Adaptive Dynamic Programming(ADP) with critic-actor architecture is a useful way to achieve online learning *** algorithm Gaussian-Kernel Adaptive Dynamic Programming(GK-ADP) that has been developed before has a k...
详细信息
ISBN:
(纸本)9781538629185
Adaptive Dynamic Programming(ADP) with critic-actor architecture is a useful way to achieve online learning *** algorithm Gaussian-Kernel Adaptive Dynamic Programming(GK-ADP) that has been developed before has a kind of two-phase iteration,which not only approximates value function,but also optimizes hyper-parameters ***,just like most iteration algorithms are applied in practice,the scale of sample set will increase as the complexity of the system increases,and it will induce a high computation *** order to speed up computation,a practical acceleration method using parallel computation for GK-ADP is presented in this *** realize parallel computation,a high efficient configuration based on CUDA is designed,in which a group of GPUs work in parallel to compute the most complex part of *** comparison test illustrates that the computation burden which hinders GK-ADP’s application is reduced to a large extent when the parallel computing is introduced.
To diagnose the specific reasons that lead to deterioration of controller performance and improve the diagnostic accuracy,a performance diagnosis method based on eigenvector subspace K-mean clustering is ***,the numbe...
详细信息
ISBN:
(纸本)9781538629185
To diagnose the specific reasons that lead to deterioration of controller performance and improve the diagnostic accuracy,a performance diagnosis method based on eigenvector subspace K-mean clustering is ***,the number of standard deterioration performance subspace with different degrees of deterioration information is increased on the basis of the eigenvector subspace distance diagnosis method,in which multiple distance values between eigenvector subspaces are ***,K-mean clustering is used to divide these distance values into two classes,and the clustering center with a maximum number of points is selected as the representative ***,current performance degradation factor is attributed to the category that represented by the nearest standard performance *** simulation,a double-tank model is established,and simulation result shows that average accuracy of controller performance diagnosis reaches 99.4%approximately.
Accurate short-term wind power prediction can improve the trade and the dispatch level of wind *** predict the short-term wind power,we investigated the empirical mode decomposition(EMD) of numerical weather predict...
详细信息
ISBN:
(纸本)9781538629185
Accurate short-term wind power prediction can improve the trade and the dispatch level of wind *** predict the short-term wind power,we investigated the empirical mode decomposition(EMD) of numerical weather prediction(NWP) and genetic algorithm(GA) optimization of support vector regression(SVR).First,the wind speed data from NWP is decomposed into the EMD components,including multiple intrinsic mode functions(IMFs) and one ***,a genetic algorithmsupport vector regression model(GA-SVR) is used to build models of all ***,the prediction results of all components are integrated,which as input of wind-power curve for obtain the predicted value of wind *** order to validate the proposed method,one real-world dataset was used for model training and testing,and the results show that the proposed method is more accurate and effective than SVR and back propagation neural networks(BPNN).
Different from other salient object detection(SOD) for the task of extracting salient obj ects in a image,collaborative saliency object detection(Co-SOD) targets a set of related image groups,and uses algorithms to fi...
详细信息
ISBN:
(数字)9789887581536
ISBN:
(纸本)9781665482561
Different from other salient object detection(SOD) for the task of extracting salient obj ects in a image,collaborative saliency object detection(Co-SOD) targets a set of related image groups,and uses algorithms to find and locate the common collaborative salient objects in related image *** current SOD has achieved remarkable results,but most of the previous researches focus on how to obtain the consistency between images,while the contextual semantic information of images and the features of salient objects are less *** solve these problems,we propose a novel network to capture long-range dependencies on images and enhance(LRDE) the representation of salient ***,In LRDE,we capture the longrange dependencies by the Non-local module to obtain contextual semantic ***,in order to highlight the features of salient objects and enhance the representation of salient objects,we propose the Coordinate Attention module,which embeds the location-attention channel attention and encodes the feature maps as orientation-aware and position-aware attention maps,and It is applied complementary to the input feature map,thereby enhancing the representation of salient *** show that the method outperforms twelve improved methods on four publicly available datasets.
The problem of generating optimal paths for curvature-constrained unmanned aerial vehicles (UAVs) performing surveillance of multiple ground targets is addressed in this paper. UAVs are modeled as Dubins vehicles so...
详细信息
The problem of generating optimal paths for curvature-constrained unmanned aerial vehicles (UAVs) performing surveillance of multiple ground targets is addressed in this paper. UAVs are modeled as Dubins vehicles so that the constraints of UAVs' minimal turning radius can be taken into account. In view of the effective surveillance range of the sensors equipped on UAVs, the problem is formulated as a Dubins traveling salesman problem with neighborhood (DTSPN). Considering its prohibitively high computational complexity, the Dubins paths in the sense of terminal heading relaxation are introduced to simplify the calculation of the Dubins distance, and a boundary-based encoding scheme is proposed to determine the visiting point of every target neighborhood. Then, an evolutionary algorithm is used to derive the optimal Dubins tour. To further enhance the quality of the solutions, a local search strategy based on approximate gradient is employed to improve the visiting points of target neighborhoods. Finally, by a minor modification to the individual encoding, the algorithm is easily extended to deal with other two more sophisticated DTSPN variants (multi-UAV scenario and multiple groups of targets scenario). The performance of the algorithm is demonstrated through comparative experiments with other two state-of-the-art DTSPN algorithms identified in literature. Numerical simulations exhibit that the algorithm proposed in this paper can find high-quality solutions to the DTSPN with lower computational cost and produce significantly improved performance over the other algorithms.
Feature selection is a crucial step in the development of a system for identifying emotions in *** to select high correlation features is an open *** paper focuses on feature selection method which aims to extract the...
详细信息
ISBN:
(纸本)9781538629185
Feature selection is a crucial step in the development of a system for identifying emotions in *** to select high correlation features is an open *** paper focuses on feature selection method which aims to extract the most effective acoustic features to improve the performance of emotion *** feature selection of speakerindependent speech based on Random Forest is proposed,which can remove the redundant features that have high correlations with each *** on the speech emotion recognition based on Support Vector Machines(SVM) is performed,where the speaker-independent features selected by the proposal and Spearman correlation analysis are used for emotion recognition,*** results show that the proposal achieves 78.6%recognition rate on average,which is 2.2%higher than using Spearman.
According to the hierarchical control system of sintering production process,a multi-layer performance assessment method is *** discuss the structure,function and technology used of multi-layer performance assessment ...
详细信息
ISBN:
(纸本)9781538629185
According to the hierarchical control system of sintering production process,a multi-layer performance assessment method is *** discuss the structure,function and technology used of multi-layer performance assessment strategy which is composed of sintering comprehensive coke ratio(CCR) assessment module,sintering ignition assessment module and fuzzy synthetic decision-making *** multi-layer performance assessment for sintering production process control system is realized based on sintering CCR prediction model,performance assessment method for sintering ignition control,and fuzzy synthetic evaluation *** proposed multi-layer performance assessment method is implemented on the simulation platform of the sintering production process in the laboratory,which effectively realized the performance assessment for sintering production process plant level control system,and then provides effective information for the staff to maintain the control system.
This paper presents a hybrid diagnosis and tuning method of coaxial cavity filter based on experience and *** method is based on the experience of skilled staff at the initial stage of tuning,and put the bandpass and ...
详细信息
ISBN:
(纸本)9781538629185
This paper presents a hybrid diagnosis and tuning method of coaxial cavity filter based on experience and *** method is based on the experience of skilled staff at the initial stage of tuning,and put the bandpass and echo curve of the filter to the frequency *** the second stages of the tuning,the phase shift is removed,which is caused by the transmission line and the higher order mode at first,then the loss factor of the filter is ***,we use the improved Cauchy method and filter synthesis knowledge to realize the coupling matrix ***,the implicit space mapping algorithm is used to establish the mapping relationship between the coupling matrix variation and the screw variation,in order to guide the tuning amplitude and direction by the coupling *** show that this method has better effects on saving tuning time and reducing tuning difficulties,and it has certain popularization value for the batch production of the filter.
This paper investigates synchronization problem of two identical chaotic Lur'e systems with time delay using sampleddata control. Firstly, a novel piecewise Lyapunov-Krasovskii function(LKF), which considers fully...
详细信息
ISBN:
(纸本)9781538629185
This paper investigates synchronization problem of two identical chaotic Lur'e systems with time delay using sampleddata control. Firstly, a novel piecewise Lyapunov-Krasovskii function(LKF), which considers fully useful information of the systems and their cross terms, is introduced. Secondly, a new synchronization criterion is developed in terms of linear matrix inequalities(LMIs) by discarding the positive definite constraint of the piecewise LKF. Then, maximal sampling interval and corresponding controller are obtained. At last, case study based on a typical Chua's circuit is carried out to verify the effectiveness and advantages of the proposed method.
This paper is concerned with the stabilization problem for T-S fuzzy system with interval time-varying delay. By constructing a novel augmented LKF and using a developed reciprocally convex matrix inequality proposed ...
详细信息
ISBN:
(纸本)9781538629185
This paper is concerned with the stabilization problem for T-S fuzzy system with interval time-varying delay. By constructing a novel augmented LKF and using a developed reciprocally convex matrix inequality proposed in this paper to bound the derivative of the LKF, a delay-dependent stabilization condition based on parallel distributed compensation scheme is worked out for the closed-loop fuzzy system. Two numerical examples and an application to control of a truck-trailer are given to illustrate the effectiveness of our method.
暂无评论