高压共轨系统优化无模型自适应轨压控制  

Model-free Adaptive Optimal Control of Rail Pressure in High Pressure Common Rail System

作　　者：闫宇 杨蒲[1,3] 姜斌[1,2] 冒泽慧[1] YAN Yu;YANG Pu;JIANG Bin;MAO Ze-hui(College of Automation,Nanjing University of Aeronautics and Astronautics,Nanjing 210000,China;Key Laboratory of Helicopter Transmission Technology,Nanjing University of Aeronautics and Astronautics,Nanjing 210000,China;Engineering Research Center of Ministry of Education for Autonomous Control Technology of Aircraft,Nanjing University of Aeronautics and Astronautics,Nanjing 210000,China)

机构地区：[1]南京航空航天大学自动化学院,江苏南京210000 [2]南京航空航天大学直升机传动技术重点实验室,江苏南京210000 [3]南京航空航天大学飞行器自主控制技术教育部工程研究中心,江苏南京210000

出　　处：《控制工程》2022年第5期888-894,共7页Control Engineering of China

基　　金：国家自然科学基金资助项目(61922042);江苏高校“青蓝工程”项目;高等学校学科创新引智计划资助项目(B20007);飞行器自主控制技术教育部工程研究中心开放课题资助项目(NJ2020004);南京航空航天大学“直升机传动技术重点实验室”开放课题资助项目(HTL-O-19G11);基本科研业务费资助项目(NC2020002,NP2020103)。

摘　　要：高压共轨柴油机的轨压大小对于柴油机的排放性能、动力性能有着至关重要的影响。目前的轨压控制多采用PID控制方案,但PID控制存在控制精度低、全工况下需要标定的控制器参数量大、对波动的控制效果不理想等缺点。为了克服PID控制算法存在的缺点,提出了一种基于无模型自适应算法的轨压控制算法。对于无模型自适应控制算法中的控制器参数,通过Q学习进行优化整定。MATLAB/Simulink仿真结果表明,在不同的工况下,与传统的PID控制相比,基于Q学习的无模型自适应控制算法控制性能更好。The rail pressure of high pressure common rail diesel engine plays an important role in its power performance and emission performance. Most of the current rail pressure control strategies adopt PID control scheme, but PID control has some disadvantages such as low control accuracy, a large number of controller calibration parameters in all working conditions, and unsatisfactory control effect on fluctuation. In order to solve the problems of PID control algorithm, a model-free adaptive algorithm for rail pressure control is proposed in this paper. The control parameters in the model-free adaptive control algorithm are adjusted by Q learning. Compared with the traditional PID control algorithm, MATLAB/Simulink simulation results show that the proposed model-free adaptive control algorithm based on Q learning has better control performance.

关 键 词：高压共轨系统 无模型自适应 Q学习 轨压控制 

分 类 号：TP27[自动化与计算机技术—检测技术与自动化装置]