摘要
为了提高深海大压力下微小波动压力的测量精度,文章介绍了一种新型的、基于液体可压缩性的、压力平衡式的活塞式压力传感器,针对该活塞式压力传感器压力控制系统存在的非线性、参数时变性以及时滞问题,提出将反向传播(back propagation,BP)神经网络与常规比例积分微分(proportional integral derivative,PID)相结合用于传感器的压力控制;设计BP神经网络PID控制器,利用BP神经网络的在线自学习能力对常规PID控制器的参数进行在线自动调节;在建立系统数学模型并进行Matlab仿真实验验证可行性后,搭建实物平台进行实验分析。阶跃实验结果表明,与常规PID控制相比,BP神经网络PID的调整时间和超调量均有所减小,其动态响应能力得到提高,表现出较好的自适应能力。
In order to improve the measurement accuracy of small fluctuation pressure under deep-sea large pressure,a new type of pressure balance type piston pressure sensor based on liquid compressibility is introduced.Aiming at the problems of non-linearity,parameter time-varying,and time lag in the pressure control system of the piston pressure sensor,the combination of back propagation(BP)neural network and proportional integral derivative(PID)for pressure control of this sensor is proposed.Based on the online self-learning ability of BP neural network,the PID controller of BP neural network is designed to automatically adjust the parameters of PID controller.After establishing the mathematical model of system control and conducting simulation experiments with Matlab to verify the feasibility,the physical platform is built for the experimental analysis.The experimental results show that compared with the PID control,the adjustment time and overshoot of BP neural network PID are reduced,the dynamic response ability is improved,and the adaptive ability is better.
作者
孟涛
张彦
王勇
MENG Tao;ZHANG Yan;WANG Yong(School of Mechanical Engineering, Hefei University of Technology, Hefei 230009, China)
出处
《合肥工业大学学报(自然科学版)》
CAS
北大核心
2022年第1期24-29,共6页
Journal of Hefei University of Technology:Natural Science
基金
国家自然科学基金资助项目(51279044)。