機(jī)械外文翻譯---機(jī)械狀態(tài)監(jiān)測(cè)和故障診斷的最新進(jìn)展

1、<p>　　Recent Progress on Mechanical Condition Monitoring and Fault diagnosis</p><p>　　Chenxing Sheng, Zhixiong Li, Li Qin, Zhiwei Guo, Yuelei Zhang</p><p>　　Reliability Engineering Institut

2、e, School of Energy and Power Engineering, Wuhan University of Technology, Wuhan 430063, P. R. China</p><p>　　Huangpi Campus, Air Force Radar Academy, Wuhan 430019, P. R. China</p><p><b>　

3、　Abstract</b></p><p>　　Mechanical equipments are widely used in various industrial applications. Generally working in severe conditions, mechanical equipments are subjected to progressive deterioration

4、 of their state. The mechanical failures account for more than 60% of breakdowns of the system. Therefore, the identification of impending mechanical fault is crucial to prevent the system from malfunction. This paper di

5、scusses the most recent progress in the mechanical condition monitoring and fault diagnosis. Excellent</p><p>　　© 2011 Published by Elsevier Ltd. Selection and/or peer-review under responsibility of [CE

6、IS 2011] </p><p>　　Keywords: Condition monitoring; Fault diagnosis; Vibration; Signal processing</p><p>　　1. Introduction </p><p>　　With the development of modern science and techno

7、logy, machinery and equipment functions are becoming more and more perfect, and the machinery structure becomes more large-scale, integrated, intelligent and complicated. As a result, the component number increases signi

8、ficantly and the precision requirement for the part mating is stricter. The possibility and category of the related component failures therefore increase greatly. Malignant accidents caused by component faults occur freq

9、uently all </p><p>　　Mechanical equipment fault diagnosis technology uses the measurements of the monitored machinery in operation and stationary to analyze and extract important characteristics to calibrate

10、 the states of the key components. By combining the history data, it can recognize the current conditions of the key components quantitatively, predicts the impending abnormalities and faults, and prognoses their future

11、condition trends. By doing so, the optimized maintenance strategies can be settled, and thus t</p><p>　　The contents of mechanical fault diagnosis contain four aspects, including fault mechanism research, si

12、gnal processing and feature extraction, fault reasoning research and equipment development for condition monitoring and fault diagnosis. In the past decades, there has been considerable work done in this general area by

13、many researchers. A concise review of the research in this area has been presented by [5, 6]. Some landmarks are discussed in this paper. The novel signal processing techniques </p><p>　　2. Fault Mechanism R

14、esearch </p><p>　　Fault Mechanism research is a very difficult and important basic project of fault diagnosis, same as the pathology research of medical. American scholar John Sohre, published a paper on &qu

15、ot;Causes and treatment of high-speed turbo machinery operating problems (failure)", in the United States Institute of Mechanical Engineering at the Petroleum Mechanical Engineering in 1968, and gave a clear and con

16、cise description of the typical symptoms and possible causes of mechanical failure. He suggested that</p><p>　　3. Advanced Signal Processing and Feature Extraction Methods </p><p>　　Advanced sig

17、nal processing technology is used to extract the features which are sensitive to specific fault by using various signal analysis techniques to process the measured signals. Condition information of the plants is containe

18、d in a wide range of signals, such as vibration, noise, temperature, pressure, strain, current, voltage, etc. The feature information of a certain fault can be acquired through signal analysis method, and then fault diag

19、nosis can be done correspondingly. To meet the s</p><p>　　Early research on vibration signal analysis is mainly focused on classical signal analysis which made a lot of research and application progress. Rot

20、ating mechanical vibration is usually of strong harmonic, its fault is also usually registered as changes in some harmonic components. Classical spectrum analysis based on Fourier transform (such as average time-domain t

21、echniques, spectrum analysis, cepstrum analysis and demodulation techniques) can extract the fault characteristic information effec</p><p>　　4. Research on Fault Reasoning</p><p>　　At present, m

22、any methods are adopted in the process of diagnostic reasoning. According to the subject systems which they belong to, the fault diagnosis can be divided into three categories: (1) the fault diagnosis based on control mo

23、del; (2) the fault diagnosis based on pattern recognition; (3) the fault diagnosis based on artificial intelligence. Among them, the fault diagnosis based on control model needs to establish model through theoretic or ex

24、perimental methods. The changes of system param</p><p>　　Pattern recognition conducts cluster description for a series of process or events. It is mainly divided into statistical method and language structur

25、e method. The fault diagnosis of equipments could be recognized as the pattern recognition process, that is to say, it recognizes the fault based on the extraction of fault characteristics. There are many common recognit

26、ion methods, including bayes category, distance function category, fuzzy diagnosis, fault tree analysis, grey theory diagnosis and</p><p>　　5. Research and Development of Fault Diagnosis Devices </p>

27、<p>　　Fault diagnosis technology ultimately comes down to the actual devices, and at present research and development of fault diagnosis devices is in the following two directions: (1) Portable vibration monitoring

28、and diagnosis (including data collector system), and (2) On-line condition monitoring and fault diagnosis system. Portable instrument is mainly adopted single-chip microcomputers to complete data acquisition, which has c

29、ertain ability for signal analysis and fault diagnosis. On-line monitor</p><p>　　Based on the realization of condition monitoring of equipments, network diagnostics center can monitor and diagnose the operat

30、ion of equipments at any time through the network to achieve the long distance information transmission. The remote monitoring system can also achieve the collaborative diagnosis of production equipments, multiple diagno

31、stic systems serve the same piece of equipment, and multiple devices share the same diagnostic system. </p><p>　　6. Conclusions </p><p>　　To achieve a dynamic system condition monitoring and fa

32、ult diagnosis, primary task is the need to get enough reliable characteristic information from the system. Due to the fluctuation of the system itself and the environment disturbance, reliable signal collection is seriou

33、sly affected. It is therefore very urgent for advanced signal processing technology to eliminate noise to get true signal. No matter classical or advance fault diagnosis techniques, they have achieved great progress in v

34、ariou</p><p>　　Acknowledgements </p><p>　　This project is sponsored by the grants from the National Natural Sciences Foundation of China </p><p>　　(NSFC) (No. 50975213). </p>

35、<p>　　References </p><p>　　[1] Wu XK. The fault diagnosis based on information fusion theory and its application in internal combustion engine. Ph.D. thesis, Wuhan University of Technology, 1998. <

36、;/p><p>　　[2] Chen YR. Modern signal processing technology in the application of vibration diagnosis of internal combustion engine.Ph.D. thesis, Wuhan University of Technology, 1998. </p><p>　　[3]

37、Qu LS, He ZJ. Mechanical fault diagnostics. Shanghai: Shanghai Science and Technology Press, 1986. </p><p>　　[4] Huang WH, Xia SB, Liu RY. Equipment fault diagnosis principle, technology and application. Bei

38、jing: Science Press, 1996. </p><p>　　[5] Jayaswalt P, Wadhwani AK. Application of artificial neural networks, fuzzy logic and wavelet transform in fault diagnosis via vibration signal analysis: A review. Aus

39、tralian Journal of Mechanical Engineering 2009; 7: 157-172. </p><p>　　[6] Daneshi-Far Z, Capolino GA, Henao H. Review of failures and condition monitoring in wind turbine generators. 19th International Conf

40、erence on Electrical Machines. Rome, Italy; 2010. </p><p>　　[7] Sohre JS. Trouble-shooting to stop vibration of centrifugal. Petrop Chem. Engineer 1968; 11: 22-23. </p><p>　　[8] Shiraki T. Mecha

41、nical vibration lectures. Zhengzhou: Zhengzhou Mechanical Institute; 1984. </p><p>　　[9] Bently DW. Forced subrotative speed dynamic action of rotating machinery. USA: ASME Publication, 74-pet-16. </p>

42、<p>　　[10] Gao JJ. Research on high speed turbine machinery vibration fault mechanism and diagnostic method. Ph.D. thesis, Xi'an Jiaotong University, 1993. </p><p>　　[11] Xu M, Zhang RL. Equipment

43、 fault diagnosis manual. Xi’an: Xi'an Jiaotong University Press, 1998. </p><p>　　[12] Chen YS, Tian JY, Jin ZW, Ding Q. Theory of nonlinear dynamics and applied techniques of solving irregular operation

44、of a large scale gas turbine in a comprehensive way. China Mechanical Engineering 1999; 10: 1063-68. </p><p>　　[13] Yang JG, Zhou YC. Internal combustion engine vibration monitoring and fault diagnosis. Dali

45、an: Dalian Maritime University Press, 1994. </p><p>　　[14] Wang Y, Gao JJ, Xia SB. The study of causes and features of faults in supporting system for rotary machinery. Journal of Harbin Institute of Techno

46、logy 1999; 31:104-6. </p><p>　　[15] Liu SY, Song XP, Wen BC. Catastrophe in fault developing process of rotor system. Journal of Northeastern University (Natural Science) 2004; 17:159-162. </p><p

47、>　　[16] Han J, Zhang RL. Rotating machinery fault mechanism and diagnostic technique. Beijing: China Machine Press, 1997. </p><p>　　[17] Chen AH. Research on some nonlinear fault phenomenon of rotating ma

48、chinery. Ph.D. thesis, Central South University of Technology, 1997. </p><p>　　[18]Zhang W, Zhang YX. Missile power system fault mechanism analysis and diagnosis technology. Xi’an: Northwest Industrial Univ

49、ersity press, 2006.</p><p>　　機(jī)械狀態(tài)監(jiān)測(cè)和故障診斷的最新進(jìn)展</p><p>　　Chenxing Sheng, Zhixiong Li, Li Qin, Zhiwei Guo, Yuelei Zhang</p><p>　　武漢理工大學(xué)，能源與動(dòng)力工程學(xué)院，可靠性工程研究所，中華人民共和國(guó)，武漢，430063</p>

50、<p>　　空軍雷達(dá)學(xué)院，黃陂校區(qū)，中華人民共和國(guó)，武漢，430019</p><p><b>　　摘要</b></p><p>　　機(jī)械設(shè)備被廣泛應(yīng)用于各種工業(yè)應(yīng)用。一般在惡劣條件下工作，機(jī)械設(shè)備的狀態(tài)會(huì)逐漸惡化。機(jī)械故障占超過(guò)60％的系統(tǒng)故障。因此，即將到來(lái)的機(jī)械故障的識(shí)別系統(tǒng)，是防止系統(tǒng)故障的關(guān)鍵。本文討論了在機(jī)械狀態(tài)監(jiān)測(cè)與故障診斷的最新進(jìn)展。從故障機(jī)

51、理研究，信號(hào)處理和特征提取，故障推理研究和設(shè)備開(kāi)發(fā)等方面進(jìn)行了出色的工作。概述了一些現(xiàn)有的信號(hào)處理和特征提取方法。對(duì)這些技術(shù)的優(yōu)點(diǎn)和缺點(diǎn)進(jìn)行了討論。研究結(jié)果表明，基于智能信息融合的機(jī)械故障診斷專家系統(tǒng)與自我學(xué)習(xí)和自我更新能力，是機(jī)械設(shè)備狀態(tài)監(jiān)測(cè)和故障診斷未來(lái)研究的發(fā)展方向。</p><p>　　©2011年由愛(ài)思唯爾公司出版。選擇（和/或）根據(jù)[2011年控制工程與信息科學(xué)會(huì)議]責(zé)任同行審查</p

52、><p>　　關(guān)鍵詞：狀態(tài)監(jiān)測(cè)，故障診斷，振動(dòng)，信號(hào)處理</p><p><b>　　1.介紹</b></p><p>　　隨著現(xiàn)代科學(xué)技術(shù)的發(fā)展，機(jī)械和設(shè)備的功能變得越來(lái)越完善，并且機(jī)械結(jié)構(gòu)變得更大型，集成，智能和復(fù)雜。因此，組件數(shù)量顯著增加，接合部件的精度要求也更加嚴(yán)格。相關(guān)組件故障的可能性和故障的種類因此也大大增加。組件故障所造成的惡性事故頻

53、繁發(fā)生在世界各地，甚至一個(gè)小的機(jī)械故障可能會(huì)導(dǎo)致嚴(yán)重的后果。因此，有效的早期故障檢測(cè)和診斷是機(jī)械正常運(yùn)轉(zhuǎn)的關(guān)鍵。雖然在機(jī)械設(shè)計(jì)過(guò)程和制造過(guò)程中已經(jīng)采用優(yōu)化技術(shù)來(lái)提高機(jī)械產(chǎn)品的質(zhì)量，由于現(xiàn)代設(shè)備的復(fù)雜性，機(jī)械故障仍然難以避免。狀態(tài)監(jiān)測(cè)和故障診斷，以先進(jìn)的科學(xué)技術(shù)為根本，作為一種有效的方式來(lái)預(yù)測(cè)潛在的故障和降低機(jī)器故障的成本。這就是所謂的出現(xiàn)在近三十年的機(jī)械設(shè)備故障診斷技術(shù) [1，2]。</p><p>　　機(jī)械設(shè)備

54、故障診斷技術(shù)使用監(jiān)控機(jī)械運(yùn)轉(zhuǎn)和固定分析和提取重要特征的測(cè)量值來(lái)校準(zhǔn)關(guān)鍵部件的狀態(tài)。通過(guò)結(jié)合歷史數(shù)據(jù)，它可以定量的識(shí)別在目前條件下的關(guān)鍵部件，預(yù)測(cè)即將發(fā)生的異常和故障，并且預(yù)測(cè)它們未來(lái)的發(fā)展趨勢(shì)。這樣做，最優(yōu)化維修策略可以被制定，因此，工業(yè)可以從狀態(tài)監(jiān)測(cè)中大大獲益。 [3，4]。</p><p>　　機(jī)械故障診斷的內(nèi)容包含四個(gè)方面，包括故障機(jī)理研究，信號(hào)處理和特征提取，故障推理研究，以及設(shè)備狀態(tài)監(jiān)測(cè)和故障診斷的開(kāi)發(fā)

55、。在過(guò)去的幾十年里，已經(jīng)有許多研究者在此領(lǐng)域做了大量的工作。在這一領(lǐng)域一個(gè)簡(jiǎn)明的研究評(píng)論已經(jīng)被提出 [5，6]。本文討論了一些里程碑式的觀點(diǎn)。介紹新型的信號(hào)處理技術(shù)。這些新的信號(hào)處理和特征提取方法的優(yōu)缺點(diǎn)，在這項(xiàng)工作中進(jìn)行了討論。然后，簡(jiǎn)要回顧了故障推理研究和診斷設(shè)備。最后，未來(lái)的研究課題中所描述的是下一代智能故障診斷和預(yù)測(cè)系統(tǒng)。</p><p><b>　　2.故障機(jī)理研究</b><

56、/p><p>　　故障機(jī)理的研究是故障診斷的一個(gè)非常艱難和重要的基礎(chǔ)工程，就像病理研究對(duì)于醫(yī)療相同。美國(guó)學(xué)者John·Sohre，于1968年在美國(guó)機(jī)械工程研究所石油機(jī)械工程發(fā)表了“高速渦輪機(jī)械操作問(wèn)題（失?。┑脑蚣疤幚怼币晃?，并對(duì)于典型的癥狀和可能引起機(jī)械故障的原因進(jìn)行了一個(gè)清晰、簡(jiǎn)明的描述。他建議，典型故障可分為9個(gè)類型和37種[7]。之后，在上世紀(jì)60年代至70年代期間Shiraki [8]在日本對(duì)

57、于故障機(jī)理的研究工作做了很大貢獻(xiàn)，并總結(jié)了豐富的現(xiàn)場(chǎng)故障排除經(jīng)驗(yàn)，以支持故障機(jī)制的理論。本特利內(nèi)華達(dá)公司也進(jìn)行了一系列實(shí)驗(yàn)研究轉(zhuǎn)子 - 軸承系統(tǒng)的故障機(jī)制 [9]。大量的相關(guān)工作在中國(guó)也已經(jīng)完成。Gao等人[10]研究了高速透平機(jī)械振動(dòng)故障機(jī)理，探討了振動(dòng)頻率和振動(dòng)發(fā)電之間的關(guān)系，并擬定了振動(dòng)故障原因，次同步、同步和超同步振動(dòng)的機(jī)制和識(shí)別功能表。根據(jù)表格他們提出，他們已經(jīng)將典型的故障分為10個(gè)類型和58種，并在機(jī)械設(shè)計(jì)與制造，安裝和維護(hù)

58、，操作及機(jī)器降解方面提供預(yù)防措施。 Xu等人[11]總結(jié)了旋轉(zhuǎn)機(jī)的常見(jiàn)故障。Chen等人[12]利用非線性動(dòng)力學(xué)理論來(lái)分析了發(fā)電機(jī)軸振動(dòng)問(wèn)題的關(guān)鍵。他們建立了發(fā)電機(jī)轉(zhuǎn)子</p><p>　　3.先進(jìn)的信號(hào)處理和特征提取方法</p><p>　　先進(jìn)的信號(hào)處理技術(shù)被用于提取的原因是靈敏，通過(guò)各種信號(hào)分析技術(shù)來(lái)處理測(cè)量信號(hào)到具體的故障。植物狀態(tài)信息中包含著廣泛的信號(hào)，如振動(dòng)，噪聲，溫度，壓力，

59、應(yīng)變，電流，電壓等?？梢酝ㄟ^(guò)信號(hào)分析方法獲得一定的故障特征信息，然后可以做出相應(yīng)的故障診斷。為了滿足故障診斷的特殊需要，故障特征提取和分析技術(shù)正在經(jīng)歷，從時(shí)間領(lǐng)域分析到傅里葉頻域分析，從線性平穩(wěn)信號(hào)分析到非線性非平穩(wěn)分析，從頻域分析到時(shí)頻分析的過(guò)程。</p><p>　　振動(dòng)信號(hào)分析的早期研究主要集中在傳統(tǒng)的信號(hào)分析，進(jìn)行了大量的研究和應(yīng)用進(jìn)展。旋轉(zhuǎn)機(jī)械振動(dòng)通常是強(qiáng)烈的諧波，其故障也通常注冊(cè)為一些諧波成分的變化。

60、傳統(tǒng)頻譜分析基于傅里葉變換（如平均時(shí)域技術(shù)，頻譜分析，倒頻譜分析和解調(diào)技術(shù)），可以有效提取故障特征信息，因此它被廣泛的用于動(dòng)力機(jī)械，尤其是在旋轉(zhuǎn)機(jī)械振動(dòng)監(jiān)測(cè)和故障診斷。在某種意義上說(shuō)，傳統(tǒng)的信號(hào)分析，仍然是機(jī)械振動(dòng)信號(hào)分析和故障特征提取的主要方法。然而，傳統(tǒng)的頻譜分析也有明顯的劣勢(shì)。傅立葉變換反映信號(hào)的整體統(tǒng)計(jì)特性，適用于平穩(wěn)信號(hào)分析。在現(xiàn)實(shí)中，從機(jī)械設(shè)備中的信號(hào)測(cè)量也是千變?nèi)f化的，非平穩(wěn)的，非高斯分布的和非線性隨機(jī)的。尤其是當(dāng)設(shè)備發(fā)生

61、故障，這種情況出現(xiàn)的更加突出。對(duì)于非平穩(wěn)信號(hào)，一些時(shí)頻細(xì)節(jié)不能在頻譜上反應(yīng)，并且它的頻率分辨率使用傅里葉變換是有限的。因此對(duì)于這些非線性的和非平穩(wěn)的信號(hào)需要提出新方法。來(lái)自于工程實(shí)踐的強(qiáng)勁需求，也有助于信號(hào)分析的快速發(fā)展。對(duì)于非平穩(wěn)信號(hào)和非線性信號(hào)分析的新方法不斷涌現(xiàn)，他們被很快應(yīng)用于機(jī)械故障診斷領(lǐng)域。信號(hào)分析的新方法主要包括時(shí)頻分析，小波分析，希爾伯特黃變換，獨(dú)立分量分析，先進(jìn)的統(tǒng)計(jì)分析，非線性信號(hào)分析等。</p>&l

62、t;p><b>　　4.故障推理研究</b></p><p>　　目前，許多方法在診斷推理過(guò)程中被采用。根據(jù)他們所屬的主體系統(tǒng)，故障診斷，可分為三類：（1）基于控制模型的故障診斷;（2）基于模式識(shí)別的故障診斷;（3）基于人工智能的故障診斷。其中，基于控制模型的故障診斷需要通過(guò)理論或?qū)嶒?yàn)方法建立模型。系統(tǒng)參數(shù)或系統(tǒng)狀態(tài)的變化可以直接反映設(shè)備的物理過(guò)程的變化，因此，它可以為故障診斷提供依據(jù)

63、。這項(xiàng)技術(shù)是指模型的建立，參數(shù)估計(jì)，狀態(tài)估計(jì)，應(yīng)用觀察員等。因?yàn)樗鬁?zhǔn)確的系統(tǒng)模型，這種方法對(duì)于實(shí)踐中的復(fù)雜設(shè)備在經(jīng)濟(jì)上是不可行的。</p><p>　　模式識(shí)別進(jìn)行集群描述為一系列的過(guò)程或事件。它主要分為統(tǒng)計(jì)方法和語(yǔ)言結(jié)構(gòu)的方法。設(shè)備的故障診斷，可以作為模式識(shí)別的過(guò)程被確認(rèn)，也就是說(shuō)，它承認(rèn)的故障，基于提取的故障特征。有許多共同的識(shí)別方法，包括貝葉斯分類，距離函數(shù)分類，模糊診斷，故障樹(shù)分析，灰色理論診斷等等。

64、近年來(lái)，一些新技術(shù)也已經(jīng)應(yīng)用到旋轉(zhuǎn)機(jī)械故障診斷的領(lǐng)域中，如模糊集與神經(jīng)網(wǎng)絡(luò)組合，基于隱馬爾可夫模型的動(dòng)態(tài)模式識(shí)別等。</p><p>　　5.故障診斷裝置的研究與發(fā)展</p><p>　　故障診斷技術(shù)最終發(fā)展成為故障診斷儀器，目前其研究和發(fā)展有兩個(gè)方面：一是便攜式震動(dòng)檢測(cè)和診斷（包括數(shù)據(jù)采集系統(tǒng)），二是在線環(huán)境監(jiān)控和故障診斷系統(tǒng)。便攜式儀器主要是可以完成數(shù)據(jù)獲取的單片機(jī)，當(dāng)然儀器本身具有數(shù)

65、據(jù)分析和診斷功能。在線檢測(cè)和診斷系統(tǒng)是一個(gè)由感應(yīng)器、數(shù)據(jù)采集、警報(bào)和互鎖保護(hù)和條件監(jiān)視組成的子系統(tǒng)，具有較強(qiáng)信號(hào)分析和診斷軟件。這些軟件主要是美國(guó)BENTLY公司開(kāi)發(fā)的3300, 3500 and DM2000系統(tǒng)，美國(guó)西屋公司開(kāi)發(fā)的PDS系統(tǒng)，ENTECK& IRD公司開(kāi)發(fā)的5911系統(tǒng)，日本三菱公司開(kāi)發(fā)的MHM系統(tǒng)，丹麥B&K公司開(kāi)發(fā)的3450指南針系統(tǒng)。中國(guó)也成功地開(kāi)發(fā)出大型在線故障診斷系統(tǒng)，主要用于蒸汽渦輪機(jī)等重

66、要設(shè)備。</p><p>　　由于采用了對(duì)設(shè)備運(yùn)行狀況的監(jiān)控手段，網(wǎng)絡(luò)診斷中心可以通過(guò)網(wǎng)絡(luò)傳輸信息，隨時(shí)完成對(duì)設(shè)備運(yùn)行的遠(yuǎn)程檢測(cè)和監(jiān)控，遠(yuǎn)程監(jiān)控系統(tǒng)還可以采集生產(chǎn)設(shè)備運(yùn)行狀況的診斷信息，多程檢測(cè)系統(tǒng)可以用來(lái)控制同一條生產(chǎn)線，所有檢測(cè)儀器可以共享診斷數(shù)據(jù)。</p><p><b>　　6.結(jié)論</b></p><p>　　要實(shí)現(xiàn)動(dòng)態(tài)系統(tǒng)監(jiān)控和故障

67、診斷，最主要的是系統(tǒng)能夠采集到可靠的特征信息，但是由于系統(tǒng)自身的波動(dòng)和設(shè)備本身的干擾信號(hào)信息經(jīng)常受到干擾，所以很重要的一點(diǎn)是要依靠先進(jìn)的數(shù)據(jù)處理技術(shù)排除噪音以保證數(shù)據(jù)的準(zhǔn)確性。不管是傳統(tǒng)的還是先進(jìn)的故障診斷技術(shù)在各種應(yīng)用中都已經(jīng)取得了很大進(jìn)步，按照信息系統(tǒng)的觀點(diǎn)，每項(xiàng)技術(shù)都是故障診斷的組成部分，所有部分的有效的融合是最好實(shí)現(xiàn)條件監(jiān)控和故障診斷的保障。因此故障機(jī)制研究、信號(hào)處理和特征采集、故障成因研究和設(shè)備發(fā)展將更加緊密地聯(lián)系在一起，才能

68、在將來(lái)實(shí)現(xiàn)故障診斷專家系統(tǒng)。實(shí)現(xiàn)專家診斷系統(tǒng)的核心是突破知識(shí)獲取的瓶頸，用可靠的方式升級(jí)數(shù)據(jù)模型，提供專家系統(tǒng)的普及能力。</p><p>　　只有這樣，故障診斷專家系統(tǒng)才能對(duì)潛在異常提供準(zhǔn)確的評(píng)估，防止事故的發(fā)生，確保機(jī)械設(shè)備的正常運(yùn)行，將由于設(shè)備故障造成的損失降低到最小程度。</p><p><b>　　致謝    </b>