摘要
随着科技的发展,传统的维修模式已逐渐被“视情维修”所取代,而此维修模式的基础是对机械设备进行监测,只有建立在监测基础上的诊断才能避免盲目性,具有针对性,因此,建立在监测基础上,对机械设备磨损状态进行有效地预测具有十分重大的意义。
油液光谱分析技术在船舶工业领域已得到广泛应用,已成为对船舶机械设备进行工况监测、故障诊断和故障预测的有效技术手段之一,它可以有效地检测出油液中的磨损性元素的含量,分析出油液的污染程度以及添加剂的状况。油液光谱数据包含两方面内容,一方面,由于磨损金属成分与对应的摩擦副材质相对应,所以可以利用光谱分析进行故障定位；另一方面,机械磨损状态是一个逐步发展的过程,因此可以利用光谱数据来进行机械设备磨损状态的预测,前者属于故障诊断范畴,后者属于状态监测范畴,本文所做的研究工作即为后者。利用油液光谱分析技术对船舶的运行状态进行监测,能尽早地发现故障或故障趋势,避免重大故障的发生,达到视情维修的目的,因此建立光谱数据预测模型有非常重要的意义。
由于船舶运行工况复杂,其尾轴和主机的润滑油中磨损元素含量受诸多因素影响,用传统的方法难以预测其变化趋势。本文提出基于遗传神经网络的润滑油铁元素含量预测方法,并用MATLAB分别对6组油样进行建模分析,其中2组来自尾轴处滑油,4组来自主机系统油。首先对油液光谱历史数据建立时间序列,然后,基于BP神经网络建立预测模型,对铁元素含量进行预测,最后结合遗传算法对BP神经网络进行改进,使预测值的平均相对误差在可接受的范围内。通过实例分析,该方法能够满足船舶状态监测的需要。
With the development of science and technology, the traditional maintenance model has gradually been replaced by'condition-based maintenance', which is based on the monitoring of machinery and equipment. Only by the basis of monitoring, diagnosis can avoid blindness and have specific aim.
Oil spectroscopic analysis technology has been widely applied in ship building industry field. It has been one of the effective and technical means for ship machinery equipment monitoring, fault diagnosis and fault forecasting, it can effectively detect the content of abrasion resistant element in the oil, and analyze the condition of oil pollution and additives. Oil spectral data contains two aspects, on one hand, since the wearing metal components matches the materials of friction pair, so the spectral data can be taken on fault location, on the other hand, mechanical wearing condition is a process of gradual development, so the spectral data can also be taken on prediction of mechanical equipment wearing condition. The former belongs to the category of fault diagnosis, and the latter belongs to the category of condition monitoring. The specific research of paper is the latter. Oil spectral analysis technology is used for ship condition monitoring, which can find fault or fault trend soon, avoid large fault and achieve the purpose of'condition-based maintenance'. Therefore, the establishment of spectral data prediction model is of great importance.
Due to the complicated condition of ship operation, the wearing element content in lubricating oil of propeller shaft and main engine is influenced by many factors, the changing trend can not be correctly predicted in traditional method. The research paper purposes a prediction method based on genetic algorithm and BP neural network for iron content in lubricating oil. What's more,6 groups of oil sample is analyzed with MATLAB,2 of them is from propeller shaft, and another 4 is from main engine. First, it need to establish the time series of oil spectral historical data, and then, prediction model is established on BP neural networks to predict the iron element content, at last, the improved BP network with GA make the average relative error within acceptable limits. Through the case analysis, the method can satisfy the needs of ship condition monitoring.
引文
[1]魏海军.船用润滑油的使用与管理.大连：大连海事大学出版社,2006.
[2]吴琴,冯钦丽,张红侠.光谱分析技术在柴油机状态监测中的应用.工艺与装备.2006(5)：36-38.
[3]张培林.自行火炮油液光谱分析研究：(硕士论文).南京：南京理工大学,2003.
[4]王海燕,卢山.非线性时间序列分析及其应用[M].北京：科学技术出版社,2006.
[5]范剑青,姚琦伟.非线性时间序列—建模、预报及应用[M].北京：高等教育出版社,2005.
[6]邓聚龙.灰预测与灰决策.武汉：华中科技大学出版社,2000.
[7]曹天捷.一类回归分析预测模型及其应用.中国民航学院学报.2005,23(2)：47-51.
[8]Yutaka Fukuoka. Hideo Matsuki, Haruyuki Minamitani, Akimasa Ishida. A modified back Propagation method to avoid false local minina. Neural networks.1998, 11(6):1059-1072.
[9]Sietsma J and Row R J. Creating artif ieial neural networks that generalize. Neural networks.1991,4(1):67-79.
[10]Fogel D B. An information criterion for optimnal neural network section IEEE transactions on neural networks.1991,2(5):490-497.
[11]Alireza Kllotanzad, RezaAfkhami-Rohani, Tusn-Liang Lu, AlirezaAbaye, Malcolm Davis,Dominic J. Maratukulam. ANNSTLF-A neural network based electric load forecasting system. IEEE transaetions on neural networks.1997,8(4):835-845.
[12]Cho S, Cho Y and Yoon S. Reliable roll force Prediction in cold mill using multiple neural networks. IEEE transaetions on neuralnetworks.1997,8(4):874-882.
[13]Hanson J V and Nelson R. Neural networks and traditional times series methods:A synergistic combination in State economic forecasts IEEE transactions on neural networks.1997,8(4):863-873.
[14]张良均,曹晶.神经网络实用教程.北京：机械工业出版社,2008.
[15]萨马拉辛荷著.史晓霞译,陈一民译,李军治译.神经网络在应用科学和工程中的应用：从基本原理到复杂的模式识别.北京：机械工业出版社,2010.
[16]Liu Yu-bing, Chen Ya-zhong, Wang Xiao-dong etal. Research on Oil spectral analysis prediction based on remnant difference correct combined model of BP neural network. Lubrication Enginnering,2007(3):172-174.
[17]付旭云,丁刚.基于双隐层径向基过程神经网络的润滑油金属含量预测方法.润滑与密封.2009,34(2)：17-20.
[18]郑长松,马彪.改进欧拉算法在油液光谱分析趋势预测中的应用.光谱学与光谱分析,2009(4)：1078-1082.
[19]李兵,张培林,曹征等.基于遗传算法的组合预测在油液光谱分析中的应用.润滑与密封,2006(4)：145-146.
[20]范红波,张英堂,任国全等.基于SVM的柴油机油液光谱预测模型研究.润滑与密封,2006(11)：148-150.
[21]高经纬,张英堂,任国全等.柴油机光谱油液分析预测模型研究.柴油机设计与制造,2004(3)：26-28.
[22]张翠凤,龚光寅.机械设备润滑技术.广州：广州高等教育出版社,2001.
[23]中国石油润滑油公司.船舶润滑油使用手册.2002.
[24]孙培廷,魏海军.油液检测技术及其应用.世界海运,2004,27(1).
[25]魏海军,胡庆存,尹峰.船舶机械油液检测光谱分析的特征参数研究.光谱学与光谱分析,2005(7)：1125-1127.
[26]魏海军,尹峰,王宏志.润滑油光谱分析特征信息研究.润滑与密封,2006,4(4)：103-105.
[27]You Si-hai, Zheng Chang-song, Jia Qiu-hong. Application of BP artificial neural network based on oil analysis in the large-scale machine fault diagnosis. Lubrication Engineering,2006(11):168-169.
[28]魏武雄,易丹辉,刘超等.时间序列分析：单变量和多变量方法.北京：中国人民大学出版社,2009.
[29]方泽南,傅尚新,张勇.时间序列在故障诊断中的应用.清华大学学报(自然科学版),1998,38(8)：123-126.
[30]张世英.金融时间序列分析.北京：清华大学出版社,2008.
[31]WANG Li-zhen,WANG Xing-qun, CHEN Tao, ZHOU Li-hua. A weather forecast system of lancang river valley based on time sequence data mining. Journal of Yunnan University,2004,26(6):479-485.
[32]党耀国,刘思峰,王正新等.灰色预测与决策模型研究.北京：科学出版社,2009.
[33]孙霞.基于GM(1,1)的黄河(兰州段)水质灰色预测实证分析.甘肃科技纵横,2010(2)：17-20.
[34]刘庆超,范炜,张伟.基于灰色预测变化风速下的风电场经济评价.现代电力,2010,27(2)：91-94.
[35]帅训波.一种基于指数平滑的天然气产量灰色预测模型.计算机技术与发展,2010,20(3)：243-245.
[36]林亚萍,金继红.工神经网络研究进展及其在光谱分析中的应用.化学分析计量,2004, 13(3)：52-54.
[37]韩力群.人工神经网络理论、设计及应用.北京：化学工业出版社,2007.
[38]朱凯,王正林.精通MATLAB神经网络.北京：电子工业出版社,2010.
[39]CHEN Shi-wei, LI Zhu-guo, CHEN Wen-xing, etal. Research on Grey Correlation Coefficients Among Parameters of Internal Combustion Engine Oil Monitoring. Chinese Internal Combustion Engine Engineering,2005(4):81-83.
[40]张德丰.MATLAB神经网络应用设计.北京：机械工业出版社,2009.
[41]BAO Chun-jiang, WANG Bi-ling, YANG Zhi-yi. Experimental Study on Monitoring Lubricating Oil of Automotive Engine. Transactions of Csice,2008 (5):457-462.
[42]刘晋钢,韩燮,李华玲.BP神经网络改进算法的应用.华北工学院学报.2002,23(6)：449-451.
[43]岳素青,徐小明.三种初值选取方法对BP神经网络收敛速度影响的比较.太原师范学院学报(自然科学版),2005,4(3)：52-55.
[44]孙帆,施学勤.基于MATLAB的BP神经网络设计.计算机与数字工程,2007,35(7)：124-126.
[45]Xiang Zhi-wei, Zhang Hui,Wang Bin. The Application of Oil Monitoing Techniques in the Failure Diagnosis of Ship Diesel Engine. Lubrication Engineering,2009(4):108-110.
[46]葛哲学,孙志强.神经网络理论与MATLAB R2007实现[M].北京：电子工业出版社,2007.
[47]Gao Jing-wei; etc. Study on Prediction Model of Engine Operation Based on Lubrication Oil Spectrum Analysis. Design and Manufacture of Diesel Engine,2004(3):26-28.
[48]史忠植等.智能科学.北京：清华大学出版社,2006.
[49]李国勇,李维民等.人工智能及其应用.北京：电子工业出版社,2009.
[50]Li Bing, Zhang Pei-lin, Cao Zheng, etal. The Application of Combination Forecasting Based on Genetic Algorithm in Oil Spectral Analysis. Lubrication Engineering,2006(4):145-146.
[51]周明,孙树栋等.遗传算法原理及应用.北京：国防工业出版社,1999.
[52]王小平,曹立明等.遗传算法——理论、应用与软件实现.西安：西安交通大学出版社,2001.
[53]Z.米凯利维茨[美]著.演化程序——遗传算法和数据编码的结合.北京：科学出版社,2000.
[54]李影,徐涛,邢伟.基于进化遗传算法的神经网络优化.长春理工大学学报,2006,29(3)：48-50.
[55]魏东等.非线性系统神经网络参数预测及控制.北京：机械工业出版社,2008.
[56]陈开峰.改进的遗传算法及其在多目标优化中的应用研究：(硕士论文).安徽：安徽大学,2006.
[57]李敏强,徐博艺,寇纪淞.遗传算法与神经网络的结合.系统工程理论与实践,1999(2)：65-69.
[58]刘春艳.基于遗传算法_BP神经网络的主汽温控制系统的研究：(硕士论文).太原：太原理工大学,2006.
[59]刘国华,包宏,李文超.用MATLAB实现遗传算法程序.计算机应用研究,2001,(8)：79-82.
[60]蒋云彩,万顷波.MATLAB遗传算法工具GAOT的应用.江西电力职业技术学院学报,2004,17(3)：42-44.