In this paper, a new adaptive optimal guidance law with impact angle and seeker’s field-of-view(FOV) angle constraints is proposed. To this end, the generalized optimal guidance law is derived first. A changeable imp...In this paper, a new adaptive optimal guidance law with impact angle and seeker’s field-of-view(FOV) angle constraints is proposed. To this end, the generalized optimal guidance law is derived first. A changeable impact angle weighting(IAW) coefficient is introduced and used to modify the guidance law to make it adaptive for all guidance constraints. After integrating the closed-form solution of the guidance command with linearized engagement kinematics, the analytic predictive models of impact angle and FOV angle are built, and the available range of IAW corresponding to constraints is certain. Next, a calculation scheme is presented to acquire the real-time value of IAW during the entire guidance process. When applying the proposed guidance law, the IAW will keep small to avoid a trajectory climbing up to limit FOV angle at an initial time but will increase with the closing target to improve impact position and angle accuracy, thereby ensuring that the guidance law can juggle orders of guidance accuracy and constraints control.展开更多
Melanoma is the most lethal malignant tumour,and its prevalence is increasing.Early detection and diagnosis of skin cancer can alert patients to manage precautions and dramatically improve the lives of people.Recently...Melanoma is the most lethal malignant tumour,and its prevalence is increasing.Early detection and diagnosis of skin cancer can alert patients to manage precautions and dramatically improve the lives of people.Recently,deep learning has grown increasingly popular in the extraction and categorization of skin cancer features for effective prediction.A deep learning model learns and co-adapts representations and features from training data to the point where it fails to perform well on test data.As a result,overfitting and poor performance occur.To deal with this issue,we proposed a novel Consecutive Layerwise weight Con-straint MaxNorm model(CLCM-net)for constraining the norm of the weight vector that is scaled each time and bounding to a limit.This method uses deep convolutional neural networks and also custom layer-wise weight constraints that are set to the whole weight matrix directly to learn features efficiently.In this research,a detailed analysis of these weight norms is performed on two distinct datasets,International Skin Imaging Collaboration(ISIC)of 2018 and 2019,which are challenging for convolutional networks to handle.According to thefindings of this work,CLCM-net did a better job of raising the model’s performance by learning the features efficiently within the size limit of weights with appropriate weight constraint settings.The results proved that the proposed techniques achieved 94.42%accuracy on ISIC 2018,91.73%accuracy on ISIC 2019 datasets and 93%of accuracy on combined dataset.展开更多
Existing curve fitting algorithms of NC machining path mainly focus on the control of fitting error,but ignore the problem that the original discrete cutter position points are not enough in the high curvature area of...Existing curve fitting algorithms of NC machining path mainly focus on the control of fitting error,but ignore the problem that the original discrete cutter position points are not enough in the high curvature area of the tool path.It may cause a sudden change in the drive force of the feed axis,resulting in a large fluctuation in the feed speed.This paper proposes a new non-uniform rational B-spline(NURBS)curve fitting optimization method based on curvature smoothing preset point constraints.First,the short line segments generated by the CAM software are optimally divided into different segment regions,and then the curvature of the short line segments in each region is adjusted to make it smoother.Secondly,a set of characteristic points reflecting the change of the curvature of the fitted curve is constructed as the control apex of the fitted curve,and the curve is fitted using the NURBS curve fitting optimization method based on the curvature smoothing preset point constraint.Finally,the curve fitting error and curve volatility are analyzed with an example,which verifies that the method can significantly improve the curvature smoothness of the high-curvature tool path,reduce the fitting error,and improve the feed speed.展开更多
The aim is to put forward the optimal selecting of weights in variational problemin which the linear advection equation is used as constraint. The selection of the functionalweight coefficients ( FWC) is one of the ke...The aim is to put forward the optimal selecting of weights in variational problemin which the linear advection equation is used as constraint. The selection of the functionalweight coefficients ( FWC) is one of the key problems for the relevant research. It wasarbitrary and subjective to some extent presently. To overcome this difficulty, thereasonable assumptions were given for the observation field and analyzed field, variationalproblems with " weak constraints" and " strong constraints" were considered separately. Bysolving Euler' s equation with the matrix theory and the finite difference method of partialdifferential equation, the objective weight coefficients were obtained in the minimumvariance of the difference between the analyzed field and ideal field. Deduction results showthat theoretically the optimal selection indeed exists in the weighting factors of the costfunction in the means of the minimal variance between the analysis and ideal field in terms ofthe matrix theory and partial differential ( corresponding difference ) equation, if thereasonable assumption from the actual problem is valid and the differnece equation is stable.It may realize the coordination among the weight factors, numerical models and theobservational data. With its theoretical basis as well as its prospects of applications, thisobjective selecting method is probably a way towards the finding of the optimal weightingfactors in the variational problem.展开更多
In this work, a new method is presented for determining the binding constraints of a general linear maximization problem. The new method uses only objective function values at points which are determined by simple vec...In this work, a new method is presented for determining the binding constraints of a general linear maximization problem. The new method uses only objective function values at points which are determined by simple vector operations, so the computational cost is inferior to the corresponding cost of matrix manipulation and/or inversion. This method uses a recently proposed notion for addressing such problems: the average of each constraint. The identification of binding constraints decreases the complexity and the dimension of the problem resulting to a significant decrease of the computational cost comparing to Simplex-like methods. The new method is highly useful when dealing with very large linear programming (LP) problems, where only a relatively small percentage of constraints are binding at the optimal solution, as in many transportation, management and economic problems, since it reduces the size of the problem. The method has been implemented and tested in a large number of LP problems. In LP problems without superfluous constraints, the algorithm was 100% successful in identifying binding constraints, while in a set of large scale LP tested problems that included superfluous constraints, the power of the algorithm considered as statistical tool of binding constraints identification, was up to 90.4%.展开更多
基金supported by the Aeronautical Science Foundation of China(20150172001)
文摘In this paper, a new adaptive optimal guidance law with impact angle and seeker’s field-of-view(FOV) angle constraints is proposed. To this end, the generalized optimal guidance law is derived first. A changeable impact angle weighting(IAW) coefficient is introduced and used to modify the guidance law to make it adaptive for all guidance constraints. After integrating the closed-form solution of the guidance command with linearized engagement kinematics, the analytic predictive models of impact angle and FOV angle are built, and the available range of IAW corresponding to constraints is certain. Next, a calculation scheme is presented to acquire the real-time value of IAW during the entire guidance process. When applying the proposed guidance law, the IAW will keep small to avoid a trajectory climbing up to limit FOV angle at an initial time but will increase with the closing target to improve impact position and angle accuracy, thereby ensuring that the guidance law can juggle orders of guidance accuracy and constraints control.
文摘Melanoma is the most lethal malignant tumour,and its prevalence is increasing.Early detection and diagnosis of skin cancer can alert patients to manage precautions and dramatically improve the lives of people.Recently,deep learning has grown increasingly popular in the extraction and categorization of skin cancer features for effective prediction.A deep learning model learns and co-adapts representations and features from training data to the point where it fails to perform well on test data.As a result,overfitting and poor performance occur.To deal with this issue,we proposed a novel Consecutive Layerwise weight Con-straint MaxNorm model(CLCM-net)for constraining the norm of the weight vector that is scaled each time and bounding to a limit.This method uses deep convolutional neural networks and also custom layer-wise weight constraints that are set to the whole weight matrix directly to learn features efficiently.In this research,a detailed analysis of these weight norms is performed on two distinct datasets,International Skin Imaging Collaboration(ISIC)of 2018 and 2019,which are challenging for convolutional networks to handle.According to thefindings of this work,CLCM-net did a better job of raising the model’s performance by learning the features efficiently within the size limit of weights with appropriate weight constraint settings.The results proved that the proposed techniques achieved 94.42%accuracy on ISIC 2018,91.73%accuracy on ISIC 2019 datasets and 93%of accuracy on combined dataset.
基金the Open Foundation Project of Jiangsu Key Laboratory of Precision and Micro-manufacturing Technology Open Fund Project.
文摘Existing curve fitting algorithms of NC machining path mainly focus on the control of fitting error,but ignore the problem that the original discrete cutter position points are not enough in the high curvature area of the tool path.It may cause a sudden change in the drive force of the feed axis,resulting in a large fluctuation in the feed speed.This paper proposes a new non-uniform rational B-spline(NURBS)curve fitting optimization method based on curvature smoothing preset point constraints.First,the short line segments generated by the CAM software are optimally divided into different segment regions,and then the curvature of the short line segments in each region is adjusted to make it smoother.Secondly,a set of characteristic points reflecting the change of the curvature of the fitted curve is constructed as the control apex of the fitted curve,and the curve is fitted using the NURBS curve fitting optimization method based on the curvature smoothing preset point constraint.Finally,the curve fitting error and curve volatility are analyzed with an example,which verifies that the method can significantly improve the curvature smoothness of the high-curvature tool path,reduce the fitting error,and improve the feed speed.
基金Foundation items: the National Natural Science Foundation of China (40075005) the National Key Basic Research Development Project Program of China (G1998040909)
文摘The aim is to put forward the optimal selecting of weights in variational problemin which the linear advection equation is used as constraint. The selection of the functionalweight coefficients ( FWC) is one of the key problems for the relevant research. It wasarbitrary and subjective to some extent presently. To overcome this difficulty, thereasonable assumptions were given for the observation field and analyzed field, variationalproblems with " weak constraints" and " strong constraints" were considered separately. Bysolving Euler' s equation with the matrix theory and the finite difference method of partialdifferential equation, the objective weight coefficients were obtained in the minimumvariance of the difference between the analyzed field and ideal field. Deduction results showthat theoretically the optimal selection indeed exists in the weighting factors of the costfunction in the means of the minimal variance between the analysis and ideal field in terms ofthe matrix theory and partial differential ( corresponding difference ) equation, if thereasonable assumption from the actual problem is valid and the differnece equation is stable.It may realize the coordination among the weight factors, numerical models and theobservational data. With its theoretical basis as well as its prospects of applications, thisobjective selecting method is probably a way towards the finding of the optimal weightingfactors in the variational problem.
文摘In this work, a new method is presented for determining the binding constraints of a general linear maximization problem. The new method uses only objective function values at points which are determined by simple vector operations, so the computational cost is inferior to the corresponding cost of matrix manipulation and/or inversion. This method uses a recently proposed notion for addressing such problems: the average of each constraint. The identification of binding constraints decreases the complexity and the dimension of the problem resulting to a significant decrease of the computational cost comparing to Simplex-like methods. The new method is highly useful when dealing with very large linear programming (LP) problems, where only a relatively small percentage of constraints are binding at the optimal solution, as in many transportation, management and economic problems, since it reduces the size of the problem. The method has been implemented and tested in a large number of LP problems. In LP problems without superfluous constraints, the algorithm was 100% successful in identifying binding constraints, while in a set of large scale LP tested problems that included superfluous constraints, the power of the algorithm considered as statistical tool of binding constraints identification, was up to 90.4%.