CAJ | 학술논문

火电厂过热汽温控制品质的好坏，直接影响发电机组的安全运行及其生产效率。常规PID控制算法无法满足过热汽温控制系统参数的时变性，利用BP神经网络的自学习性和鲁棒性的特点，结合常规PID控制算法，设计了一种基于BP神经网络的PID过热汽温控制系统，根据被控对象参数的变化，采用BP神经网络自动调整PID参数，实现了PID参数自调整的功能。经过仿真分析与实际投入工厂试运行表明，设计的控制系统可行，且控制效果良好。
화전엄과열기온공제품질적호배，직접영향발전궤조적안전운행급기생산효솔。상규PID공제산법무법만족과열기온공제계통삼수적시변성，이용BP신경망락적자학습성화로봉성적특점，결합상규PID공제산법，설계료일충기우BP신경망락적PID과열기온공제계통，근거피공대상삼수적변화，채용BP신경망락자동조정PID삼수，실현료PID삼수자조정적공능。경과방진분석여실제투입공엄시운행표명，설계적공제계통가행，차공제효과량호。
The control quality of superheated steam temperature in thermal power plant directly affects the safe operation of the generating units and production efficiency. Traditional PID control algorithm could not meet the parameter time variability of the superheated steam temperature control system. Based on BP neural network with the characteristics of self-learning and robustness and combined with traditional PID control algorithm, a superheated steam temperature control system based on BP neural network is designed. PID parameters are automatically adjusted according to BP neural network and the function of automatic adjustment is realized. Simulation analysis and factory test run shows that the designed control system is feasible, and the control performance is good.