to search the optimal hyper parameters of Gaussian process regression(GPR)model in the training process and form MA-GPR algorithms,and then the model was used to predict and test the results.When used in the marine long-range precision strike system(LPSS)battle effectiveness evaluation,the proposed MA-GPR model significantly improved the prediction accuracy,compared with the conjugate gradient method and the genetic algorithm optimization process.展开更多
Remaining useful life(RUL) prediction is one of the most crucial elements in prognostics and health management(PHM). Aiming at the imperfect prior information, this paper proposes an RUL prediction method based on a n...Remaining useful life(RUL) prediction is one of the most crucial elements in prognostics and health management(PHM). Aiming at the imperfect prior information, this paper proposes an RUL prediction method based on a nonlinear random coefficient regression(RCR) model with fusing failure time data.Firstly, some interesting natures of parameters estimation based on the nonlinear RCR model are given. Based on these natures,the failure time data can be fused as the prior information reasonably. Specifically, the fixed parameters are calculated by the field degradation data of the evaluated equipment and the prior information of random coefficient is estimated with fusing the failure time data of congeneric equipment. Then, the prior information of the random coefficient is updated online under the Bayesian framework, the probability density function(PDF) of the RUL with considering the limitation of the failure threshold is performed. Finally, two case studies are used for experimental verification. Compared with the traditional Bayesian method, the proposed method can effectively reduce the influence of imperfect prior information and improve the accuracy of RUL prediction.展开更多
Additive Manufacturing(AM)can provide customized parts that conventional techniques fail to deliver.One important parameter in AM is the quality of the parts,as a result of the material extrusion 3D printing(3D-P)proc...Additive Manufacturing(AM)can provide customized parts that conventional techniques fail to deliver.One important parameter in AM is the quality of the parts,as a result of the material extrusion 3D printing(3D-P)procedure.This can be very important in defense-related applications,where optimum performance needs to be guaranteed.The quality of the Polyetherimide 3D-P specimens was examined by considering six control parameters,namely,infill percentage,layer height,deposition angle,travel speed,nozzle,and bed temperature.The quality indicators were the root mean square(Rq)and average(Ra)roughness,porosity,and the actual to nominal dimensional deviation.The examination was performed with optical profilometry,optical microscopy,and micro-computed tomography scanning.The Taguchi design of experiments was applied,with twenty-five runs,five levels for each control parameter,on five replicas.Two additional confirmation runs were conducted,to ensure reliability.Prediction equations were constructed to express the quality indicators in terms of the control parameters.Three modeling approaches were applied to the experimental data,to compare their efficiency,i.e.,Linear Regression Model(LRM),Reduced Quadratic Regression Model,and Quadratic Regression Model(QRM).QRM was the most accurate one,still the differences were not high even considering the simpler LRM model.展开更多
Because of the relativity among the parameters, partial least square regression(PLSR)was applied to build the model and get the regression equation. The improved algorithm simplified the calculating process greatly be...Because of the relativity among the parameters, partial least square regression(PLSR)was applied to build the model and get the regression equation. The improved algorithm simplified the calculating process greatly because of the reduction of calculation. The orthogonal design was adopted in this experiment. Every sample had strong representation, which could reduce the experimental time and obtain the overall test data. Combined with the formation problem of gas metal arc weld with big current, the auxiliary analysis technique of PLSR was discussed and the regression equation of form factors (i.e. surface width, weld penetration and weld reinforcement) to process parameters(i.e. wire feed rate, wire extension, welding speed, gas flow, welding voltage and welding current)was given. The correlativity structure among variables was analyzed and there was certain correlation between independent variables matrix X and dependent variables matrix Y. The regression analysis shows that the welding speed mainly influences the weld formation while the variation of gas flow in certain range has little influence on formation of weld. The fitting plot of regression accuracy is given. The fitting quality of regression equation is basically satisfactory.展开更多
Using the orthogonal experimental design method involving three factors and three levels, the flexural strength and the compressive strength of copolymer grouting material were studied with different compositions of w...Using the orthogonal experimental design method involving three factors and three levels, the flexural strength and the compressive strength of copolymer grouting material were studied with different compositions of water-cement ratio （mass fraction of water to cement）, epoxy resin content, and waterborne epoxy curing agent content. By orthogonal range and variance analysis, the orders of three factors to influence the strength, the significance levels of different factors, and the optimized compound ratio scheme of copolymer grouting material mixture at different curing ages were determined. An empirical relationship among the strength of copolymer grouting material, the water-cement ratio, the epoxy resin content, and the waterborne epoxy curing agent content was established by multivariate regression analysis. The results indicate that water-cement ratio is the most principal and significant influencing factor on the strength. Epoxy resin content and waterbome epoxy curing agent content also have a significant influence on the strength. But epoxy resin content has a greater influence on the 7-day and 28-day flexural strength, and waterborne epoxy curing agent content has a greater influence on the 3-day flexural strength and the compressive strength. The copolymer grouting material with water-cement ratio of 0.4, epoxy resin content of 8% （mass fraction） and waterbome epoxy curing agent content of 2% （mass fraction） is the best one for repairing of cement concrete pavement. The flexural strength and the compressive strength have good correlation, and the ratio of compressive strength to flexural strength is between 1.0 and 3.3.展开更多
The adaptive neuro-fuzzy inference systems(ANFIS)are widely used in the concrete technology.In this research,the compressive strength of light weight concrete was determined.To this end,the scoria percentage and curin...The adaptive neuro-fuzzy inference systems(ANFIS)are widely used in the concrete technology.In this research,the compressive strength of light weight concrete was determined.To this end,the scoria percentage and curing day variables were used as the input parameters,and compressive strength and tensile strength were used as the output parameters.In addition,100 patterns were used,70%of which were used for training and 30%were used for testing.To assess the precision of the neuro-fuzzy system,it was compared using two linear regression models.The comparisons were carried out in the training and testing phases.Research results revealed that the neuro-fuzzy systems model offers more potential,flexibility,and precision than the statistical models.展开更多
This paper contributed to the pool of studies about agricultural surplus labor in China, also acted as the root to the imminent settlement of the issues concerning agriculture, countryside and farmers. Using data from...This paper contributed to the pool of studies about agricultural surplus labor in China, also acted as the root to the imminent settlement of the issues concerning agriculture, countryside and farmers. Using data from survey of agricultural surplus labor in 2012, which covered three provinces in northern, midwestem and southern parts of China, this paper analyzed the influential factors on agricultural surplus labor professionalization by adoption of a logistic regression model. It showed that agricultural surplus labor shortage could be explained by low-quality professionalization. It was a feasible and effective way to solve the issue of workforce shortage during economic downturn by improving agricultural surplus labor＇s professionalization.展开更多
基金Project(513300303)supported by the General Armament Department,China
文摘Gaussian process(GP)has fewer parameters,simple model and output of probabilistic sense,when compared with the methods such as support vector machines.Selection of the hyper-parameters is critical to the performance of Gaussian process model.However,the common-used algorithm has the disadvantages of difficult determination of iteration steps,over-dependence of optimization effect on initial values,and easily falling into local optimum.To solve this problem,a method combining the Gaussian process with memetic algorithm was proposed.Based on this method,memetic algorithm was used to search the optimal hyper parameters of Gaussian process regression(GPR)model in the training process and form MA-GPR algorithms,and then the model was used to predict and test the results.When used in the marine long-range precision strike system(LPSS)battle effectiveness evaluation,the proposed MA-GPR model significantly improved the prediction accuracy,compared with the conjugate gradient method and the genetic algorithm optimization process.
基金supported by National Natural Science Foundation of China (61703410,61873175,62073336,61873273,61773386,61922089)。
文摘Remaining useful life(RUL) prediction is one of the most crucial elements in prognostics and health management(PHM). Aiming at the imperfect prior information, this paper proposes an RUL prediction method based on a nonlinear random coefficient regression(RCR) model with fusing failure time data.Firstly, some interesting natures of parameters estimation based on the nonlinear RCR model are given. Based on these natures,the failure time data can be fused as the prior information reasonably. Specifically, the fixed parameters are calculated by the field degradation data of the evaluated equipment and the prior information of random coefficient is estimated with fusing the failure time data of congeneric equipment. Then, the prior information of the random coefficient is updated online under the Bayesian framework, the probability density function(PDF) of the RUL with considering the limitation of the failure threshold is performed. Finally, two case studies are used for experimental verification. Compared with the traditional Bayesian method, the proposed method can effectively reduce the influence of imperfect prior information and improve the accuracy of RUL prediction.
文摘Additive Manufacturing(AM)can provide customized parts that conventional techniques fail to deliver.One important parameter in AM is the quality of the parts,as a result of the material extrusion 3D printing(3D-P)procedure.This can be very important in defense-related applications,where optimum performance needs to be guaranteed.The quality of the Polyetherimide 3D-P specimens was examined by considering six control parameters,namely,infill percentage,layer height,deposition angle,travel speed,nozzle,and bed temperature.The quality indicators were the root mean square(Rq)and average(Ra)roughness,porosity,and the actual to nominal dimensional deviation.The examination was performed with optical profilometry,optical microscopy,and micro-computed tomography scanning.The Taguchi design of experiments was applied,with twenty-five runs,five levels for each control parameter,on five replicas.Two additional confirmation runs were conducted,to ensure reliability.Prediction equations were constructed to express the quality indicators in terms of the control parameters.Three modeling approaches were applied to the experimental data,to compare their efficiency,i.e.,Linear Regression Model(LRM),Reduced Quadratic Regression Model,and Quadratic Regression Model(QRM).QRM was the most accurate one,still the differences were not high even considering the simpler LRM model.
文摘Because of the relativity among the parameters, partial least square regression(PLSR)was applied to build the model and get the regression equation. The improved algorithm simplified the calculating process greatly because of the reduction of calculation. The orthogonal design was adopted in this experiment. Every sample had strong representation, which could reduce the experimental time and obtain the overall test data. Combined with the formation problem of gas metal arc weld with big current, the auxiliary analysis technique of PLSR was discussed and the regression equation of form factors (i.e. surface width, weld penetration and weld reinforcement) to process parameters(i.e. wire feed rate, wire extension, welding speed, gas flow, welding voltage and welding current)was given. The correlativity structure among variables was analyzed and there was certain correlation between independent variables matrix X and dependent variables matrix Y. The regression analysis shows that the welding speed mainly influences the weld formation while the variation of gas flow in certain range has little influence on formation of weld. The fitting plot of regression accuracy is given. The fitting quality of regression equation is basically satisfactory.
基金Projects(40728003, 40772180, 40802064) supported by the National Natural Science Foundation of ChinaProject (07JJ4012) supported by the Hunan Provincial Natural Science Foundation of China+1 种基金project (20080430680) supported by China Postdoctoral Science FoundationProject(B308) supported by Shanghai Leading Academic Discipline Project
文摘Using the orthogonal experimental design method involving three factors and three levels, the flexural strength and the compressive strength of copolymer grouting material were studied with different compositions of water-cement ratio （mass fraction of water to cement）, epoxy resin content, and waterborne epoxy curing agent content. By orthogonal range and variance analysis, the orders of three factors to influence the strength, the significance levels of different factors, and the optimized compound ratio scheme of copolymer grouting material mixture at different curing ages were determined. An empirical relationship among the strength of copolymer grouting material, the water-cement ratio, the epoxy resin content, and the waterborne epoxy curing agent content was established by multivariate regression analysis. The results indicate that water-cement ratio is the most principal and significant influencing factor on the strength. Epoxy resin content and waterbome epoxy curing agent content also have a significant influence on the strength. But epoxy resin content has a greater influence on the 7-day and 28-day flexural strength, and waterborne epoxy curing agent content has a greater influence on the 3-day flexural strength and the compressive strength. The copolymer grouting material with water-cement ratio of 0.4, epoxy resin content of 8% （mass fraction） and waterbome epoxy curing agent content of 2% （mass fraction） is the best one for repairing of cement concrete pavement. The flexural strength and the compressive strength have good correlation, and the ratio of compressive strength to flexural strength is between 1.0 and 3.3.
文摘The adaptive neuro-fuzzy inference systems(ANFIS)are widely used in the concrete technology.In this research,the compressive strength of light weight concrete was determined.To this end,the scoria percentage and curing day variables were used as the input parameters,and compressive strength and tensile strength were used as the output parameters.In addition,100 patterns were used,70%of which were used for training and 30%were used for testing.To assess the precision of the neuro-fuzzy system,it was compared using two linear regression models.The comparisons were carried out in the training and testing phases.Research results revealed that the neuro-fuzzy systems model offers more potential,flexibility,and precision than the statistical models.
文摘This paper contributed to the pool of studies about agricultural surplus labor in China, also acted as the root to the imminent settlement of the issues concerning agriculture, countryside and farmers. Using data from survey of agricultural surplus labor in 2012, which covered three provinces in northern, midwestem and southern parts of China, this paper analyzed the influential factors on agricultural surplus labor professionalization by adoption of a logistic regression model. It showed that agricultural surplus labor shortage could be explained by low-quality professionalization. It was a feasible and effective way to solve the issue of workforce shortage during economic downturn by improving agricultural surplus labor＇s professionalization.
