Aiming at solving the problem of control performance due to the inaccuracy in the two-eye robot visual servoing system modeling, an RBF neural network based on the adaptive algorithm is proposed, which is used to iden...
详细信息
Aiming at solving the problem of control performance due to the inaccuracy in the two-eye robot visual servoing system modeling, an RBF neural network based on the adaptive algorithm is proposed, which is used to identify the uncertainties of the modeling. A dynamic control law is put forward for compensating the uncertainties of the modeling, an adaptive law is put forward to ensure the boundness of the neural network's weights and a kinematic control law is put forward which takes the errors between the actual position and the target position of the manipulators as input. The stability of the two control laws is demonstrated using the Lyapunov stability theorems, and the stability of the manipulator system which is under the proposed control laws is illustrated. The results, which are obtained from the Matlab simulation, verify the high performance of the control strategy.
Through analyzing of the electric power steering (EPS) structure and union the vehicle dynamic characteristics, this paper establishes a mathematical model of EPS. And the EPS system simulation model based on Matlab/S...
详细信息
With the development of vehicle autonomous driving technology and wireless network communication technology, the mix platoon of connected autonomous vehicles (CAVs) and connected human-driven vehicles (CHVs) is becomi...
详细信息
The hydraulic system's reliability is a key factor to ensure the reliable operation of equipment and it is very important to evaluate reliability of hydraulic system. The paper describes a reliability prediction m...
详细信息
Nowadays, machine learning is widely used in malware detection system as a core component. The machine learning algorithm is designed under the assumption that all datasets follow the same underlying data distribution...
详细信息
Nowadays, machine learning is widely used in malware detection system as a core component. The machine learning algorithm is designed under the assumption that all datasets follow the same underlying data distribution. But the real-world malware data distribution is not stable and changes with time. By exploiting the knowledge of the machine learning algorithm and malware data concept drift problem, we show a novel learning evasive botnet architecture and a stealthy and secure C&C mechanism. Based on the email communication channel, we construct a stealthy email-based P2 P-like botnet that exploit the excellent reputation of email servers and a huge amount of benign email communication in the same channel. The experiment results show horizontal correlation learning algorithm is difficult to separate malicious email traffic from normal email traffic based on the volume features and time-related features with enough confidence. We discuss the malware data concept drift and possible defense strategies.
In order to overcome the difficulty of constructing the multi-state system's reliability optimization model, and the shortage of premature convergence of PSO (Particle Swarm Optimization) algorithm, a new reliabil...
详细信息
This paper investigates the composite design of fixed-time control and fixed-time extended state observer(FTESO) for the underactuated autonomous underwater vehicle system with external disturbance. A FTESO which can ...
详细信息
This paper investigates the composite design of fixed-time control and fixed-time extended state observer(FTESO) for the underactuated autonomous underwater vehicle system with external disturbance. A FTESO which can estimate the disturbance and state in fixed-time unrelated to initial states of the system. Continuous fixed-time convergent control approach conjunction with FTESO are used to make sure that the system states can be convergent in a fixed time at the present of external time-varying disturbance. The horizontal plane of the AUV model is first divided into two cascade connected subsystems by use of input and state transformations, and the proposed result is further extended to the stabilization control for horizontal plane of the AUV, which considers external current disturbance. In the last, simulation results are given to demonstrate the effectiveness of the proposed method.
Base on the the high performance requirements of permanent magnet synchronous motor(PMSM) speed servo system for non-sinusoidal oscillation control system of continuous casting mold, a global dynamic sliding mode(GDSM...
详细信息
Base on the the high performance requirements of permanent magnet synchronous motor(PMSM) speed servo system for non-sinusoidal oscillation control system of continuous casting mold, a global dynamic sliding mode(GDSM) control method is proposed, The reaching law of the sliding mode is designed by exponential fast terminal sliding mode(EFTSM) method and the controllers could effectively diminish chattering by designing the first derivative of control output which contains discontinuous function of sliding mode control; Considers the time variation of parameters perturbation and load disturbance of PMSM, a extended state observer (ESO) is constructed to observe the dynamic observation of total system perturbation and conduct feedforward compensation; theoretical analysis shows that the closed-loop system is global bounded stability; The simulated results show that the static and dynamic performance of the PMSM speed servo control system can be significantly improved by using the proposed method.
Based on Lyapunov stability theorem, a MRAC system was researched to solve that differential value of plant output is unknown. Meanwhile an improved design for MRAC system aimed on the factor of restricting convergenc...
详细信息
Based on Lyapunov stability theorem, a MRAC system was researched to solve that differential value of plant output is unknown. Meanwhile an improved design for MRAC system aimed on the factor of restricting convergence of system is given. The method not only solves the problem that makes the system can not work well as a result of the adjustable parameters, but also improves the convergence of plant. The simulation graphs have shown that the plant can follow the output of the reference model quit well
A new variable tap-length LMS algorithm is proposed in this paper. This algorithm can effectively obtain both fast convergence rate and small steady state error by non-linear weighting L errors of the current moment a...
详细信息
暂无评论