CAJ | 학술논문

弹性轴类零件液压伺服扭转振动试验机在实验过程中，由于系统非线性及负载变化或干扰因素的影响，其控制系统参数及数学模型易发生改变，导致控制效果变差。针对该试验机的控制系统，提出了基于BP神经网络（BPNN）的PID自适应控制算法。利用MATLAB/Simulink工具箱对该算法进行仿真实验。结果表明：结合了神经网络特点的智能PID控制器具有响应快、精度高、鲁棒性好和抗干扰能力强等优点，改善了控制系统的动态性能。
탄성축류령건액압사복뉴전진동시험궤재실험과정중，유우계통비선성급부재변화혹간우인소적영향，기공제계통삼수급수학모형역발생개변，도치공제효과변차。침대해시험궤적공제계통，제출료기우BP신경망락（BPNN）적PID자괄응공제산법。이용MATLAB/Simulink공구상대해산법진행방진실험。결과표명：결합료신경망락특점적지능PID공제기구유향응쾌、정도고、로봉성호화항간우능력강등우점，개선료공제계통적동태성능。
The hydraulic servo control system of torsional vibration testing machine used on flexible shaft doesn’t perform good enough in the process of the test.The parameters or mathematic model of the electro-hydraulic servo control system could be changed by the nonlinear, change of load or noise from outer space,leading to bad control effect of the system.Based on the control system of the testing machine,an a-daptive PID control algorithm is provided based on back propagation (BP)neural network.And a simulation experiment is given using the Simulink tool box of MATLAB.The results show that the PID controller based on BP neural network can get better control characteristics and adaptability,rapid response,high precision,strong robustness and good anti-jamming ability.The dynamic performance of the control system has been improved.