Hyperspectral imaging is a promising technique for identifying variety of seeds. But the hyperspectral features of seeds are vulnerable to the influence of years. Present modeling methods mostly depend on the training...
详细信息
ISBN:
(纸本)9781510810501
Hyperspectral imaging is a promising technique for identifying variety of seeds. But the hyperspectral features of seeds are vulnerable to the influence of years. Present modeling methods mostly depend on the training samples in the same year and prediction accuracy of these models will be decreased when these models are used to discriminate the same kind of seeds from the other different years. To improve the stability and robustness of the model, hyperspectral image coupled with model updating strategy based on support vector data description (SVDD) algorithm and Least squares support vector machine (LSSVM) was proposed. SVDD was used to find new samples which were not contained in the original model to update present SVDD model, respectively. Recognition experiments on four kinds of maize seeds under different years showed that the model updating strategy based on SVDD and LSSVM worked well, and the prediction accuracy of model was improved from 84.13% to 93.91% by adding 11.5% to 13.15% of samples under testing from other years to the original training set.
In order to reduce the blast furnace coke rate, pulverized coal is injected through lances into the raceway in front of the tuyeres. Close inspection of the tuyeres is particularly important as critical incidents such...
详细信息
In order to reduce the blast furnace coke rate, pulverized coal is injected through lances into the raceway in front of the tuyeres. Close inspection of the tuyeres is particularly important as critical incidents such as a tuyere blockage or burning of the injection lance can happen at any time. To increase Operation safety, Paul Wurth has developed the Tuyère Phenomena Detection System, a camera-based monitoring system for the tuyère and raceway area. The system allows simultaneous monitoring of all tuyères from a safe distance. At the same time an image recognition system processes the camera images to automatically detect phenomena of the injection lance and the tuyère.
Due to the nonlinearities, model uncertainties and disturbances of the two-tank liquid level cascade system, active disturbance rejection controller (ADRC) solution was developed. First, a nonlinear mechanism model an...
Due to the nonlinearities, model uncertainties and disturbances of the two-tank liquid level cascade system, active disturbance rejection controller (ADRC) solution was developed. First, a nonlinear mechanism model and its linearized model were built based on the theories of fluid dynamics for the system. Second, first-order linear ADRCs for the outer loop of the two cascade systems with an unknown order were designed, respectively. With a simple integrator as the normalized type of the feedback system, other parts of dynamic system which are different from the normalized type are treated as the total disturbances. The disturbances were estimated by the second-order linear extended state observer and compensated in the control law. Then the system, with nonlinearities, uncertainties and disturbances, is reduced to only a linear integrator. In comparison with the traditional PI controller, simulation results show that both the proposed ADRCs have better robustness and adaptability against model uncertainties.
Nowadays, novel construction materials, more efficient power supplies and advanced artificial intelligence algorithms allow one to use unmanned aerial vehicles (UAV) in various fields of life. One of the biggest event...
详细信息
ISBN:
(纸本)9781479987023
Nowadays, novel construction materials, more efficient power supplies and advanced artificial intelligence algorithms allow one to use unmanned aerial vehicles (UAV) in various fields of life. One of the biggest events promoting this idea is the Air Cargo Challenge (ACC) competition. In this paper the motivation for ACC participation and the overall procedure of CAD aided UAV design are presented. The nonlinear aircraft model as well as Computational Fluid Dynamic simulations are discussed. Finally, some details concerning designed UAV prototype are revealed.
This work addresses stability and robustness properties of hybrid limit cycles for a class of hybrid systems, which combine continuous dynamics on a flow set and discrete dynamics on a jump set. Under some mild assump...
详细信息
ISBN:
(纸本)9781479978878
This work addresses stability and robustness properties of hybrid limit cycles for a class of hybrid systems, which combine continuous dynamics on a flow set and discrete dynamics on a jump set. Under some mild assumptions, we show that the stability of hybrid limit cycles for a hybrid system is equivalent to the stability of a fixed point of the associated Poincare map. As a difference to related efforts for systems with impulsive effects, we also explore conditions under which the stability properties of the hybrid limit cycles are robust to small perturbations. The spiking Izhikevich neuron is presented to illustrate the notions and results throughout the paper.
Due to the nonlinearities, model uncertainties and disturbances of the two-tank liquid level cascade system,active disturbance rejection controller(ADRC) solution was developed. First, a nonlinear mechanism model and ...
详细信息
Due to the nonlinearities, model uncertainties and disturbances of the two-tank liquid level cascade system,active disturbance rejection controller(ADRC) solution was developed. First, a nonlinear mechanism model and its linearized model were built based on the theories of fluid dynamics for the system. Second, first-order linear ADRCs for the outer loop of the two cascade systems with an unknown order were designed, respectively. With a simple integrator as the normalized type of the feedback system, other parts of dynamic system which are different from the normalized type are treated as the total disturbances. The disturbances were estimated by the second-order linear extended state observer and compensated in the control law. Then the system, with nonlinearities, uncertainties and disturbances, is reduced to only a linear integrator. In comparison with the traditional PI controller, simulation results show that both the proposed ADRCs have better robustness and adaptability against model uncertainties.
This paper studies consensus control for multi-input/multi-output(MIMO)discrete-time multi-agent systems(MASs).It makes use of the novel idea of resource allocation in designing both the communication graph and feedba...
详细信息
This paper studies consensus control for multi-input/multi-output(MIMO)discrete-time multi-agent systems(MASs).It makes use of the novel idea of resource allocation in designing both the communication graph and feedback *** weakest consensusability condition is obtained for MASs over both directed and undirected graphs,which extends the existing results to MIMO discrete-time *** synthesis procedures are also *** work demonstrates the importance of the graph and controller co-design based on resource allocation for MIMO discrete-time MASs.
Surgical robotic systems have to deliver a high quality of safety, since they deal with human lives. Their safety specifications must ensure the absence of risks for the patient and the operating room staff. To respec...
详细信息
ISBN:
(纸本)9781479947287
Surgical robotic systems have to deliver a high quality of safety, since they deal with human lives. Their safety specifications must ensure the absence of risks for the patient and the operating room staff. To respect the modular nature of a surgical system, we propose a contract based verification approach for safety. We introduce a case study based on a typical surgical robotic operation scenario and model its components by using hybrid automata. We exploit the theory of parallel composition of contracts to verify properties on each component and prove that the property of the overall system can be obtained by composition.
In addition to simplicity, the DTC of the IM allows a good torque control in steady-state and transient operating conditions. However, high torque ripple is produced, which is reflected in speed estimation responses. ...
详细信息
ISBN:
(纸本)9781849198158
In addition to simplicity, the DTC of the IM allows a good torque control in steady-state and transient operating conditions. However, high torque ripple is produced, which is reflected in speed estimation responses. It also increases acoustical noise and makes the voltage source inverter operated in high and variable switching frequency, requiring a high sampling frequency. In this paper, a simple effective ANN-based DTC of the induction machine is proposed. Neural networks with a simple architecture are designed and implemented in influential points of the direct torque control block of the three phase induction machine in order to improve its dynamic performance while preserving the DTC structure simplicity as much as possible. In particular, this paper proposes to reduce, on the one hand, the torque ripple and commutation frequency. Neural comparators are used to select the appropriate bandwidth for the torque and flux hysteresis controllers. Their aim is to optimize the ripple level in the developed torque and flux. On the other hand, a neural speed controller is designed in order to improve the system ability to respond rapidly to changes in process variables and mitigate the effects of external perturbations. The performance of the proposed control are tested in simulation and highlighted by comparing to the conventional DTC control based on conventional hysteresis comparators and conventional PI speed controller. The obtained results show the feasibility and good performances of the proposed control.
A novel on-line diagnosis method is proposed in this paper that uses a qualitative dynamic model of the system and its colored Petri nets model. The model contains both the normal and the possible faulty operational m...
详细信息
ISBN:
(纸本)9789077381861
A novel on-line diagnosis method is proposed in this paper that uses a qualitative dynamic model of the system and its colored Petri nets model. The model contains both the normal and the possible faulty operational modes of the system. The deviation between the normal and faulty modes is characterized based on P-HAZID tables. The actual system state can be searched on the occurrence graph constructed in advance. Starting from this node the possible consequences and root causes can be determined on-line with traversing on the graph. The proposed method is illustrated on simple case studies.
暂无评论