智能水下机器人BP神经网络S面控制
|
摘要
针对智能水下机器人传统S面控制器参数设置过程依赖经验且设置不当将严重影响运动控制效果的问题,设计了BP神经网络S面控制器,由神经网络正向传播输出S面控制器参数,并在反向传播中实现参数的在线整定。采用某微小型智能水下机器人模型仿真实验的结果表明,该控制器能够自主完成控制参数初始化与调整,具有收敛速度快、超调与稳态误差小、干扰条件下能够迅速恢复稳定等优点,可以为实际工程中运动控制器设计提供参考。
As a practical motion controller for autonomous underwater vehicle, S plane controller needs to set its control parameters manually relying on experience, of which improper setting will lead to adverse effect on precision and effect. A controller combining BP neural network with S plane control is proposed. In BP neural network S plane controller, the parameters of S plane controller are outputted from the forward propagation of BP neural network, and on-line tuning of parameters is realized in backpropagation. The simulation experiment using a micro autonomous underwater vehicle model shows that the controller can complete the process of initializing and adjusting parameters independently, it has the advantages of fast convergence rate, small overshoot and steady-state error, and the ability to recover stability quickly under disturbance, which provides a reference for the design of motion controller in practical engineering.
As a practical motion controller for autonomous underwater vehicle, S plane controller needs to set its control parameters manually relying on experience, of which improper setting will lead to adverse effect on precision and effect. A controller combining BP neural network with S plane control is proposed. In BP neural network S plane controller, the parameters of S plane controller are outputted from the forward propagation of BP neural network, and on-line tuning of parameters is realized in backpropagation. The simulation experiment using a micro autonomous underwater vehicle model shows that the controller can complete the process of initializing and adjusting parameters independently, it has the advantages of fast convergence rate, small overshoot and steady-state error, and the ability to recover stability quickly under disturbance, which provides a reference for the design of motion controller in practical engineering.
引文
[1] Tanakitkorn K, Wilson P A, Turnock S R, et al. Depth control for an over-actuated,hover-capable autonomous underwater vehicle with experimental verification[J]. Mechatronics, 2017, 41:67-81.
[2] Li Q, Shi X H, Kang Z Q. The Research of Fuzzy-PID Control Based on Grey Predition for AUV[J]. Applied Mechanics & Materials, 2012, 246-247:888-892.
[3] Khodayari M H, Balochian S. Modeling and control of autonomous underwater vehicle(AUV) in heading and depth attitude via self-adaptive fuzzy PID controller[J]. Journal of Marine Science & Technology,2015,20(3): 559-578.
[4] Sun B, Zhu D, Yang S X. An Optimized Fuzzy Control Algorithm for Three-Dimensional AUV Path Planning[J]. International Journal of Fuzzy Systems,2017,20(5):1-14.
[5] Tanakitkorn K, Wilson P A, Turnock S R, et al. Sliding mode heading control of an overactuated, hover-capable autonomous underwater vehicle with experimental verification[J]. Journal of Field Robotics, 2017(1):
[6] Elmokadem T, Zribi M, Youcef-Toumi K. Terminal sliding mode control for the trajectory tracking of underactuated Autonomous Underwater Vehicles[J].Ocean Engineering, 2016,129.
[7] 刘学敏,徐玉如.水下机器人运动的S面控制方法[J].海洋工程,2001,19(3):81-84.
[8] 刘胜,任冬,李冰.基于SA-PSO算法的潜器S面控制[J].控制工程,2011,18(5):710-714.
[9] 孙玉山,李岳明,张英浩,等.改进的模拟退火算法在水下机器人S面运动控制参数优化中的应用[J].兵工学报,2013, 34(11):1418-1423.
[10] Sun X J, Shi J, Yang Y. Neural Networks Based Attitude Decoupling Control for AUV with X-Shaped Fins[J]. Advanced Materials Research, 2013, 819:222-228.
[11] Hu Q Y, Zhou J, Zha Z. Application of PSO-BP Network Algorithm in AUV Depth Control[J]. Applied Mechanics & Materials, 2013, 321-324:2025-2031.
[12] Huang H, Zhu D, Ding F. Dynamic Task Assignment and Path Planning for Multi-AUV System in Variable Ocean Current Environment[M]. Kluwer Academic Publishers, 2014.
[13] Huang Z, Zhu D, Sun B. A multi-AUV cooperative hunting method in 3-D underwater environment with obstacle[J]. Engineering Applications of Artificial Intelligence, 2016, 50(C):192-200.
[14] 崔士鹏.微小型水下机器人运动控制[D].哈尔滨:哈尔滨工程大学,2013.
[2] Li Q, Shi X H, Kang Z Q. The Research of Fuzzy-PID Control Based on Grey Predition for AUV[J]. Applied Mechanics & Materials, 2012, 246-247:888-892.
[3] Khodayari M H, Balochian S. Modeling and control of autonomous underwater vehicle(AUV) in heading and depth attitude via self-adaptive fuzzy PID controller[J]. Journal of Marine Science & Technology,2015,20(3): 559-578.
[4] Sun B, Zhu D, Yang S X. An Optimized Fuzzy Control Algorithm for Three-Dimensional AUV Path Planning[J]. International Journal of Fuzzy Systems,2017,20(5):1-14.
[5] Tanakitkorn K, Wilson P A, Turnock S R, et al. Sliding mode heading control of an overactuated, hover-capable autonomous underwater vehicle with experimental verification[J]. Journal of Field Robotics, 2017(1):
[6] Elmokadem T, Zribi M, Youcef-Toumi K. Terminal sliding mode control for the trajectory tracking of underactuated Autonomous Underwater Vehicles[J].Ocean Engineering, 2016,129.
[7] 刘学敏,徐玉如.水下机器人运动的S面控制方法[J].海洋工程,2001,19(3):81-84.
[8] 刘胜,任冬,李冰.基于SA-PSO算法的潜器S面控制[J].控制工程,2011,18(5):710-714.
[9] 孙玉山,李岳明,张英浩,等.改进的模拟退火算法在水下机器人S面运动控制参数优化中的应用[J].兵工学报,2013, 34(11):1418-1423.
[10] Sun X J, Shi J, Yang Y. Neural Networks Based Attitude Decoupling Control for AUV with X-Shaped Fins[J]. Advanced Materials Research, 2013, 819:222-228.
[11] Hu Q Y, Zhou J, Zha Z. Application of PSO-BP Network Algorithm in AUV Depth Control[J]. Applied Mechanics & Materials, 2013, 321-324:2025-2031.
[12] Huang H, Zhu D, Ding F. Dynamic Task Assignment and Path Planning for Multi-AUV System in Variable Ocean Current Environment[M]. Kluwer Academic Publishers, 2014.
[13] Huang Z, Zhu D, Sun B. A multi-AUV cooperative hunting method in 3-D underwater environment with obstacle[J]. Engineering Applications of Artificial Intelligence, 2016, 50(C):192-200.
[14] 崔士鹏.微小型水下机器人运动控制[D].哈尔滨:哈尔滨工程大学,2013.