Unit 94270 of PLA
Unit 94270 of PLA
Liu X.,PLA Air Force Aviation University |
Sun X.-X.,PLA Air Force Aviation University |
Liu S.-G.,PLA Air Force Aviation University |
Xu S.,PLA Air Force Aviation University |
Hao Z.,Unit 94270 of PLA
Kongzhi Lilun Yu Yingyong/Control Theory and Applications | Year: 2013
A non-fragile recursive sliding mode dynamic surface adaptive control method is proposed for a class of uncertain, mismatched nonlinear system. By employing the neural network (NN) to approximate the system uncertainty and designing the recursive sliding mode dynamic surface to synthesize the interaction of the tracking error in each step of backstepping scheme, we make the method to get rid of the 'explosion of complexity' associated with the backstepping control and to avoid being fragile to the perturbation in both the filter time constant and adaptive parameters of neural network in the traditional dynamic surface control. Stability analysis verifies the semi-global, uniform, and ultimate boundedness (SUUB) for all the states of the closed-loop system, and guarantees the tracking error to converge to an arbitrarily small neighborhood of the origin.
Yan X.,Wuhan University of Technology |
Li Z.,Wuhan University of Technology |
Zhang Y.,Unit 94270 of PLA |
Yuan C.,Wuhan University of Technology |
Peng Z.,University of New South Wales
Zhongguo Jixie Gongcheng/China Mechanical Engineering | Year: 2013
To ensure the reliable operation of marine diesel engines, a marine diesel engine fault diagnosis system was developed based on the information fusion of multi-dimensional sensors. In the light of the application of the proposed diagnosis system, the key issues on the wear condition monitoring and fault diagnosis for marine diesel engines were discussed from view point of the coupling of tribologic and dynamic information. Lastly, existing problems and future research directions were reported.
Chenxing S.,Wuhan University of Technology |
Yuelei Z.,Unit 94270 of PLA |
Xinping Y.,Wuhan University of Technology |
Jie L.,Wuhan University of Technology
Research Journal of Applied Sciences, Engineering and Technology | Year: 2013
The study aims to investigate the mechanical system optimum design based on collaborative theory. Due to the complexity of the modern machinery, mechanical systems are readily to damage when unexpected failures occur on important components. It is therefore, critical to monitor the machine state for preventing the impending faults. The key issues to realize the feasible and reliable mechanical condition monitoring is information acquisition, which relies on the available design of the detection devices. Literature review indicates that an extensive attention has been put on the so called Monitorability in the systematic design of mechanical systems. Monitorability is emphasized that in the original design of mechanical systems one should consider available information acquisition property. Moreover, monitorability-based design is known as a design attribute of mechanical system worldwide. However, less work has been done in this field. In this study, a novel method based on collaborative theory is proposed for the monitorability design. The connotation and application of collaborative theory for monitorability design are discussed in details. The information synergy model and organization framework of monitorability-based design are established by using computer technology and network technology. The experiments demonstrate the effectiveness of the proposed monitorability design system for a more powerful optimum design of mechanical systems and show a promising future for the industrial applications. © Maxwell Scientific Organization, 2013.
Xu X.,China Three Gorges University |
Wei D.,Nanyang Institute of Technology |
Zhang Y.,Unit 94270 of PLA
Proceedings - PACCS 2011: 2011 3rd Pacific-Asia Conference on Circuits, Communications and System | Year: 2011
The intrusion detection rate is greatly influenced by the parameters of the support vector machine (SVM) model. In order to overcome the parameter limits to improve the identify accuracy of Distributed Denial of Service (DDoS) attack, this paper presents a new detection method based on Kernel Principle Component Analysis (KPCA) and Particle Swarm Optimization (PSO)-Support Vector Machine (SVM). The KPCA was used to obtain the important characteristics of the intrusion data to eliminate the redundant features. Then the PSO was used to optimize the SVM parameters. Experimental results show the proposed approach can enhance the detection rate, and performs better than the PCA based methods. © 2011 IEEE.