摘要
为了解决直接膨胀式空调系统人工神经网络控制器控制范围和精度的问题,引入在线自适应控制系统;该控制器的控制能力测试采用直接膨胀式空调系统实验装置进行;试验结果表明,基于人工神经网络动态模型的在线自适应控制器进行训练的前提下,该控制器能够将室内空气的干球和湿球温度控制在一定范围内,具有较高的控制精度;该控制器具有一定的实用价值,对于其他的控制器设计也有一定的借鉴意义。
To address the issue of limited controllable range of a previously developed artificial neural network(ANN)-based controller for a direct expansion(DX) air conditioning(A/C) system,on-line adaptive control system is introduced.The control ability tests for the controller were carried out using an experimental DX A/C system.The test results showed that the ANN-based on-line adaptive controller developed was able to control indoor air dry-bulb and wet-bulb temperatures both near and away from the operating condition at which an ANN-based dynamic model in the ANN-based on-line adaptive controller was initially trained,with a high control accuracy.The controller has some practical value.Also,it has a certain significance for other controller design.
引文
[1]张秀玲,神经网络自适应控制的研究进展及展望[J].工业仪表与自动化装置,2002,1(5):10-14.
[2]Westphalen D.New approach to energy savings for rooftop AC[J].ASHRAE J,2004,46:38-46.
[3]Li Z S,Deng M.An experimental study on the inherent operational characteristics of a direct expansion(DX)air conditioning(A/C)unit,Build[J].Environ,2007,42:1-10.
[4]程慧,周斌,张蓉,等.神经网络自适应控制及其发展应用[J].大众科技,2010(5):4-8.
[5]Qi Q,Deng S M.Multivariable control-oriented modeling of a direct expansion(DX)air conditioning(A/C)system[J].Int.J.Refrig,2008,31:841-849.
[6]Li Z,Deng S M.A DDC-based capacity controller of a direct expansion(DX)air conditioning(A/C)unit for simultaneous indoor air temperature and humidity control-Part I:Control algorithms and preliminary controllability tests[J].Int.J.Refrig,2007,30:113-123.
[7]吴磊,李振亮.一种网络温湿度控制器设计与实现[J].计算机测量与控制,2014,22(10):3165-3167.
[8]李杰.带干扰的时滞系统的神经网络自适应控制[D].南宁:广西师范学院,2012.
[9]唐超颖,王彪.基于在线神经网络的自适应控制器的设计与应用[J].华南理工大学学报:自然科学版,2006,6(7):34-38.
[10]Khosrowshahi F.Innovation in artificial neural network learning:Learn-On-Demand methodology[J].Automat Constr,2011,20(8):1204-1210.
[11]Hussain M A,Kershenbaum L S.Implementation of an inversemodel-based control strategy using neural networks on a partially simulated exothermic reactor[J].Chem.Eng.Res.Des,2000,78:299-311.