Neural Network-Based Error-Tracking Iterative Learning Control for Tank Gun Control Systems With Arbitrary Initial States

Yang, Qing; Yan, Qingdong; Cai, Jianping; Tian, Jinghua; Guan, Xiaohui

doi:10.1109/access.2020.2987976

Cited by 20 publications

(12 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is expected to solve this problem with a lower cost of design and implementation complexity, in exchange for a significant improvement in the control performance. From this point of view, it may be a feasible way to design an iterative learning controller (ILC) [7]- [10] with a simple structure to adjust the given value of the MIT controller by using the idea of indirect iterative learning control (indirect ILC). The work in this paper shows that this method can not only keep the independence of MIT controller design and system stability, but also improve the dynamic performance of the system obviously.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Improved Indirect Iterative Learning MIT Control Method for Ultrasonic Motor

2021

View full text Add to dashboard Cite

MIT control strategy is a kind of model reference adaptive control method with the simplest structure. The reason why the structure is simple is that only the gain of the controlled object is adaptively adjusted. Because only the gain is adjusted, the ability of MIT control strategy to change the characteristics of the controlled object is limited. This also limits its application. In this paper, the simple idea of iterative learning control is introduced into MIT controller to increase the controller's ability to adjust the characteristics of the controlled object, and make it suitable for complex control objects. In the proposed control method, the output of the iterative learning controller is used to adjust the adaptive law of the MIT controller. The proposed control method is applied to the speed control system of ultrasonic motor. Experiments show that although only the gain of MIT controller can be adjusted, the learning process based on memory increases the degree of control freedom. Therefore, the dynamic characteristics of the system can be greatly changed, and the control performance can be significantly improved. Moreover, the proposed method only needs to add a simple P-type iterative learning controller to the MIT controller, and the increase of online calculation amount is small. INDEX TERMS Ultrasonic motor, iterative learning control (ILC), MIT control.

show abstract

Section: Introductionmentioning

confidence: 99%

“…In [9], a time-varying control method based on norm optimal crosscoupling iterative learning is proposed to improve the control precision of multi-axis motion control system. And a neural network-based error-track iterative learning control scheme is proposed in [10] to tackle trajectory tracking problem for tank gun control systems.…”

Section: Introductionmentioning

confidence: 99%

Improved Indirect Iterative Learning MIT Control Method for Ultrasonic Motor

2021

View full text Add to dashboard Cite

show abstract

“…However, the algorithm still requires that the initial state error be bounded and cannot satisfy the case of a random initial state. In recent years, in order to further relax the restrictions on the initial positioning conditions, some scholars have allowed the initial state of each iteration to be a random value [17,[31][32], which is the fourth kind of hypothesis. This kind of assumption can obtain zeroerror complete tracking in a specified interval.…”

Section: Introductionmentioning

confidence: 99%

Consensus Tracking via Iterative Learning for Multi-Agent Systems With Random Initial States

2020

View full text Add to dashboard Cite

In this paper, a distributed consensus iterative learning control algorithm is proposed for the finite-time consensus tracking of multi-agent systems with random initial states. The tracking errors from the agent itself and its neighbours are applied to successively rectify the control protocol when only some agents can obtain the desired trajectory information. Additionally, a time interval is designed in the control protocol, and the random initial state errors are rectified, one-by-one, in the time interval. The interval can gradually shorten as the number of iterations increases. Furthermore, the convergence of the algorithm is theoretically proven by the contraction mapping method, and the convergence condition is derived. The proposed algorithm can cause the time interval to gradually shorten with the iterations increase, during the time, the desired trajectory cannot be consistently tracked due to the random initial state errors. As a consequence, the algorithm gradually widens the time interval for full consensus tracking of the multi agents. Finally, the simulation examples are provided to verify the effectiveness of the algorithm.

show abstract

“…In the past several decades, some works have been done to heighten the control precision and robust stability for tank gun control systems, such as PID control schemes [32], variable structure control schemes [33], optimal control schemes [34], adaptive control schemes [35], [36] and active disturbance rejection control schemes [37]. For getting better control performance, some researchers have explored the iterative learning control algorithms for tank gun control systems [38]- [40]. In [38], Zhu et al considered the velocity tracking problem of tank gun control systems, with an iterative learning control scheme proposed for tank gun control systems under alignment condition.…”

Section: Introductionmentioning

confidence: 99%

“…In [39], Zhang et al investigated the adaptive iterative learning velocity control algorithm for tank gun control systems with input deadzone. In [40], Yang et al proposed an iterative learning velocity control algorithm for tank gun control systems with arbitrary initial states. So far, to the best of authors' knowledge, few results have discussed the position tracking problem for tank gun control systems with periodic reference signals.…”

Section: Introductionmentioning

confidence: 99%

The Tracking Problem in Tank Gun Control Systems With Periodic Reference Signals

et al. 2020

Self Cite

View full text Add to dashboard Cite

In this paper, the position tracking control for tank gun control systems with periodic reference signal is studied. On the basis of corresponding system modeling, a novel repetitive controller is developed by using Lyapunov synthesis. During the controller design, signal replacement mechanism is used to deal with the nonparametric uncertainties under Lipschitz-like continuous condition, and repetitive learning laws are developed to estimate the unknown periodic parameters. Meanwhile, robust learning approach is used to compensate the sum of random disturbances, whose upper bound is estimated according repetitive learning mechanism. Hyperbolic tangent function, rather than sign function, is applied to design a robust feedback term to release the occurrence of chattering phenomenon. Numerical simulations demonstrate the effectiveness of the proposed repetitive control scheme. INDEX TERMSTank gun control systems, repetitive control, Lyapunov approach, Lipschitz-like continuous condition. JINGHUA TIAN received the B.S. degree in computer science and technology from the Huazhong University of Science and Technology, in 2002, and the M.S. degree in communication and information system from the Zhejiang University of Technology. She was with the Zhejiang University of Water Resources and Electric Power, Hangzhou, in 2004, where she was an Assistant with the Information Engineering and Art Design Department. Since 2004, she has been working as a Lecturer with the Zhejiang University of Water Resources and Electric Power. Her current research interests include automatic control, industrial automation, computer networking technology, and communication technology.

show abstract

Neural Network-Based Error-Tracking Iterative Learning Control for Tank Gun Control Systems With Arbitrary Initial States

Cited by 20 publications

References 26 publications

Improved Indirect Iterative Learning MIT Control Method for Ultrasonic Motor

Improved Indirect Iterative Learning MIT Control Method for Ultrasonic Motor

Consensus Tracking via Iterative Learning for Multi-Agent Systems With Random Initial States

The Tracking Problem in Tank Gun Control Systems With Periodic Reference Signals

Contact Info

Product

Resources

About