摘要
数控机床故障诊断及维护是机床调试和使用过程中的重要组成部分,是目前制约数控机床发挥正常作用的主要因素之一。现有数控机床故障自诊断系统能够诊断常见电器系统故障及简单的与系统相连部件的故障,但故障出现率较高且引起机床加工质量下降的机械类故障的自诊断基本上还是盲点,而主轴组件的故障在此类故障中占了相当比重,这也一直是国内外数控机床故障诊断领域的难题。
本文针对性提出从软计算理论的全新视角解决该问题,对在获取故障知识的数据准备阶段和知识发现阶段的几个关键问题展开了较为深入的研究和探索。
在知识获取的数据准备阶段,进行了两个方面的研究工作。
首先选取数控机床主轴系统的两大组件即滚动轴承和齿轮作为研究对象,通过对比分析它们与一般机械振动的机理后得到结论,即滚动轴承故障主要表现为表面磨损和剥落,而主轴齿轮最主要的故障来源于运动中产生的齿面均匀磨损和局部剥落故障。对前者,在进行知识获取过程提取特征时可以用基频及其整数或分数倍频处幅值为特征参数；对后者,可以依据振动信号啮合频率及其两侧产生的边频带的组合频谱诊断故障。针对主轴齿轮故障数据获取时的测点布置优化问题,采用有限元建模分析和谐响应分析,确定出主轴箱振动测点的理论最佳位置。搭建了以上两种组件故障模拟实验系统,为后续研究工作获取原始数据做了准备。
其次,从数据采集和处理角度,特别提出使用一个三阶低通巴特沃斯滤波器和一个三阶高通巴特沃斯滤波器建立的带通滤波器进行滤波,并对该滤波过程进行了数学分析；为了实现将传感器获取数据的融合,针对单一传感器数据融合的时问性问题,提出了结合算术均值与递推估计的数据融合方法,获得了比算术平均值更可靠的测量结果,而针对多传感器数据融合的空间性问题,提出一种多传感器数据的加权融合算法,不同的传感器按照相应的权数,在总均方误差最小这一最优条件下,根据各个传感器所得到的测量值以自适应的方式寻找其对应的权数,使融合后的数据结果达到最优,并提出采用信息熵来评价数据融合的效果。
在故障数据的知识发现过程阶段,分别对两种组件的故障采取不同软计算方法获取了故障知识规则,实现了故障诊断。
针对滚动轴承故障实验所获取数据,分别运用基于等间距聚类与属性重要度约简算法和基于k-均值聚类与区分矩阵约简算法,均实现表面磨损和剥落故障及正常状态三种模式的知识及规则的获取。
针对数控机床主轴齿轮的典型故障诊断,构建了一种具有三层网络结构模型的BP神经网络,经过实验数据样本的训练和仿真,实例结果验证了该方法可以实现对齿轮齿面均匀磨损故障、齿面局部剥落故障以及正常状态的识别。
Fault diagnosis and maintenance of CNC machine tools are important parts of machine debugging and processing, which is one of the main factors restricting CNC machine tools playing a normal role.Simple fault of components which are connected to system as well as common electrical system fault can be self-diagnosed presently. As to high-frequency mechanical failure which leads to declining machining quality, self-diagnosis is still of blind zone. Spindle component fault accounts for a considerable proportion of such fault, which has been puzzling the field of fault diagnosis for CNC machine tools at home and abroad.
From the perspective of Soft Computing Theory, the dissertation discusses and investigates key issues regarding fault knowledge acquisition data preparation stage and fault knowledge discovery stage.
Two tasks are done in data preparation stage of knowledge acquisition.
In the first place, the two major components of the CNC machine tools spindle system, rolling bearings and gears, are selected as research objects. By comparative study of general mechanical vibration mechanism with vibrations of rolling bearings and gears, it can conclude that the main fault of rolling bearings are surface wear and spalling while the main fault of spindle gears derives from tooth surface uniform wear and localized spalling. As to the fault of rolling bearings, the corresponding amplitude about base frequency as well as its integer or fraction multiple frequency are selected as characteristic parameters in the process of knowledge acquisition. As to the fault of gears, vibration signal meshing frequency as well as combined spectrum produced in sidebands can be used in fault diagnosis. In regard to measurement point arrangement optimization, finite element modeling and harmonic response analysis can be introduced in determining the theoretical optimum position of spindle box vibration measurement points. The fault simulation experiment system of rolling bearings and gears is established for original data acquisition.
In the second place, from the perspective of data collecting and processing, a third-order low-pass Butterworth filter and a third-order high-pass Butterworth filter are used to establish a band-pass filter for filtering. Besides, the filtering process is mathematically analyzed. In order to achieve sensor acquisition data fusion, data fusion method of arithmetic mean and recursive estimation is proposed regarding single sensor data fusion timing problem. Thus, measurement results which are more reliable than arithmetic mean are acquired. As to the spatial problem of multi-sensor data fusion, a multi-sensor data weighted fusion algorithm is proposed. Based on measurement result of each sensor, different sensors look for corresponding weights in an adaptive way under optimal conditions that the total mean square error is minimum. In this way, the fused data are optimal. Besides, information entropy is used to evaluate the effect of data fusion.
In the stage of fault data knowledge discovery, different soft computing methods are used to acquire fault knowledge rules based on rolling bearing and gear fault respectively, through which self-diagnosis is achieved.
Based on acquired data of rolling bearing fault experiment, algorithm combining equally spaced clustering with attribute importance reduction as well as algorithm combining k-means clustering with discernibility matrix reduction are applied to acquire knowledge and rules of surface wear, spalling failure and normal state mode respectively.
A kind of BP neural network of three-tier network architecture model is established according to typical CNC machine tools spindle gear fault diagnosis. After training and simulation of the experimental data samples, the result shows that the method can be used to recognize gear tooth surface even wear failure, tooth surface localized spalling failure and normal state.
引文
[1]钟秉林,黄仁.机械故障诊断学(第2版)[M].北京：机械工业出版社,2002.
[2]屈梁生,何正嘉.机械故障诊断学[M].上海：上海科学出版社,1986.
[3]额田啓三.机械故障可靠性与故障分析[M].北京：国防工业出版社,2007.
[4]陈进.机械设备振动监测与故障诊断[M].上海：上海交通大学出版社,1999.
[5]吴今培.智能故障诊断技术的发展和展望[J].振动、测试与诊断,1999,19(2)：79-86.
[6]何勇,李增芳.智能化故障诊断技术的研究与应用[J].浙江大学学报(农业与生命科学版),2003,29(2)：119-124.
[7]Samanta B. Artificial neural networks and genetic algorithms for gear fault detection[J]. Mechanical Systems and Signal Processing.2004,18(5):1273-1282.
[8]Javier Sanza R.P.,Consuelo Huerta.Fault diagnosis of rotating machinery based on auto-associative neural networks and wavelet transforms [J].Journal of Sound and Vibration,2007,302(4-5):981-999.
[9]宋刚.基于网络的数控机床远程协作诊断系统研究[D].上海：上海交通大学,2003.
[10]林朝平.数控机床故障诊断技术的发展动向[J].新技术新工艺,2003,9：9-10
[11]王侃夫.数控机床故障诊断及维护.北京：机械工业出版社,2000.
[12]李斌.数控加工技术.北京：高等教育出版社,2001
[13]卢斌.数控机床及其使用维修.北京：机械工业出版社,2001
[14]冯辛安.机械制造装备设计(第2版)[M].北京：机械工业出版社,2005.
[15]邓三鹏,徐小力,张建新等.基于噪声小波包络谱的数控机床主轴故障诊断研究[J].机床与液压,2009,37(12)：219-221
[16]周广文,贾亚洲,刘君义.专用数控机床主轴早期可靠性控制图分析[J].机床与液压,2005(3)：37-39.
[17]伍星,陈进,李如强等.基于数据挖掘的设备状态监测和故障诊断.振动与冲击,2004.23(4)：p.70-74.
[18]张建军.基于元数据的故障诊断知识统一方法.计算机工程,2010.36(16)：p.49-51.
[19]杨兵.基于知识库的变压器故障诊断专家系统.中国电机工程学报,2002(10).
[20]韩捷,石来德.全谱分析技术及其在故障诊断中的应用.郑州大学学报：工学版,2002.23(3)：44-47.
[21]Fayyad U, Piatetsky-Shapiro, Smyth Uthurusamy, Advances in Knowledge Discovery and Data Mining,MIT Press,1996
[22]E.Mjolsness, D.DeCoste. Machine Learning for Science:State of the Art and Future Prospects. Science.2001,293(14):2051-2055.
[23]Zadeh L.A.,Fuzzy logic,Neural Networks and soft computing, Communications of the ACM,1994,37(3):77-84
[24]软计算,2011 [Online].Available:http://baike.baidu.com/view/911667.htm
[25]Zadeh L.A.,A definition of soft computing in greater detail.1991 [Online].Available:http://secs.ceas.uc.edu/-mazlack/professional/BISC/BISC-DBM-so ft.html
[26]汤建国,祝峰.粗糙集与其他软计算理论结合情况研究综述[J].计算机应用研究,2010,27(7).
[27]宋颖钊,郭海湘,廖貅武等.软计算与硬计算融合的含油性属性与样本约简[J].数学的实践与认识,2010(23).
[28]何春梅.模糊神经网络的性能及其学习算法研究[D].南京：南京理工大学,2010.
[29]薛锋,柯孔林.粗糙集理论和遗传算法集成的上市公司违规行为预警研究[J].软科学.2008,22(4)：49-53
[30]王国胤,张清华,胡军.粒计算研究综述[J].智能系统学报,2007,2(6)：8-26.
[31]黄文虎,夏松波,刘瑞岩等.设备故障诊断原理、技术及应用[M].北京：科学出版社,1996
[32]陈大禧,朱铁光.大型回转机械诊断的现场实用技术[M].北京：机械工业出版社,2002.
[33]何正嘉,訾艳阳,孟庆丰等.机械设备非平稳信号的故障诊断原理及应用[M].北京：高等教育出版社,2001.
[34]史铁林,陈勇辉,李巍华等.提高大型复杂机电系统故障诊断质量的几种新方法[J].机械工程学报,2003,39(3)：1-10.
[35]周瑞.基于第二代小波的机械故障信号处理方法研究[D].哈尔滨：哈尔滨工业大学,2009.
[36]宋晓萍.旋转机械振动信号的分离[D].西安：西北工业大学,2007.
[37]何慧龙.机电设备微弱特征提取与诊断方法研究[D].天津：天津大学,2006.
[38]何俊.循环平稳和解调频技术在故障诊断中的研究和应用[D].上海：上海交通大学,2008
[39]何清波.多元统计分析在设备状态监测诊断中的应用研究[D].合肥：中国科学技术大学,2007.
[40]王胜春.自适应时频分析技术及其在故障诊断中的应用研究[D].济南：山东大学,2007.
[41]朱启兵.基于小波理论的非平稳信号特征提取与智能诊断方法研究[D].东北大学,2005.
[42]李巍华.基于核方法的机械故障特征提取与分类技术研究[D].华中科技大 学,2003.
[43]郝志华.基于局域波法和盲源分离的故障诊断方法应用研究[D].大连理工大学,2005.
[44]任达千.基于局域均值分解的旋转机械故障特征提取方法及系统研究[D].浙江大学,2008.
[45]毕果.基于循环平稳的滚动轴承及齿轮微弱故障特征提取应用研究[D].上海交通大学,2007.
[46]高金吉.高速涡轮机械振动故障机理及诊断方法的研究[D].北京：清华大学,1993.
[47]徐敏,张瑞林,等.设备故障诊断手册[M].西安：西安交通大学出版社,1998.
[48]钟掘,陈安华.机械系统状态监测与故障诊断领域的重要课题—机械非线性故障的描述、诊断与预测[J].世界科技研究与发展,1996,6：15-19.
[49]陈予恕,田家玉,金宗武,等.非线性动力学理论与大型火电机组振动故障综合治理技术[J].中国机械工程,1999,10(9)：1063-1068.
[50]闻邦椿,武新华,丁千,等.故障旋转机械非线性动力学的理论与试验[M].北京：科学出版社,2004.
[51]王太勇.复杂制造系统动态测控与智能诊断技术.航空制造技术[J].2010.13
[52]于金.数控机床热误差的模型预报补偿.组合机床与自动化加工技术[J],2002.4(7).
[53]周尧.多维非平稳时间序列在机床主轴故障诊断中的应用.机床与液压,2007.35(6)：p.228-230
[54]杨树莲.数控机床主轴在线故障诊断新方法的实现.机床与液压,2003：p.331-332
[55]冯冬芳.用故障诊断方法判断机床主轴轴承的工作状态.组合机床与自动化加工技术,2005：p.33-35.
[56]邓三鹏.基于噪声小波包络谱的数控机床主轴故障诊断研究.机床与液压,2009：p.219-221.
[57]宋刚.基于Sugeno模糊模型的数控机床故障诊断法.上海交通大学学报Vol.39 No.1 Jan.2005
[58]姚鑫骅.基于粗糙集理论的数控机床智能故障诊断研究.浙江大学学报：工学版,2008.42(10)：p.1719-1724.
[59]史忠植.知识发现[M].北京：清华大学出版社,2002
[60]J R Quinlan. Induction of decision trees[J].International Journal of Man-Machine Studies,1987,27:221—234.
[61]J R Hong. AEI:An Extension Matrix Approximate Method for the General Covering Problem [J]. Int J of Computer and Information Science,1985,14(6).
[62]洪家荣.示例学习的扩张矩阵理论[J].计算机学报,1991,14(6)：37—42.
[63]James S, Ribeiro K A, Kaufman L K. Knowledge Discovery from Multiple Databases. In:Proc.Of the 1st Int. Conf. on Knowledge Discovery in Databases and Data Mining [M]. Montreal, Canada:AAAI Press,1995.240—245.
[64]黄考利.装备故障诊断专家系统知识获取方法.计算机工程[J],2004,30(23)
[65]伊利亚·普利高津.确定性的终结-时间、浑沌与新自然法则[M].上海：上海科技教育出版社.2009.
[66]Z.Pawlak.Rough Sets [J].International Journal of Computer and Information Sciences, 1982,11:341-356.
[67]Qiang Shen, Richard Jensen. Rough Sets, Their Extensions and Applications [J]. International Journal of Automation and Computing.2007,04(3):217-228.
[68]Z.Pawlak. Some Issues on Rough Sets. Transactions on Rough Sets, vol.1, pp.1-58, 2004.
[69]王国胤.Rough集理论与知识获取[M].西安：西安交通大学出版社,2001
[70]张文修,吴伟志.粗糙集理论介绍和研究综述[J].模糊系统与数学,2000,14(4)：1-12)
[71]张邦基,于德介,杨胜.基于小波变换与粗集理论的滚动轴承故障诊断[J]中国机械工程,2008,19(15)：1793-1796.
[72]李建兰,黄树红,张燕平.基于Rough Set理论的典型振动故障诊断[J].动力工程,2008,28(1)：76-79.
[73]文振华,左洪福.基于粗糙集-集成神经网络的航空发动机磨损故障诊断方法[J].中国机械工程,2007,18(21)：2580-2584
[74]Y.Y.Yao, S.K.M.Wong, C.J.Butz. On information-theoretic measures of Attribute importance [C]. Proceedings of 3rd pacific-Asia Conference on Knowledge Diseovery and Data Mining(PKDD),1999:133-137
[75]B.Walczak, D.L.Massart. Rough sets theory [J]. Chemometrics and Intelligent Laboratory Systems,1999,47:9-13
[76]王伟杰,黄文涛,赵学增,代礼周.基于粗糙集理论的汽轮机组回热系统故障诊断模型[J].热能动力工程,2003,18(6)：618-622.
[77]董辛,石来德,韩捷,简小刚.基于失谱和粗糙集理论的旋转机械故障诊断[J].中国机械工程学报,2008,6(1)：73-78.
[78]郭小荟,马小平.基于粗糙集的特征提取[J].计算机工程与应用,2007,43(1)：221-224
[79]赵荣珍,孟凡明,张优云.基于粗糙集知识获取的转子轴承系统故障诊断知识库构造研究[J].润滑与密封,2004,7(4)：25-30
[80]赵荣珍,张优云.基于Rough set知识获取的故障数据表聚类离散化方法研究[J].机械工程学报,2005,41(1)：145-150
[81]郭庆琳,郑玲.基于模糊粗糙集数据挖掘的汽轮机组故障诊断研究[J].中国电机工程学报,2007,27(8)：81-87
[82]董立新,肖登明.模糊粗糙集数据挖掘方法在电力变压器故障诊断中的应用研究[J].电力系统及其自动化学报,2004,16(5)：1-3.
[83]李艳,董健康,耿宏等.基于粗糙集-神经网络的飞机故障诊断方法研究[J].计算机科学,2008,35(8A)：79-99.
[84]李增芳,何勇.基于粗糙集与BP神经网络的发动机故障诊断模型[J].农业机械学报,2005,36(8)：118-121.
[85]凌维业,贾民平,许飞云.粗糙集神经网络故障诊断系统的优化方法研究[J].中国电机工程学报,2003,23(5)：95-102.
[86]郝丽娜.粗糙集网络智能混合系统及其工程应用[D].沈阳：东北大学,2001.
[87]皮骏.基于粗糙集理论的旋转机械故障诊断技术[D].西安：西北工业大学,2006.
[88]张琦,韩祯祥,文福拴.一种基于粗糙集理论的电力系统故障诊断和警报处理新方法[J].中国电力,1998,31(4)：32-35.
[89]袁小宏,赵仲生,屈梁生.粗糙集理论在机械故障诊断中的应用研究[J].西安交通大学学报,2001,35(9)：954-957.
[90]黄仙,方璐.基于变精度粗糙集的电力设备故障诊断[J].现代电力,2009,126(1)：67-70.
[91]肖迪.新型粗糙神经网络的模式识别与故障诊断方法的研究[D].南京航空航天大学,2005.
[92]宋艳清.基于仿生模式识别理论的双权值神经网络模拟电路故障诊断方法研究[D].中国海洋大学,2007.
[93]张威.人工神经网络用于传感信号的模式识别[D].北京交通大学,2011.
[94]周明.基于模式识别原理的模拟电路故障诊断神经网络方法[D].湖南大学,2001.
[95]侯俊剑.基于声像模式识别的故障诊断机理研究[D].上海交通大学,2011.
[96]周家驹,许志宏,石乐明,张跃敏,蔡松筠.人工神经网络方法在材料性能预报及化工过程故障诊断中的应用[J].化工冶金,1993,(01)：57-62.
[97]袁海英.基于时频分析和神经网络的模拟电路故障诊断及可测性研究[D].电子科技大学,2006.
[98]杨涛.基于小波分时尺度矩特征的多状态信息融合振动故障诊断和预测方法研究[D].华中科技大学,2009.
[99]张克鑫.2种不同内陆水体浮游藻类发生动态及预测模型构建[D].宁波大学,2011.
[100]郑小霞,钱锋.模糊神经网络推理的实时故障诊断专家系统[J].计算机工程与 应用,2006,(03)：226-229.
[101]马宁波,王春平,孙书鹰,姜为学.基于神经网络的火控系统故障诊断专家系统研究[J].科学技术与工程,2008,(23)：6228-6230.
[102]王洋.单、双级耦合热泵系统故障分析与诊断研究[D].哈尔滨工业大学,2007.
[103]顾雪平,张文勤,高曙,杨以涵,盛四清.人工神经网络和专家系统结合运用的电力系统故障诊断方法[J].华北电力学院学报,1994,(02)：12-17.
[104]程龙.多推理机制及信息反馈的远程故障诊断专家系统的研究[D].合肥工业大学,2010.
[105]李如强,陈进,伍星,一种基于软计算的转子故障诊断方法[J].振动与冲击,2005,24(1)：77-80.
[106]张周锁,李凌均,何正嘉.基于支持向量机的机械故障诊断方法研究[J].西安交通大学学报,2002,36(12)：1303-1306.
[107]KORBICZ J, KOSCIELN Y J M, KOWALCZU K Z, et al. Fault diagnosis-models, artificial intelligence and applications[M]. Berlin:Springer,2004.
[108]周延佑,陈长年.智能机床-数控机床技术发展新的里程碑[J].制造技术与机床,2007,56(4)：43-45.
[109]HU D J,SONG G. Application of neural network in CNC machine fault diagnosis [J]. Journal of Donghua University,2004,21(4):131-138.
[110]程发斌.面向机械故障特征提取的混合时频分析方法研究[D].重庆：重庆大学,2007.
[111]李云松,任艳君.智能诊断技术发展综述[J]四川兵工学报,2010,31(4)：122-125
[112]朱大奇.电子设备故障诊断原理与实践[M].北京：电子工业出版社,2004.
[113]安治永,李应红,苏长兵.航空电子设备故障诊断技术研究综述[J].电光与控制,2006,13(3)：5-10.
[114]胡洁.高维数据特征降维研究综述[J].计算机应用研究,2008,25(9)：2601-2606.
[115]DHILLON I S, MALLELA S, MODHA S. Information theoretic co-clustering [C]//Proc. of the 9th ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining. New York:ACM,2003:89-98.
[116]熊光华.数控机床[M].北京：机械工业出版社,2002.
[117]Rubini R, Meneghettiu. Application of the envelope and wavelet transform analyses for the diagnosis of incipient faults in ball bearings.Mechanical systems and signal Processing.2001(15):287-302.
[118]廖伯瑜.机械故障诊断基础[M].北京：冶金工业出版社.1995.
[119]张安华.机电设备诊断原理与技术[M].西安：西北工业大学出版社.1995.
[120]韩捷,张瑞林等.旋转机械故障机理及诊断技术[M].北京：机械工业出版社.1997.8
[121]闻邦椿,顾家柳,夏松波等.高等转子动力学[M].北京：机械工业出版社,2000.
[122]魏木生.广义最小二乘问题的理论和计算[M].北京：科学出版社2006.9
[123]Choi D., Kwon W.T., Chu C.N. Real-time monitoring of tool fracture in turning using sensor fusion [J]. International Journal of Advanced Manufacturing Technology. 1999.15(5):305-310.
[124]Renzullo, Luigi J, Barrett. Multi-sensor model-data fusion for estimation of hydrologic and energy flux parameters [J]. Remote Sensing of Environment.2008. 112(4):1306-1319.
[125]Cohen Lior, Avrahami-Bakish. Real-time data mining of non-stationary data streams from sensor networks [J].Information Fusion.2008.9(3):344-353.
[126]Ren Hongliang, Rank Denis. Multisensor data fusion in an integrated tracking system for endoscopic surgery [J]. IEEE Transactions on Information Technology in Biomedicine.2012.16(1):106-111.
[127]Moore T., Starr A, Hesketh G. A hierarchical multi-stage data fusion approach to non-destructive evaluation of aero engine components [J].Non-Destructive Testing and Condition Monitoring.2004.46(8):468-472.
[128]唐雅娟.发动机试验传感器数据证实的软计算方法与系统实现研究[D].国防科学技术大学,2007.
[129]曾黄麟.智能计算：关于粗集理论、模糊逻辑、神经网络的理论及其应用[M].重庆：重庆大学出版社.2004.
[130]黄文涛,赵学增,王伟杰,等.基于粗糙集理论的故障诊断决策规则提取方法[J]中国电机工程学报,2003,23(11)：150-154.
[131]肖云魁,李世义,王建新,等.以粗糙集近似逼近理论提取发动机振动故障特征[J].振动、测试与诊断,2004,24(4)：262-265.
[132]许琦粗糙集理论在旋转机械故障诊断技术上应用的研究[D].南京：南京工业大学2003.
[133]谭天乐.基于粗糙集的过程建模、控制与故障诊断[D].杭州：浙江大学,2003.
[134]胡清华.混合数据知识发现的粗糙计算模型和算法[D].哈尔滨：哈尔滨工业大学,2008.
[135]伍星,迟毅林,陈进.基于熵度量和遗传算法的粗糙集归约方法[J].振动与冲击,2009,28(2)：82-85.
[136]李如强,陈进,伍星.基于奇异值分解、模糊聚类和粗糙集理论的旋转机械故障诊断[J].振动与冲击,2005,24(4)：46-49.
[137]Rafiq Maliha, Can U. Dogruer, H. Nevzat Oezgueven. Nonlinear Dynamic Modeling of Gear-Shaft-Disk-Bearing Systems Using Finite Elements and Describing Functions [J]. Journal of Mechanical Design.2004.126(3):534-541.
[138]刘国庆,杨庆东.ANSYS工程应用教程-机械篇[M].北京：中国铁道出版社2002.
[139]韩立群.人工神经网络教程[M].北京：北京邮电大学出版社.2006.
[140]Chen D., Wang W.J. Classification of wavelet map patterns using multi-layer neural networks for gear fault detection [J]. Mechanical Systems and Signal Processing,2002, 16(4):695-704.
[141]Stehen O.T.Ogaji, Riti Singh. Advanced engine diagnostics using artificial neural networks [J].Applied Soft Computing,2003,3(3):259-271.
[142]Yaguo Lei, Ming J. Zuo, Zhengjia He, et al A multidimensional hybrid intelligent method for gear fault diagnosis [J]. Expert Systems with Applications,2010, 37(2):1419-1430.
[143]B. Samanta, C. Nataraj. Use of particle swarm optimization for machinery fault detection [J]. Engineering Applications of Artificial Intelligence,2009,22(2):308-316.
[144]Jian-Da Wu, Peng-Hsin Chiang. Application of Wigner-Ville distribution and probability neural network for scooter engine fault diagnosis [J]. Expert Systems with Applications,2009,36(2):2187-2199.
[145]汤宝平,习建民,李锋.基于E lm a n(?)神经网络的旋转机械故障诊断[J].计算机集成制造系统,2010,16(10)：2148-2152.
[146]N. Saravanan, V.N.S. Kumar Siddabattuni, K.I. Ramachandran. Fault diagnosis of spur bevel gear box using artificial neural network (ANN), and proximal support vector machine (PSVM)[J]. Applied Soft Computing,2010,10(1):344-360.
[147]Samanta B. Artificial neural networks and genetic algorithms for gear fault detection [J]. Mechanical Systems and Signal Processing,2004.18(5):1273-1282.
[148]Javier Sanza,R.P.Consuelo Huerta.Fault diagnosis of rotating machinery based on auto-associative neural networks and wavelet transforms[J] Journal of Sound and Vibration,2007,302(4-5):981-999.
[149]Sheng Zhang,Asakura T.,Xiaoli Xu,et al,Fault diagnosis system for rotary machines based on fuzzy neural network[C].2003 IEEE/ASME International Conference on Advanced Intelligent Mechatronics,l:199-204.
[150]Jian-Da Wu, Chiu-Hong Liu. An expert system for fault diagnosis in internal combustion engines using wavelet packet transform and neural network [J]. Expert Systems with Applications,2009,36(3):4278-4286.
[151]Tetsuro Mitoma, Huaqing Wang, Peng Chen. Fault diagnosis and condition surveillance for plant rotating machinery using partially-linearized neural network[J]. Computers & Industrial Engineering,2008,55(4):783-794.
[152]Peng Chen, Yamamoto T., Mitoma T., et al. Intelligent diagnosis method for plant machinery using wavelet transform, rough sets and neural network[C]. Proceedings of 2005 International Conference on Machine Learning and Cybernetics,2005, 1:417-422.
[153]李巍华,张盛刚.基于改进证据理论及多神经网络融合的故障分类[J].机械工程学报,2010,46(9)：93-99.
[154]N. Saravanan, K.I. Ramachandran. Incipient gear box fault diagnosis using discrete wavelet transform (DWT) for feature extraction and classification using artificial neural network (ANN)[J]. Expert Systems with Applications,2010,37(6):4168-4181.
[155]Deng Lin-feng, Zhao Rong-zhen. An Improved Fuzzy Neural Network and Its Application in Machine Fault Diagnosis[C]. The 2010 International Conference on Computational and Information Sciences (ICCIS2010), Chengdu,2010.