针对风电叶片模具电加热系统中被控对象存在的大惯性、非线性、干扰多等问题,提出一种基于改进径向基（RBF）神经网络的串级PID温度控制方法。首先,采用RBF神经网络结构对常规PID串级控制主回路结构进行优化,在此基础上,引入双动量因子,对主控制回路的输出Jacobian信息进行系统辨识,进而实现对控制器参数的自适应整定;其次,采用Kalman滤波器对主回路的输出噪声进行滤波,以消除外部扰动对系统辨识效果的影响;最后,搭建电加热试验平台,通过现场试验对上述算法的控制效果进行分析。仿真及现场试验结果表明：改进的径向基神经网络串级PID温度控制系统相较于常规串级控制具有响应快、超调低、抗干扰能力强等优点,且在主控制回路中的Kalman滤波算法能有效消减系统的输出噪声,可在很大程度上提高控制性能。
Abstract
To solve the problems of large inertia,non-linearity,and many disturbances of the controlled object in the electric heating control system of wind turbine blade mold,a cascade temperature control system based on improved radial basis （Radial-Basis Function,RBF） neural network was proposed. Firstly,the RBF neural network structure was used to optimize the main loop of the conventional PID cascade control. On this basis, the dual momentum factor was introduced to identify the output Jacobian information of the main control loop,and then achieve the adaptive tuning of the controller parameters. Secondly, the Kalman filter was adopted to perform algorithm processing on the output noise concentration of the main loop to eliminate the influence of external disturbance on the system identification effect. Finally,an electric heating test platform was built and the control effect of the algorithm was analyzed through field tests. Simulation analysis and field test results show that the improved RBF neural network cascade PID temperature control system was compared with the conventional cascade control has quick response and lower,and the advantages of strong anti-interference ability. In the main control circuit , Kalman filter algorithm can reduce the system output noise effectively and improve the control performance greatly.
关键词
风电叶片 /
电加热 /
神经网络 /
PID /
Kalman滤波 /
串级控制
Key words
wind turbine blades /
electric heating /
neural networks /
PID /
Kalman filters /
cascade control
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 韩超, 刘晓宇, 马永光. 风电叶片成型模具多路温度控制系统的设计[J]. 化工自动化及仪表, 2011, 38(9): 1100-1103.
HAN C, LIU X Y, MA Y G.Multi-channel temperature control system design for molding wind turbine blades[J].Control and instruments in chemical industry, 2011, 38(9): 1100-1103.
[2] 于祥勇. 风电叶片型腔后固化恒温控制理论研究与系统开发[D]. 淄博: 山东理工大学, 2016.
YU X Y.Research and development on constant temperature control system for postcure process of wind turbine blade[D]. Zibo: Shandong University of Technology, 2016.
[3] 阮博, 乌建中, 周俊杰. 风电叶片模具电加热系统温度特性及控制算法研究[J]. 流体传动与控制, 2014(2): 38-41.
RUAN B, WU J Z, ZHOU J J.Research on the control algorithm and temperature characteristics of electrical heating system for wind turbine blade mold[J]. Fluid power transmission & control, 2014(2): 38-41.
[4] 管鹏飞, 冯立超. 基于遗传算法的PID控制在叶片模温控制中的应用[J]. 科学技术创新, 2019(21): 134-135.
GUAN P F, FENG L C.Application of PID control based on genetic algorithm in blade mold temperature control[J].Science and technology innovation, 2019(21): 134-135.
[5] MINOUCHEHR N, VAEZI N, TAVAKOLI P, et al.Temperature control of heating procedure in blade production process[C]//Iranian Conference on Electrical Engineering, 2016: 271-276.
[6] 王纪亮, 焦晓红. 变速恒频双馈风力发电系统RBF网络整定PID控制器设计[J]. 太阳能学报, 2011, 32(3): 311-317.
WANG J L, JIAO X H.Design of PID controler adjusted by RBF Neural network for dfig-based wind farm[J]. Acta energiae solaris sinica, 2011, 32(3): 311-317.
[7] 于蒙, 邹志云. 基于改进差分进化算法-径向基神经网络的电热水浴串级控制系统研究[J]. 化工学报, 2019, 70(12): 4680-4688.
YU M, ZOU Z Y.Electric heated water bath cascade control system research based on improved differential evolution algorithm-radial basis function neural network[J]. CIESC journal, 2019, 70(12): 4680-4688.
[8] 林巍, 王亚刚. 串级控制系统闭环辨识及PID参数整定[J]. 控制工程, 2018, 25(1): 11-18.
LIN W, WANG Y G.Modeling for cascade control systems based on frequency domain and PID parameter tuning[J].Control engineering of China, 2018, 25(1): 11-18.
[9] ZHANG J, ZHANG F, REN M, et al.Cascade control of superheated steam temperature with neuro-PID controller[J]. ISA transactions, 2012, 51(6): 778-785.
[10] 王爽心, 贺飞, 刘如九, 等. 基于间接能量平衡的锅炉汽温GPC-PID串级控制[J]. 电机与控制学报, 2016, 20(9): 9-16.
WANG S X, HE F, LIU R J, et al.GPC-PID cascade control strategy based on indirect energy balance method for boiler steam temperature system[J]. Electric machines and control, 2016, 20(9): 9-16.
[11] 李明, 封航, 张延顺. 基于UMAC的RBF神经网络PID控制[J]. 北京航空航天大学学报, 2018, 44(10): 2063-2070.
LI M, FENG H, ZHANG Y S.RBF neural network tuning PID control based on UMAC[J]. Journal of Beijing University of Aeronautics and Astronautics, 2018, 44(10): 2063-2070.
基金
国家重点研发计划（2018YFB1501203）; 山东省自然科学基金（ZR2019MEE076）; 山东省重点研发计划（2019GGX104001）; 山东省高等学校青创科技支持计划（2019KJB031）
PDF(2046 KB)
