基于神经网络补偿的坦克全电双向稳定系统非线性滑模控制

doi:10.12382/bgxb.2024.0421

摘要/Abstract

摘要：

传统坦克双向稳定系统的控制策略难以有效处理新一代全电双向稳定系统中的耦合性、非线性和不确定性,而基于模型的非线性控制能够充分利用系统动态模型的先验信息提升控制效果。因此,建立计及执行器动态的全电双向稳定系统机电耦合动力学模型,提出一种基于神经网络补偿的非线性滑模控制方法。引入滑模面和基于双曲正切函数改进的滑模鲁棒控制律设计非线性滑模控制函数,以有效地消除系统振荡,提高系统的稳态性能。同时,深度融合多层神经网络,准确估计系统的不确定性并进行前馈补偿,避免高增益反馈。基于Lyapunov理论严格证明了新控制策略可以实现连续控制输入下坦克全电双向稳定系统的渐近稳定性能。搭建了联合仿真环境与半实物实验平台,通过大量对比实验验证了新控制策略的优越性。

关键词: 坦克, 全电双向稳定系统, 滑模控制, 神经网络, 动力学建模, 对比实验验证

Abstract:

The control strategy of traditional tank bidirectional stabilizers is difficult to effectively deal with the coupling,nonlinearity and uncertainty in the new generation of all-electric bidirectional stabilizers,while the model-based nonlinear control can make full use of a priori information from the dynamic model of the system to enhance the control effect.Based on this,an electromechanical coupled dynamics model of an all-electric bidirectional stabilizer taking the actuator dynamics into account is established,and a nonlinear sliding mode control method based on neural network compensation is proposed.The sliding mode surface and the improved sliding mode robust control law based on hyperbolic tangent function are introduced to construct the nonlinear sliding mode control function,which can effectively eliminate the system oscillations and improve the system stability.Meanwhile,the multilayer neural network technique is deeply fused to accurately estimate the uncertainty in the system and make compensation for the feedforward,thereby avoiding high-gain feedback.It is rigorously demonstrated by the stability theory based on Lyapunov functions that the proposed control strategy can achieve the asymptotic stability performance of tank all-electric bidirectional stabilizer with continuous control inputs.A co-simulation environment and a semi-physical experimental platform are built.The superiority of the proposed control strategy is verified through a large number of comparative experiments.

Key words: tank, all-electric bidirectional stabilizer, sliding mode control, neural network, dynamics modeling, comparative experimental validation

中图分类号:

TJ810

王一珉, 袁树森, 林大睿, 杨国来. 基于神经网络补偿的坦克全电双向稳定系统非线性滑模控制[J]. 兵工学报, 2025, 46(3): 240421-.

WANG Yimin, YUAN Shusen, LIN Darui, YANG Guolai. Nonlinear Sliding Mode Control Based on Neural Network Compensation for Tank All-electric Bidirectional Stabilizers[J]. Acta Armamentarii, 2025, 46(3): 240421-.

图/表 23

图1 坦克全电双向稳定系统

Fig.1 Tank all-electric bidirectional stabilizer

图2 垂直向运动几何关系

Fig.2 Geometry of vertical motion

图3 FOC控制原理

Fig.3 Principle of FOC control

图4 本文前馈神经网络结构

Fig.4 Structure of the feedforward neural network

图5 函数y=tanh(x/ξ)与y=sgn(x)对比

Fig.5 Comparison of functions y=tanh(x/ξ) and y=sgn(x)

图6 控制系统原理

Fig.6 Schematic diagram of control system

图7 坦克拓扑关系

Fig.7 Topological relation of tank

图8 坦克的多体动力学模型

Fig.8 Multibody dynamics model of the tank

图9 E级路面的三维路面谱

Fig.9 3D spectrum of E-level pavement

图10 软件交互实现原理

Fig.10 The principle of software interaction

表1 联合仿真环境中的主要物理参数

Table 1 Major physical parameters for co-simulation

参数	数值
水平向旋转体旋转半径h₁/m	0.20
垂直向旋转体旋转半径h₂/m	0.12
水平向旋转体总质量m₁/kg	5200.0
垂直向旋转体总质量m₂/kg	2088.0
电动缸上支点至耳轴中心距离d₁/m	0.44
电动缸下支点至耳轴中心距离d₂/m	0.30
零度射角下电动缸长度d/m	0.40
零度射角下电动缸安装角度α₀/rad	1.07
炮塔电机力矩系数k₁/(N·m·A^-1)	1.89
电动缸电机力矩系数k₂/(N·m·A^-1)	1.54
水平向传动系数N₁	400
垂直向传动系数N₂	5
垂直向传动效率η	0.98
重力加速度g/(m·s^-2)	9.80
路面参考空间频率n₀/m^-1	0.1
路面频率指数w	2

图11 联合仿真中炮口水平向角位移对比

Fig.11 Comparison of horizontal angular displacements of muzzle in co-simulation

图12 联合仿真中炮口垂直向角位移对比

Fig.12 Comparison of vertical angular displacements of muzzle in co-simulation

图13 联合仿真中炮口水平向角位移跟踪误差对比

Fig.13 Comparison of horizontal angular displacement errors of muzzle in co-simulation

图14 联合仿真中炮口垂直向角位移跟踪误差对比

Fig.14 Comparison of vertical angular displacement errors of muzzle in co-simulation

图15 联合仿真中炮塔电机控制电流对比

Fig.15 Comparison of turret motor control currents in co-simulation

图16 联合仿真中电动缸电机控制电流对比

Fig.16 Comparison of electric cylinder motor control currents in co-simulation

图17 坦克火炮垂直向稳定系统半实物平台

Fig.17 Semi-physical platform of tank gun vertical stabilizer

表2 实验中的主要物理参数

Table 2 Major physical parameters for experiment

参数	数值
垂直向旋转体旋转半径h₂/m	0.06
垂直向旋转体总质量m₂/kg	71.01
电动缸上支点至耳轴中心距离d₁/m	0.194
电动缸下支点至耳轴中心距离d₂/m	0.170
零度射角下电动缸长度d/m	0.094
零度射角下电动缸安装角度α₀/rad	0.51
垂直向传动系数N₂	36
垂直向传动效率η	0.98
电动缸电机力矩系数k₂/(N·m·A^-1)	0.195
重力加速度g/(m·s^-2)	9.80

图18 跟踪实验结果

Fig.18 Tracking experimental result

图19 抗干扰实验结果

Fig.19 Anti-interference experimental results

表3 D级路面下稳定精度

Table 3 Stabilization accuracy on D-level road

控制器及降低百分比	车速/(km·h^-1)
控制器及降低百分比	25	30	35
PID控制器/mrad	1.919	2.844	2.511
SMCNN控制器/mrad	0.942	1.296	1.618
降低百分比/%	50.91	54.43	35.56

表4 E级路面下稳定精度

Table 4 Stabilization accuracy on E-level road

控制器及降低百分比	车速/(km·h^-1)
控制器及降低百分比	25	30	35
PID控制器/mrad	2.403	2.344	3.282
SMCNN控制器/mrad	1.429	1.465	2.232
降低百分比/ %	40.53	37.50	31.99

参考文献 22

[1]	SUN Q Q, YANG G L, WANG X Y, et al. Regulating constraint-following bound for fuzzy mechanical systems:indirect robust control and fuzzy optimal design[J]. IEEE Transactions on Cybernetics, 2020, 52(7):5868-5881.
[2]	MA Y Z, YANG G L, SUN Q Q, et al. Adaptive robust feedback control of moving target tracking for all-electrical tank with uncertainty[J]. Defence Technology, 2022, 18(4):626-642.
[3]	李长兵, 袁东, 马晓军, 等. 高速机动条件下坦克火炮系统扰动力矩谱研究[J]. 兵工学报, 2015, 36(4):582-589. doi: 10.3969/j.issn.1000-1093.2015.04.002
	LI C B, YUAN D, MA X J, et al. Research on disturbance moment spectrum of tank gun system under high maneuvering conditions[J]. Acta Armamentarii, 2015, 36(4):582-589. (in Chinese)
[4]	YUAN S S, DENG W X, YAO J Y, et al. Nonlinear robust adaptive control for bidirectional stabilization system of all-electric tank with unknown actuator backlash compensation and disturbance estimation[J]. Defence Technology, 2024, 32:144-158.
[5]	陈宇. 坦克行进间发射动力学分析及优化研究[D]. 南京: 南京理工大学, 2019.
	CHEN Y. Dynamic analysis and optimization of tank firing on the move[D]. Nanjing: Nanjing University of Science & Technology, 2019. (in Chinese)
[6]	陈宇, 杨国来, 付羽翀, 等. 高速机动条件下坦克行进间火炮非线性振动动力学研究[J]. 兵工学报, 2019, 40(7):1339-1348. doi: 10.3969/j.issn.1000-1093.2019.07.002
	CHEN Y, YANG G L, FU Y C, et al. Dynamic simulation on nonlinear vibration of marching tank gun under high mobility conditions[J]. Acta Armamentarii, 2019, 40(7):1339-1348. (in Chinese) doi: 10.3969/j.issn.1000-1093.2019.07.002
[7]	CAI J P, QIAN F, YU R, et al. Adaptive control for a pneumatic muscle joint system with saturation input[J]. IEEE Access, 2020, 8:117698-117705.
[8]	王宗范, 杨国来. 计及不等式约束的坦克炮稳定系统约束跟随控制[J]. 南京理工大学学报, 2023, 47(4):461-467.
	WANG Z F, YANG G L. Constraint following control for tank gun stabilization systems with inequality constraints[J]. Journal of Nanjing University of Science and Technology, 2023, 47(4):461-467. (in Chinese)
[9]	吕从鑫, 汪波, 陈静波, 等. 永磁同步电机控制策略综述与展望[J]. 电气传动自动化, 2022, 44(4):1-10.
	LÜ C X, WANG B, CHEN J B, et al. Review and prospect of control strategies for permanent magnet synchronous motors[J]. Electric Drive Automation, 2022, 44(4):1-10. (in Chinese)
[10]	马晓军, 袁东, 臧克茂, 等. 数字全电式坦克炮控系统研究现状与发展[J]. 兵工学报, 2012, 33(1):69-76.
	MA X J, YUAN D, ZANG K M, et al. Research on situation and development of digital all-electrical gun control system of tank[J]. Acta Armamentarii, 2012, 33(1):69-76. (in Chinese)
[11]	孙国轩, 宫新宇, 时岩, 等. 基于差分进化算法的自行高炮随动系统PID参数整定[J]. 兵工学报, 2021, 42(5):903-912. doi: 10.3969/j.issn.1000-1093.2021.05.002
	SUN G X, GONG X Y, SHI Y, et al. PID parameter tuning of self-propelled antiaircraft gun servo system based on differential evolution algorithm[J]. Acta Armamentarii, 2021, 42(5):903-912. (in Chinese) doi: 10.3969/j.issn.1000-1093.2021.05.002
[12]	LIN D R, WANG X Y, WANG Y M, et al. Adaptive robust servo control for vertical electric stabilization system of tank and experimental validation[J]. Defence Technology, 2024, 31:326-342. (in Chinese)
[13]	邱晓波, 窦丽华, 韩京清, 等. 自抗扰控制在坦克机动目标状态估计中的应用[J]. 兵工学报, 2009, 30(7):989-993.
	QIU X B, DOU L H, HAN J Q, et al. The application of active disturbance rejection controller to estimating maneuvering target states for tank[J]. Acta armamentarii, 2009, 30(7):989-993. (in Chinese)
[14]	LI C, WANG X Y, MA Y Z, et al. The prediction of projectile-target intersection for moving tank based on adaptive robust constraint-following control and interval uncertainty analysis[J]. Defence Technology, 2024, 31:351-363.
[15]	代普, 潘军, 马晴, 等. 火炮俯仰电液伺服系统速度非线性抑制技术研究[J]. 兵工学报, 2022, 43(6):1246-1254. doi: 10.12382/bgxb.2021.0357
	DAI P, PAN J, MA Q, et al. Research on velocity nonlinear suppression technology of gun pitching electro-hydraulic servo system[J]. Acta Armamentarii, 2022, 43(6):1246-1254. (in Chinese) doi: 10.12382/bgxb.2021.0357
[16]	MA X, DENG W X, YUAN S S, et al. Neural network based adaptive rise control of tank gun systems[C]// Proceedings of 2020 International Conference on Defence Technology. Nanjing: IOP Publishing, 2020, 1507(5):052001.
[17]	高强, 侯润民, 杨国来, 等. 基于分数阶神经滑模的某顶置火炮调炮控制[J]. 兵工学报, 2013, 34(10):1311-1317. doi: 10. 3969/ j. issn. 1000-1093. 2013. 10. 018
	GAO Q, HOU R M, YANG G L, et al. Adjustment and control of a certain yop-mounted gun based on a novel fractional order neural sliding mode strategy[J]. Acta Armamentarii, 2013, 34(10):1311-1317. (in Chinese)
[18]	曾子健, 杨国来, 龙义强, 等. 基于自适应鲁棒控制的坦克俯仰系统建模与仿真[J]. 弹道学报, 2022, 34(2):41-46. doi: 10.12115/j.issn.1004-499X(2022)02-006
	ZENG Z J, YANG G L, LONG Y Q, et al. Modeling and simulation of tank pitching system based on adaptive robust control[J]. Journal of Ballistics, 2022, 34(2):41-46. (in Chinese) doi: 10.12115/j.issn.1004-499X(2022)02-006
[19]	谢润. 车载武器行进间发射动力学研究[D]. 南京: 南京理工大学, 2015.
	XIE R. Study on launch dynamics for vehicle-mounted weapon on traveling[D]. Nanjing: Nanjing University of Science & Technology, 2015. (in Chinese)
[20]	王经纬, 侯远龙, 高强, 等. 炮控系统电动负载模拟器神经网络滑模控制[J]. 兵工自动化, 2019, 38(4):62-65.
	WANG J W, HOU Y L, GAO Q, et al. Neural network sliding mode control for electric load simulator of gun control system[J]. Ordnance Industry Automation, 2019, 38(4):62-65. (in Chinese)
[21]	潘公宇. 汽车振动学基础及其应用[M]. 北京: 北京大学出版社, 2013:105-108.
	PAN G Y. Fundamentals of automotive vibration and its applications[M]. Beijing: Peking University Press, 2013:105-108. (in Chinese)
[22]	袁树森, 邓文翔, 姚建勇, 等. 全电坦克双向稳定系统自适应积分鲁棒控制[J]. 兵工学报, 2023, 44(1):140-155. doi: 10.12382/bgxb.2022.0107
	YUAN S S, DENG W X, YAO J Y, et al. Adaptive Integral robust control for the bidirectional stability system of all-electric tanks[J]. Acta Armamentarii, 2023, 44(1):140-155. (in Chinese) doi: 10.12382/bgxb.2022.0107