| 92 | 1 | 15 |
| 下载次数 | 被引频次 | 阅读次数 |
针对采用离线测量方法测量淀粉含水量所带来的测量周期长、精度低等问题,提出了一种使用智能算法进行测量的方法,该方法包括线下算法与线上运算:线下算法使用BP神经网络算法,以出料的温度与湿度作为网络输入,以出料含水量作为网络输出,通过训练网络得到二者之间的数学模型;线上运算使用计算机对实时采集的数据进行运算,得出实时含水量。此方法不仅能代替测量仪器,而且还能实现实时预测的功能。通过仿真实验,验证了该方法的可行性。
Abstract：As for using off-line measuring method brings the long measuring cycle and low accuracy in water content of starch, this paper proposes a method of using the intelligent algorithm for measurement, this method can not only instead of measuring instrument, and also can realize the function of real-time prediction. This method includes the offline algorithm and online computing, offline algorithm is that using BP neural network algorithm, the temperature and humidity of the material as the input of the network, while the water content as the output of the network, through the training for the network to get the mathematical model between the input and output. Online computing is that using the computer to calculate with real-time data which has been collected, so as to obtain the real-time water content. This method can not only replace the measuring instrument, but also can realize the function of real-time prediction. The feasibility of the method is verified by the simulation experiment.
[1]王万森.人工智能[M].北京:人民邮电出版社,2011.
[2]CHEN C H.Compensatory neural fuzzy networks with rulebas ed cooperative differential evolution for nonlinear system control[J].Nonlinear Dynamics,2014,75(1/2):355-366.
[3]CHANG W D.Recurrent neural network modeling combined with bilinear model structure[J].Neural Computing and Applications,2014,4(3/4):765-77.
[4]CHAND Y,ALAM A.Performance comparison of artificial neural networks learning algorithms and activation functions in predicting severity of autism[J].Network Modeling Analysis in Health Informatics and Bioinformatics,2015(1):1-23.
[5]张昭昭,乔俊飞,余文.基于动态神经网络的瓦斯浓度实时预测方法[J].控制工程,2016,23(4):478-483.
[6]TAN P N,STEINBACH M,KUMAR V.Introduction to Data Mining[M].Beijing:Machinery Industry Press,2010.
[7]RUSSELL S J,NORVIG P.Artificial Intelligence:A Modern Approach[M].Beijing:Tsinghua University Press,2013.
[8]STEFAN F,SCHWENKER F.Neural network ensembles in reinforcement learning[J].Neural Processing Letters,2015,41(1):55-69.
[9]喻宗泉,喻晗.神经网络控制[M].西安:西安电子科技大学出版社,2009.
[10]李国勇,杨丽娟.神经·模糊·预测控制及其MATLAB实现[M].北京:电子工业出版社,2013.
[11]安军涛.基于模糊神经网络的智能PID控制器研究与设计[D].武汉:武汉理工大学,2010.
[12]刘智斌,曾晓勤,徐彦,等.采用资格迹的神经网络学习控制算法[J].控制理论与应用,2015,32(7):887-894.
[13]CHU J,NIU Y D.A novel hybrid intelligent method for fault diafnosis of the complex system[J].International Journal of Information Technology,2016,9(3):331-340.
[14]蔡立,徐鑫.MATLAB神经网络工具箱在非线性系统建模中的应用[J].机电工程技术,2008,37(2):82-84.
[15]陈宏希,邹益民.基于OPC的Matlab与S7-200 PLC实时通信在过程控制实验装置中应用[J].工业仪表与自动化装置,2015(5):55-58.
基本信息:
DOI：
中图分类号:TS237;TP183
引用信息:
[1]牛亚东,储健,李刚.一种新型淀粉含水量测量方法及仿真[J].天津职业技术师范大学学报,2016,26(03):30-33.
基金信息: