This paper proposes a new incremental learning method based on weighted constraints support vector regression, called ***,a modified nearest neighbor clustering method is used to partition the whole input space into s...
详细信息
ISBN:
(纸本)9781479900305
This paper proposes a new incremental learning method based on weighted constraints support vector regression, called ***,a modified nearest neighbor clustering method is used to partition the whole input space into several ***,according to the distance distinguish condition,all the samples in sub-cluster are identified to form the candidate support vector *** each new sample added,it was clustered to an individual candidate support vector subset where the cluster center is the closest to the new ***,in the WCSVR learning process,the object function is modified by introducing a weight for each new sample and the corresponding regularization *** experiment shows prominence of our proposed incremental method in comparison with the standard SVR.
The model of NCS (Networked control Systems) with reduced dimension observer is presented when the network-induced random time-varying delays are bounded and the upper bound of which is longer than one sampling period...
详细信息
This paper has proposed a new group synchronization protocol for nonlinear dynamical complex networks whose information interaction exists among different groups via pinning control *** constructing an effective Lyapu...
详细信息
ISBN:
(纸本)9781479900305
This paper has proposed a new group synchronization protocol for nonlinear dynamical complex networks whose information interaction exists among different groups via pinning control *** constructing an effective Lyapunov function,we have proved that all nodes in each group can converge to its own synchronous state ***,some simulations are presented to illustrate our theoretical results.
According to the difficulties measuring two-phase flow process multi-parameter with single sensor, a gas-water of two-phase flow process parameters (flow rate and phase fraction) multi-sensor measuring system was pres...
详细信息
According to the difficulties measuring two-phase flow process multi-parameter with single sensor, a gas-water of two-phase flow process parameters (flow rate and phase fraction) multi-sensor measuring system was presented, which combines a new long waist cone differential pressure sensor and conductance ring sensor. The computational fluid mechanics and multi-physics field coupling analysis were used to simulate the flow field and electric field of long waist cone conductance ring sensor in horizontal pipe (DN50 mm), which provided the accurate theoretical basis for the later study about coupling simulation of the electric field and fluid field.
This paper investigates the setpoints compensation for a class of complex industrial processes. Plants at the device layer are controlled by the local regulation controllers, and a multirate output feedback control ap...
详细信息
ISBN:
(纸本)9781467357692;9781467357678
This paper investigates the setpoints compensation for a class of complex industrial processes. Plants at the device layer are controlled by the local regulation controllers, and a multirate output feedback control approach for setpoint compensation is proposed such that the subsystems can reach the dynamically changed setpoints and the given economic objective can also be tracked via certain economic performance index (EPI). First, a sampled-data multivariable direct output feedback proportional integral (PI) controller is designed to regulate the performance of the subsystems. Second, the outputs and control inputs of the plants at the device layer are sampled at operation layer sampling time to form an EPI. Thus the multirate problem is solved by a lifting method. Third, static setpoints are generated by real time optimization (RTO) and the dynamic setpoints are calculated by the compensator according to the error between the EPI and objective at each operation layer step. Finally, a rougher flotation process model is employed to demonstrate the effectiveness of the proposed method.
Electrical resistance tomography(ERT) attempts to image the conductivity distribution of an object by measuring the voltage on its boundary. The reconstruction of ERT is an ill-posed inverse problem,and little noise...
详细信息
Electrical resistance tomography(ERT) attempts to image the conductivity distribution of an object by measuring the voltage on its boundary. The reconstruction of ERT is an ill-posed inverse problem,and little noise in the measured data can cause large errors in the estimated *** this paper, an improved TV regularization method for ERT is introduced with iterations updated by the projected Gauss-Newton *** replaces the conventional TV regularization penalty term(?)|▽g|dΩby(?)|▽g|dΩ,in which p is selected as 1.5. The choice of such a penalty compromises both the conventional smoothness and discontinuities of the imaged *** improved approach can reconstruct images with sharp edges as well as reducing the suffering of the staircase effect. Simulation and experimental results of the improved method,TV regularization and Tikhonov regularization are compared,which show that this improved TV regularization can endure a relatively high level of noise in the measured voltages.
Breast cancer seriously endangers the health of women,which makes intra-operative assessment of cancer focus have vital *** information of bioelectrical impedance has unique ability to distinguish cancerous and normal...
详细信息
Breast cancer seriously endangers the health of women,which makes intra-operative assessment of cancer focus have vital *** information of bioelectrical impedance has unique ability to distinguish cancerous and normal tissue,and can provide basis for intra-operative assessment of cancer *** order to achieve accurate measurement,a measurement system is established composed of the impedance analyzer and probe with optimized *** integral area is regarded as characteristic parameter to reflect the over all *** utilize the advantages of different frequency-resistance curves,BP neural network is finally selected and good-training neural networks are integrated to make the final *** result indicates that the characteristic parameter selected can reflect differences of tissues and the integrated BP neural network has better performance than single neural network.
Numerical simulation and experimental tests were undertaken to study the vortex stability of gas-liquid two-phase flow around a bluff body in a horizontal pipe. A 3-D Computational Fluid Dynamics (CFD) modeling is car...
详细信息
ISBN:
(纸本)9781467363846
Numerical simulation and experimental tests were undertaken to study the vortex stability of gas-liquid two-phase flow around a bluff body in a horizontal pipe. A 3-D Computational Fluid Dynamics (CFD) modeling is carried out in order to model the gas-liquid two-phase flow around a bluff body using a volume of fluid (VOF) model. The captured photographs of typical flow patterns are used to compare the CFD predictions and a good qualitative agreement is observed between them. The relationship between the Strouhal number and cross-sectional void fraction is derived from the experimental data. The vortex stability is analyzed in terms of frequency, Strouhal number and the requirement of vortex stability.
Due to the complexity of the multiphase flow process and the limitation of traditional single sensor, the existing measurement methods can not meet the requirement of accurate measurement for industrial processes. In ...
详细信息
Due to the complexity of the multiphase flow process and the limitation of traditional single sensor, the existing measurement methods can not meet the requirement of accurate measurement for industrial processes. In order to solve the problem of accurate and comprehensive information acquisition of the multiphase flow process, a multi-sensor fusion method is proposed for multiphase flow parameter measurement. A conductance-ring sensor and a cone-shape differential pressure sensor are selected as the means of measurement. The cross-correlation velocity measurement technology is combined with the measurement model of differential pressures. Kalman centralized fusion estimation method not only can realize the effective information fusion between heterogeneous sensors, but also can satisfy accurate and real-time requirements of the multiphase flow parameters estimation. The experiment results have verified the feasibility of the method.
暂无评论