期刊文献+

锅炉过热汽温系统的DRNN网络自整定PID控制 被引量:24

A DIAGONAL RECURRENT NEURAL NETWORK SELF-TUNING PID CONTROL FOR SUPERHEATED STEAM TEMPERATURE SYSTEM
下载PDF
导出
摘要 火电厂过热汽温控制系统具有大惯性、大迟延、参数慢时变的特点,受到的扰动因素较多;随机组负荷的变化又表现出参数快时变的特性,常规的按照典型工况整定的固定参数PID控制难以适应负荷变化,往往未能取得满意的调节效果。为此,提出一种基于DRNN的两级神经网络的过热汽温系统自整定PID控制策略,其中两级神经网络分别为静态网络SNN和动态网络DNN,SNN依据机组运行工况如负荷进行PID参数的粗调整定,以适应机组负荷的较大范围变化,如参与调峰:DNN依据偏差和偏差变化率进行PID参数的细调整定,以克服机组负荷的小范围变化、参数的慢时变漂移 和各种扰动。为了克服系统的大惯性和大迟延,引入灰色预测器对未来信号进行预测,预测结果作为DNN使用的整定信息。对某汽温系统的计算机仿真研究结果表明:基于两级神经网络自整定控制策略的主汽温控制系统获得了良好的动态调节品质,具有较强的鲁棒性。 In a thermal power plant, several systems have the property of big inertia, large time delay and slow parameter variance, Superheated Steam Temperature System(SSTS) is one of them.SSTS also has a property of fast parameter variance while the unit load changes. Conventional PID controller which is tuned at typical operating point can hardly work well at different unit load. A novel self tuning PID control strategy based on a two level Neural Networks(NN) is proposed for SSTS, the two level NNs are called Static NN(SNN) and Dynamic NN(DNN) respectively. SNN is used for controller PID's arguments primary tuning according to the system operating point such as unit load, in order to follow the wide range load changing; DNN is used for PID fine tuning according to error and error rates of the SSTS, in order to overcome the small range load changing, system parameters' slow variance and some disturbance. For overcoming the big inertia and large time delay of the controlled plant, grey predictor is introduced to predict future output value, the predictive result is used as tuning information of DNN. Simulation results of a SSTS show that good dynamic regulation performance can be obtained by using the presented new method, and stronger robustness is also obtained.
出处 《中国电机工程学报》 EI CSCD 北大核心 2004年第8期196-200,共5页 Proceedings of the CSEE
关键词 锅炉 过热器 汽温系统 DRNN网络 自整定PID控制 灰色预测理论 神经网络 Thennal power engineering Superheated steam temperature system Self-tuning Diagonal recurrent neural network(DRNN) PID control Grey prediction
  • 相关文献

参考文献14

二级参考文献89

共引文献569

同被引文献234

引证文献24

二级引证文献187

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部