摘要
故障诊断系统发展到今天,仍然面临着支撑理论的局限性、规则获取和更新困难、诊断模型更新的不同步等各种问题。为此,本文以粗糙集理论为支撑理论,提出了知识发现模型,并将其分别应用到工程和医学诊断领域,发现了若干有用的诊断知识。
针对粗糙集理论核心计算环节的计算复杂性问题,本文提出一种适用于连续和离散条件属性并存的混合条件属性全距离(Mixed Attribute Whole Distance,简称MAWD)空间降维模型,并就MAWD降维方法对于粗糙集理论后续若干重要计算环节的计算复杂度进行了量化分析,提出了MAWD模型对于提高粗糙集核心计算效率的数学评判。
针对故障诊断规则获取问题,本文在所研究的论域空间MAWD降维模型、变精度粗糙集模型基础上,结合先进的连续属性IMDV-SOM启发式自动聚类模型、决策矩阵计算模型。本文将四个核心模型进行有机的统一和集成,提出了一种简称为MMS-VPRS(MAWD-MDV-SOM-Variable Precision Rough Set)的知识发现模型,并实现了程序化,为故障诊断规则的发现提供了精准、高效的规则获取途径。
本文以工程领域中的旋转机械故障诊断、注射成型质量控制、电子镇流器故障诊断等若干典型故障诊断问题为对象,开展MMS-VPRS知识发现模型的应用性研究,导出了若干有用的工程领域诊断规则。验证了MMS-VPRS知识发现模型的工程适用性。
为了研究故障诊断模型的更新问题,本文将MMS-VPRS知识发现模型探索性地应用到医学诊断领域,利用该模型对51例可疑冠心病患者的信息进行全面分析,得出了较理想的诊断规则。经临床验证,该诊断规则有较高的敏感性与特异性,可以为早期诊断冠心病提供一种新的途径。
Up to now, fault diagnosis system is still facing various problems such as the limitation of supporting theories, the difficulties in obtaining and renewing the rules, non-synchronization of renewing processes of the diagnostic models. Therefore in this paper, we use the rough set theory as basic supporting theory and put forward a knowledge finding model. This model is then applied to engineering and medical diagnostic areas respectively, to find some meaningful diagnostic knowledge.
To simplify the complexity of calculation on rough set theory, we bring forward a spatial-dimensions-reducing model named as mixed attribute whole distance (MAWD). This model is suitable for analysis of the data where both the continuous and discrete attributes are coexisted. We find that MAWD model can be used quantitatively for dealing with the complexity of calculation processes of rough set theory and improve the calculation efficiency of rough set theory.
To solve the problem of obtaining fault diagnosis rules, the MAWD model, the variable precision rough set (VPRS) model, the advanced continuous attribute IMDV-SOM heuristic automatic clustering model and the decision matrix calculation model were integrated in this paper and a new knowledge discovery model called MMS-VPRS (MAWD-MDV-SOM-Variable Precision Rough Set) was presented for the first time. This MMS-VPRS model was programmed to provide a concise, high efficiency way for the mining of fault diagnosis rules.
To validate the applicability of the MMS-VPRS knowledge discovery model in engineering, and to find out useful diagnosis rules for practical fault diagnosis, we took rotating mechanical devices fault diagnosis, injection molding quality control, and electron ballast fault diagnosis as practical application examples. All these application studies had a good result and some useful diagnostic rules in engineering fields are discovered.
For studying the updating of fault diagnosis models, the MMS-VPRS knowledge discovery model was introduced into medical diagnosis field. This model was used to analyze all-around clinical information in 51 patients suspected of having coronary heart disease. The obtained diagnostic results were well matched with that made by medical experts, with high sensitivity and specificity. Thus, this model could be helpful to diagnose coronary heart disease at its early stage.
In conclusion, this paper puts forward a spatial-dimensions-reducing model called MAWD, which was then combined with several other models to create MMS-VPRS, a new knowledge discovery model. The validity of MMS-VPRS model has been confirmed in engineering field and in medical diagnostic process.
引文
[1] Margaret H. Dunham. Data Mining Introductory and Advanced Topics. Pearson Education Asia Limited and Tsinghua University Press, 2003
[2] Zhou Zhi-hua. Three Perspectives of Data Mining. Artificial Intelligence, 2003, Vol.143(1): 139-146
[3] Kao S.-C., Chang H.-C., Lin C.-H. Decision support for the academic library acquisition budget allocation via circulation database mining. Information Processing & Management, 2003, Vol.39 (1): 133-147(15)
[4] Pawlak Z., Grzymala-Busse J., Slowinski R, et al. Rough sets. Communications of the ACM, 1995, Vol.38(11):89-95
[5] Pawlak Z. Rough sets. International Journal of Computer and Information Sciences, 1982, Vol.11(5):341-356
[6] Hu X. Knowledge Discovery in database: an attribute-oriented rough set approach. Canada: University of Regina, 1995
[7] 徐章遂,房立清,王希武.故障信息诊断原理及应用.北京:国防工业出版社,2000
[8] 虞和济,韩庆大,李沈等.设备故障诊断工程.北京:冶金工业出版社,2001
[9] Huang, Y. A new data mining approach to dissolved gas analysis of Oil-insulated power apparatus. IEEE Transactions on Power Delivery, 2003, 18:1257-1261
[10] 王晓垠.基于神经网络和专家系统的智能故障诊断系统研究[硕士学位论文].南京:东南大学,2007
[11] 虞和济.基于神经网络的智能诊断.北京:冶金工业出版社,2002
[12] Frank P M. Fault diagnosis in the dynamic systems using analytical and knowledge-based redundancy-a survey and some new results, Automatica, 1990, (26):459-474.
[13] Patton R J, Chen J. Review of Parity Space Approaches to Fault Diagnosis for Aerospace System. Journal of Guidance, Control and Dynamics, 1994, Vol. 17(2):278-285
[14] Ye H, Wang G.Z, Fang C Z. Application of wavelet transform to leak detection and location in transport pipelines. Engineering Simulation, 1996, (13): 1025-1032
[15] Iman I etc. Development of an on-line rotor crack detection and monitoring System. Journal of Vibration, Acoustics, Stress, and Reliability in Design, 1999, (111):241-250
[16] 王计生,黄惟公,喻俊馨.小波分析和神经网络技术在故障诊断中的应用.振动、测试与诊断,2004,Vol.24(1):46-49
[17] 敖志刚.人工智能与专家系统导论.合肥:中国科技大学出版社,2002
[18] 蔡自兴,约翰·德尔金,龚涛.高级专家系统:原理、设计及应用.北京:科学出版社,2005
[19] 王荣杰.基于知识的故障诊断方法的发展现状与展望.微计算机信息,2006,Vol.22(31):218-220
[20] LEE, Pui Shan, Dexter, Arthur L. A fuzzy approach to fault diagnosis in the presence of sensor bias. IEEE International Conference on Fuzzy Systems, 2002
[21] Michael P. S. Brown, William Noble Grundy, David Lin, et al. Knowledge-based analysis of microarray gene expression data by using support vector machines. PNAS, 2000, Vol.97(1):262-267
[22] 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:[博士学位论文].辽宁:东北大学,2006
[23] 陈真勇,何永勇,等.多Agent故障诊断原型系统研究.中国机械工程,2002,Vol.13(13):1084-1087
[24] 吴伟蔚,吴今培.基于智能Agent的故障诊断系统研究.模式识别与人工智能,2000,Vol.13(1):78-82
[25] Cios KJ, Teresinska A, Konieczna S, et al. A knowledge discovery approach to diagnosing myocardial perfusion. IEEE EMB Mag, 2000, Vol. 19(4): 17-25
[26] Jiawei Han, Micheline Kamber. Data mining: Concepts and techniques. Morgan Kaufmann Publishers, 2001
[27] 陈真诚,蒋勇,胥明玉,等.人工智能技术及其在医学诊断中的应用及发展.生物医学工程学杂志,2002,Vol.19(3):505-509
[28] E.H.Shortliffe, S.G.Axline, B.G.Buchanan et al An artificial intelligence program to advise of physicians regarding antimicrobial therapy. Compute Bimed Res, 1973, (6):544-560
[29] Miller R.A., People H.E., Myers J.D. Internist-I, an experimental computer-based diagnostic consultant for general internal medicine. N EngI J Med. 1982, Vol.307(8):468-476
[30] Barnett G.O., Hoffer E.P., Packer M.S. et al. DXPLAIN-demonstration and discussion of a diagnostic clinical decision support system. Proc Annul Syrup Compute Apply Med Care 1991, 878-885
[31] Umbangh S.E., Moss R.H., Stoecher W.V. Applying artificial intelligence to the identification of variegated coloring in skin tumors. IEEE Engineering in Medicine and Biology Magazine, 1991, Vol.10(4):57-62
[32] Provan G.M., Clarke J.R. Dynamic network construction and updating techniques for the diagnosis of acute abdominal pain. IEEE Trans on Pattern Analysis and Machine Intelligence. 1993, Vol. 15(3):299-306
[33] Edward R. Valstar, Charl P. Botha, et al. Towards computer-assisted surgery in shoulder joint replacement ISPRS. Journal of Photo grammetry and Remote Sensing, 2002, Vol.56(5-6):326-337
[34] Schep NW, Broeders IA, van der Werken C. Computer assisted orthopedic and trauma surgery: State of the art and future perspectives. Injury, 2003, Vol.34(4):299-306
[35] Sabur Malek, Roger Phillips, Am Mohsen, et al Validations of Computer-assisted Orthopaedic Surgical System for insertion of distal hocking screws for intramedullary nails [R]. International Congress Series, Volume June 2004,1268:614-619
[36] N.I.B imdorf, J.O. Pentecost, J.R. Coakley et al. An expert system to diagnose anemia and report results directly on hematology forms. Compute Biomed Res, 1996, Vol.29(1):16-26
[37] Robert S. Parker, et al. A Model Based Algorithm for Blood Glucose Control in Type Ⅰ Diabetic Patients. IEEE Transactions on Biomedical Engineering, 1999, Vol.46(2): 148-154
[38] Wells D.M., Walrath D., Craighead P.S. Improvement in tangential breast planning efficiency using a knowledge-based expert system. Med Dosim, 2000, Vol.25(3): 133-138.
[39] 熊武.医学诊断专家系统的发展现状及趋势分析.医疗设备信息,2006:Vol.21(4):27-28
[40] 白净,张永红著.远程医疗概论.北京:清华大学出版社,2000
[41] 程勇.医疗诊断专家系统的研究和应用.医疗设备信息,2005,Vol.20(12):33-35,51
[42] Pawlak Z.Rough sets and their applications. Microcomputer Applications, 1994, Vol. 13(2): 71-75
[43] 李德毅.不确定性人工智能.软件学报,2004,Vol.15(11):1583-1594
[44] 陈奇南.模糊集和粗糙集.计算机工程,2002,Vol.28(8):138-140
[45] 乔斌.粗糙集理论分层递阶约简算法的研究[博士学位论文].杭州:浙江大学,2003
[46] 杨善林.机器学习与智能决策支持系统.北京:科学出版社,2004
[47] Z.Pawlak. Rough logic. Bulletin of the Polish Academy of Sciences, Technical Sciences, 1987, Vol.35(5-6): 253-258
[48] M.Krynicki, A Note on Rough Concept Logic, Fundamenta Informaticae, 1990, (13) :227-245
[49] M Banerjee, M K Chakraborty, Rough sets through algebraic logic. Fundamenta Informaticae, 1996, Vol.3(4):211-221
[50] 陈湘晖.与特征选取和离散化集成的决策规则挖掘方法.系统工程理论与实践,2001,(11):1-7
[51] Jan Komorowski, Lech Polkowski, Andrzej Skowron, Rough Sets: ATutorial, http://www.folli.uva.nl/CD/1999/library/pdf/skowron.pdf
[52] Dubois D., Prade H. Rough Fuzzy Sets and Fuzzy Rough Sets. International Journal of General Systems, 1990, (17): 191-209
[53] 代建华.基于粗糙集的综合推理模型.浙江大学学报,2006,Vol.40(9):1526-1530
[54] J.F Peters, K. Ziaei, S.Ramanna. Approximate time, rough control: concepts and application to satellite attitude control. Proceedings of RSCTC'98 Warsaw, Poland, 1998, 491-498
[55] 王楠,律方成,刘云鹏,等.基于粗糙集理论与模糊Petri网络的油浸电力变压器综合故障诊断.中国电机工程学报,2003,Vol.23(12):127-132
[56] 王国胤.Rough集理论与知识获取.西安:交通大学出版社,2001
[57] 苗夺谦,胡桂荣.知识约简的一种启发式算法.计算机研究与发展,1999,Vol.36(6):681-684
[58] 石峰,娄臻亮,张永清.一种改进的粗糙集属性约简启发式算法.上海交通大学学报,2002,Vol.36(4):478-481
[59] 芦晓红,陈世权,吴今培.基于可辨识矩阵的启发式属性约简方法及其应用计算机工程,2003,Vol.29(1):56-59
[60] 代建华,李元香.一种基于粗糙集的决策系统属性约简算法.小型微型计算机系统,2003,Vol.24(3):523-526
[61] 刘业政,杨善林,马溪骏.粗糙集数据分析的计算方法.合肥:合肥工业大学学报,2002,Vol.25(2):161-166
[62] 陶志,许宝栋,汪定伟,等.基于遗传算法的粗糙集知识约简方法[J].系统工程 2003,Vol.21(4):116-122
[63] 杜金莲,迟忠先,翟巍.基于属性重要性的逐步约简算法.小型微型计算机系统,2003.Vol.24(6).976-978
[64] Czyzewski A. Speaker-Independent Recognition of Isolated Words Using Rough Sets. Information Sciences, 1998,104:3-14
[65] Pal, S.K., Mitra, P, Multispectral image segmentation using the rough-set-initialized EM algorithm. IEEE Transactions on Geoscience and Remote Sensing, 2002, Vol.40(11): 2495-2501
[66] Huang Y C. Fault section estimation in power systems using a novel decision support system. IEEE Transactions on Power Systems, 2002, 17(2): 439-444
[67] Ching-Lai Hor, Crossley P. & Dunand E Intelligent information retrieval and fault classification in distribution substations using a rough set approach, IEE Conference on Power System Management and Control, London, UK, 2002, 432-438
[68] 王晓晔,王正欧.正则化训练的神经网络与粗集理论相结合的股票时间序列数据挖掘技术.电子与信息学报,2004,26(4),625-631
[69] Mrozek A. Rough Sets and Dependency Analysis among Attributes in Computer Implementation of Expert,5 Inference Models.Int.J.Man-Machine Studies,1989,30:457-473
[70] Plonka L. Rule-Based Stabilization of the Inverted Pendulum. Computational Intelligence,995, Vol. 11 (2):348-356
[71] R Deja, Conflict Model with Negotiations. Institute of Computer Science Reports, Warsaw University of Technology, Warsaw, 1995
[72] J.W.Grzymala-Busse. LERS-A system for learning from examples based on rough sets.Intelligent Decision Support-Handbook of Applications and Advances of the Rough Sets Theory, Kluwer, 1992:3-8
[73] 安海忠.粗糙集知识发现的研究现状和展望.计算机测量与控制,2003,11(2)81-83
[74] 张文修,吴伟志,梁吉业等,.粗糙集理论与方法.北京:科学出版社,2001
[75] 赵荣泳.粗糙集理论及数字化工厂技术在企业生产DSS中的应用研究[博士学位论文].上海:同济大学,2005
[76] Skowron A. Extracting laws from decision tables: A rough set approach. Computational Intelligence,1995,(11):371-388
[77] 苗夺谦.Rou曲Set理论中连续属性的离散化方法.自动化学报,2001,Vol.27(3):296-302
[78] Slowinski R. Rough classification of HSV patients. Intelligent Decision Support. Kluwer:Roman Slowinski, 1992
[79] Hu X. H, Cercone N. Learning in relational databases: A rough set approach. Inter. J. of Computational Intelli-gence, 1995, Vol. 11 (2):323-338
[80] Lenareik A,Piasta Z. Discretizationof Condition Attributes Space. Intelligent Decision Support. Kluwer: Roman Slowinski, 1992, 373-389
[81] 李翠玲.粗糙集理论研究及其在虚拟装配系统中的应用[博士学位论文].上海:同济大学,2007
[82] 代建华,李元香,刘群.粗糙集理论中基于遗传算法的离散化方法.计算机工程与应用,2003,(8):13-14
[83] KOHONEN T.The self organizing map.Neurocomputing,1998,21:126.
[84] 彭玉华.小波变换与工程应用.北京:科学出版社,2002
[85] 杨建刚.旋转机械振动分析与工程应用.北京:中国电力出版社,2007
[86] 廖伯瑜.机械故障诊断基础.冶金工业出版社,2003
[87] 陈大禧,朱铁光.大型同转机械诊断现场使用技术.北京:机械工业出版社,2002
[88] 周洋,萧蕴诗,何斌,等.基于小波变换的机械振动故障诊断系统的研究.华东交通 大学学报,2006,Vol.23(4):105-107
[89] 郭小荟,马小平.基于粗糙集的故障诊断特征提取.计算机工程与应用,2007,43(1):221-224
[90] 高晓康.粗糙集理论在旋转机械实时故障诊断中的应用.制造业自动化.2006,Vol.28(12):23-26
[91] Murphey Y L, Masrur M A, Chen Z, et al. Model-based fault diagnosis in electric drives using machine learning, IEEE/ASME Transactions on Mechatronics 2006, Vol.11(3):290-303
[92] Viola J, Strefezza M, Restrepo J. Influence of the motor load inertia and torque in the fault diagnosis of rotors in induction machines. Latin America Transactions, IEEE (Revista IEEE America Latina), 2005, Vol.3(4):48-53
[93] 祁才君.数字信号处理技术的算法分析与应用.北京:机械工业出版社,2005
[94] 贺银芝,沈松,应怀樵.小波包分解及其能量谱在发动机连杆轴承故障诊断中的应用.振动工程学报,2001,Vol.14(1):72-75
[95] 冯象初,甘小冰,宋国乡.数值泛函与小波理论.西安:西安电子科技大学出版社,2003
[96] 牛志斌.数控磨床故障诊断与维修技巧.机械工业出版社,2005
[97] Geong Menges,Walter Michaeli,Paul Moheren.注射模具制造工程.北京:化学工业出版社,2003
[98] 张增红.塑料注射成型.北京:化学工业出版社,2005
[99] 王刚,单岩.Moldflow模具分析应用实例.北京:清华大学出版社,2005
[100] 蒋文胜,庞祖高,夏薇,等.基于神经网络和遗传算法的薄壳件注塑成型工艺参数优化.塑料制造,2007,(1):59-62
[101] Mok SL, Kwong CK, Lau WS. A hybrid neural network and genetic algorithm approach to the determination of initial process parameters for injection moulding. The International Journal of Advanced Manufacturing Technology, 2001, (18):404-409
[102] Prasad KDV Yaflagadda. Prediction of processing parameters for injection moulding by using a hybrid neural Network. Proceedings Institution Mechanical Engineers, 2001, (215):1465-1470
[103] 杨华.电子镇流器局部热点分析.佳木斯大学学报,2006,24(2):226-228
[104] Bhalodakar NC, Blum S, Rana T, et al. Comparison of levels of large and small high-density lipoprotein cholesterol in Asian Indian men compared with Caucasian men in the Framingham offspring study. Am J cardiol, 2004, (94):1561-1563
[105] Ortlepp JR, Schmitz F, Bozoglu T, et al. Cardiovascular risk factors in patients with aortic stenosis predict prevalence of coronary artery disease but not of aortic stenosis: an angiographic pair matched case-control study. Heart, 2003, (89): 1019-102
[106] Kato J, Aihara A, Kikuya M, et al. Risk factors and predictors of coronary arterial lesions in Japanese hypertensive patients. Hypertens Res, 2001, 24:3-11
[107] Washio M, Sasazuki S, Kodama H, et al. Role of hypertension, dyslipidemia and diabetes mellitus in the development of coronary atherosclerosis in Japan. Jpn Circ J, 2001,(65):731-737
[108] Nissen SE, Tuzcu EM, Schoenhagen P, et al. Statin therapy, LDL cholesterol, C-Reactive protein, and coronary artery disease. N Engl J Med, 2005, 352:29-38
[109] 邢燕,陈红,刘茹辉,等.冠心病危险因素与冠状动脉病变程度的相关性研究.中国医药导刊,2004.Vol.6(3):159-161
[110] Kasaoka S, Okuda F, Saton A, et al. Effect of coronary risk factors on coronary angiographic morphology in patients with ischemic heart disease. Jpn Circ J, 1997,61:390-395.
[111] 朱明军,王建忠,王永霞.冠心病检查指标的评价.中西医结合心脑血管病杂志,2007,Vol.5(2):139-141
[112] 陈清启,杨庭树,卢喜烈,等.心电图学.济南:山东科学技术出版社,2002
[113] 杜国庆.实用临床超声波心动图学.沈阳:辽宁科学技术出版社,2005
[114] Schillaci O, Danieli R, Marmi C, et al. Technetium-99m-labelled red blood cell imaging in the diagnosis of hepatic haemangiomas: the role of SPECT/CT with a hybrid camera. Eur J.Nucl Med Mol Imaging, 2004, Vol.31(7):1011-1015
[115] Li W, Qu WY, et al. Evaluation of using 99Tcm-MDP SPECT/CT for differentiating malignancy from benignancy in spine diseases. Chin J Nucl Meal,2002,22(6):343-345
[116] 姜云飞,范昭赋.关于智能诊断中模型的构建和应用.计算机科学,2006,Vol.33(2):193-196
[117] Chen QQ, Yang TS, Lu XL et al. Electrocardiographicology Sandong: Sandong Science and Technology Press, 2002
[118] Djalaly A, Hedayatti HA, Zeighami E. Screening capabilities of the lead I electrocardiogram. J Electrocardiol 1977, Vol.10(3):245-250
[119] 施仲伟.正常中年人心电图导联Ⅰ七项指标的统计分析.心电学杂志,1983,Vol.2(1):9-12
[120] Green M, Ohlsson M, Forberg JL, et al. Best leads in the standard electrocardiogram for theemergency detection of acute coronary syndrome. J Electrocardiol 2007, Vol.40(3):251-256
[121] Tragardh E, Engblom H, Pahlm O. How many ECG leads do we need? Cardiol Clin 2006,24(3):317-330
[122] Hoffman I. Clinical vectorcardiography in adults. Part 2. Am Heart J 1980, Vol.100(3):373-396
[123] Shen T, Tompkins W. Biometric Statistical Study of One-Lead ECG Features and Body Mass Index (BMI). Conf Proc IEEE Eng Med Biol Soc 2005,(2):1162-1165
[124] Ziarko W. Variable precision rough set model.Journal of Computer and System Sciences,1993, 39-59
[125] Sheu WHH, Jeng CY, Young MS, et al. Coronary artery disease risk predicted by insulin resistance, plasma lipids, and hypertension in people without diabetes. Am J Med Sci, 2000, 319(2):84-88
[126] Jeppesen J, Hein HO, Suadicani P, et al. Triglyceride concentration and ischemic heart disease: an eight-year follow-up in the Copenhagen male study. Circulation,1998, 97:1029-1036
[127] Takaishi H, Taniguchi T, Fujioka Y, et al. Impact of increasing diabetes on coronary artery disease in the past decade. J Atheroscler Thromb, 2004, 11:271-277
[128] Kato J, Aihara A, Kikuya M, et al. Risk factors and predictors of coronary arterial lesions in Japanese hypertensive patients. Hypertens Res, 2001, 24:3-11
[129] Aizawa Y, Watanabe H, Aizawa Y, et al. Excess accumulation of risk factors in ischemic heart disease. Jpn Heart J, 2004, 45:733-738
[130] Abbasi F, Brown BW Jr, Lamendola C, et al. Relation between obesity, insulin resistance, and coronary heart disease risk. J Am Colll Cardiol, 2002, 40:937-943
[131] Assmann G, Schulte H. The prospective cardiovascular Munster (PROCAM) Study: prevalence of hyperlipidemia in persons with hypertension and/or diabetes mellitus and the relationship to coronary heart disease. Am Heart J, 1998, 116:1713-1724
[132] Stamler J, Vaccaro O, Neaton JD, et al. Diabetes, other risk factors, and 12-yr cardiovascular mortality for man screened in the Multiple Risk Factor Intervention Trial. Diabetes Care, 1993,16:434-444