为提升舰船航行安全性，提出神经网络优化PID的舰船关键设备智能控制方法。构建PID控制器，将舰船关键设备灵敏度期望值与实际值之间的误差作为控制器输入，经PID控制器控制后，输出使灵敏度误差达到最小的控制结果，将该结果作用于舰船关键设备，实现智能控制。为提升控制效果，采用RBF神经网络优化PID控制器的比例、积分、微分系数3种参数，将优化后的控制器参数作为PID控制器选取最终参数，完成舰船关键设备的智能控制。经实验验证：该方法控制后的舰船蓄能器与伺服阀具有较高的灵敏度，控制后可使发电机在调速时迅速达到相应速度；避免液压缸出现大幅度位移现象。
In order to improve the safety of ship navigation, an intelligent control method of ship key equipment based on neural network optimized PID is proposed. The PID controller is constructed, and the error between the expected value and the actual value of the sensitivity of the ship's key equipment is taken as the controller input. After being controlled by the PID controller, the control result that minimizes the sensitivity error is output. The result is applied to the ship's key equipment to achieve intelligent control; In order to improve the control effect, the RBF neural network is used to optimize the three parameters of the PID controller, namely, the proportion, integral and differential coefficients. The optimized controller parameters are used as the final parameters of the PID controller to complete the intelligent control of the key equipment of the ship. The experimental results show that the marine accumulator and servo valve controlled by this method have high sensitivity, and the generator can quickly reach the corresponding speed when adjusting the speed; Avoid large displacement of hydraulic cylinder.
2022,44(21): 168-171 收稿日期：2022-08-18
DOI：10.3404/j.issn.1672-7649.2022.21.035
分类号：U664.11
作者简介：常志东(1980-),男,副教授,主要研究方向为云计算技术、大数据、计算机应用及人工智能
参考文献：
[1] 侯远欣, 范久臣. 神经网络PID控制的液压驱动主动升沉补偿预测控制研究[J]. 机床与液压, 2020, 48(16): 145–148+200
HOU Yuanxin, FAN Jiuchen. Research on Hydraulic Drive Active Heaving Compensation Predictive Control Based on Neural Network PID Control[J]. Machine Tool & Hydraulics, 2020, 48(16): 145–148+200
[2] 麦鹏. 基于人工鱼群算法优化的车辆防滑PID神经网络控制研究[J]. 中国工程机械学报, 2020, 18(3): 215–219
MAI Peng. Research on anti-skid PID neural network control of vehicle based on artificial fish swarm algorithms[J]. Chinese Journal of Construction Machinery, 2020, 18(3): 215–219
[3] 郑晓晨. 伺服电机NCS神经网络PID趋近律滑模控制[J]. 火力与指挥控制, 2020, 45(8): 22–29
ZHENG Xiaochen. Neural network PID reaching law sliding mode control of servo motor NCS[J]. Fire Control & Command Control, 2020, 45(8): 22–29
[4] 邓华, 王仁强, 胡甚平, 等. 分布式遗传的船舶航向神经网络优化控制[J]. 上海海事大学学报, 2020, 41(4): 15–19+49
DENG Hua, WANG Renqiang, HU Shenping, et al. Ship course neural network optimal control based on distributed genetic algorithm[J]. Journal of Shanghai Maritime University, 2020, 41(4): 15–19+49
[5] 熊中刚, 刘忠, 王寒迎, 等. RBF神经网络增量式PID自动转向控制系统设计[J]. 农机化研究, 2021, 43(4): 27–32
XIONG Zhonggang, LIU Zhong, WANG Hanying, et al. Design of automatic steering control system based on RBF neural network incremental PID[J]. Journal of Agricultural Mechanization Research, 2021, 43(4): 27–32
[6] 时尚, 童仲志, 侯远龙, 等. 基于模糊RBF神经网络的大口径武器PID控制[J]. 电光与控制, 2020, 27(10): 94–98
SHI Shang, TONG Zhongzhi, HOU Yuanlong, et al. PID control of large-caliber weapon based on fuzzy RBF neural network[J]. Electronics Optics & Control, 2020, 27(10): 94–98
[7] 王顺山, 汪建华. 改进型BP神经网络PID控制器在微波电源磁场强度控制中的仿真研究[J]. 电视技术, 2022, 46(6): 68–72
WANG Shunshan, WANG Jianhua. Simulation research on improved BP Neural network PID controller in the control of magnetic field strength of microwave power supply[J]. Video Engineering, 2022, 46(6): 68–72
