外文文獻(xiàn)及翻譯--應(yīng)用高階神經(jīng)網(wǎng)絡(luò)對旋轉(zhuǎn)機(jī)器的多種故障進(jìn)行診斷-免費(fèi)閱讀
【正文】 6(3): 205–211 5. MacIntyre J,Jennings monitoring software that thinks for MAINTEC 97 International Maintenance Conference,Birmingham,UK,1997 6. MacIntyre works in condition monitoring just another fad?Proc 5th International Conference on Profitable Condition Monitoring,Harrogate,UK,1996 7. Leonard JA,Kramer of the back propagation approach to fault diagnosis and improvement with basis Annual Meeting,Chicago, IL,1990 8. Kavuri SN,Venkatasubramanian bounded fault classes using neural works with ellipsoidal activation in Chemical Eng 1993。3(1),24–37 [13] Bishop Networks for Pattern Recognition,Oxford University Press,1995 High Order Neural Networks for Simultaneous Diagnosis of Multiple Faults in Rotating Machines B. Zhong39。這對于故障診斷的應(yīng)用是一個適當(dāng)?shù)倪x擇。 正確診斷的百分比是 %。然而，在條件監(jiān)測應(yīng)用中，用大量故障數(shù)據(jù)是極端罕見的。 在這網(wǎng)絡(luò)中每個輸入單位一起連接到每個隱藏的單位二個壓重 上。作為樣式分類的方法，標(biāo)準(zhǔn)多層前向反饋神經(jīng)網(wǎng)絡(luò)決策空間以超平面和決定地區(qū)，形成的總是無邊際的，可能導(dǎo)致不夠精確的推測。它是一個初始化方法為 hyperellipsoids 和標(biāo)準(zhǔn) BP 算法的訓(xùn)練算法，在這樣的網(wǎng)絡(luò)運(yùn)用一定概念和推測， 根據(jù)橢球狀單位網(wǎng)絡(luò) (HDANN)的等級制度診斷的人工神經(jīng)網(wǎng)絡(luò) ,在旋轉(zhuǎn)電機(jī)中常遇到多個缺點同時診斷的問題，包括幾個子網(wǎng)絡(luò)并且將一個大模式空間劃分成幾個更小的子空間時， 子網(wǎng)絡(luò)可以在各自子空間中訓(xùn)練，并且整體網(wǎng)絡(luò)是有能力對多個故障上同時進(jìn)行診斷。 最終，典型的故障數(shù)據(jù)從旋轉(zhuǎn)電 機(jī)中被網(wǎng)絡(luò)測試出來，研究結(jié)果表示， HDANN 可能得到更加準(zhǔn)確和更加高效率的診斷結(jié)果，并且這種實時條件監(jiān)測和對旋轉(zhuǎn)電機(jī)的診斷是有用的。雖然使用橢球狀單位要克服高位神經(jīng)網(wǎng)絡(luò)這個局限，但是對于故障診斷應(yīng)用方面是有用。 分別地 , 在 相應(yīng) 的尺寸上決定 了 橢圓體的主要軸的中心共縱線和長度 。這里用于應(yīng)付這個問題的方法是假設(shè)增加隨機(jī)噪聲的訓(xùn)練樣品，從而訓(xùn)練出比較精確的結(jié)果，并且使用這種方法， 200個小組樣本分為七個類型的故障來生成，訓(xùn)練和測試網(wǎng)絡(luò)結(jié)構(gòu)。 2．作為雙重斷層類型，最后的診斷結(jié)果 2。對于這樣的網(wǎng)絡(luò)，一個等級制度的診斷方法能同時為多個故障診斷是可實行的。 J. MacIntyre2, Y. He` and J. Tait2 Abstract: To overe the limitations of the standard feedforward neural works,highorder neural works( unit works),which are very useful for fault diagnosis applications due to their bounded generalisation and extrapolation,are paper describes the theory and structure of such method for initialising hyperellipsoids and a training algorithm based on the standard backpropagation algorithm are the properties of bounded generalisation and extrapolation inherent in such works,a Hierarchical Diagnostic Artificial Neural Network(HDANN)based on the ellipsoidal unit work is put forward with respect to simultaneous diagnosis of multiple faults on rotating machines,which consists of several subworks and aims at dividing a large pattern space into several smaller subworks can be trained in subspaces respectively and the whole work is capable of simultaneous diagnosis of multiple ,typical fault data from rotating machines are tested in the research results show that HDANN can obtain more accurate and efficient diagnostic results and is useful for realtime condition monitoring and online diagnosis of rotating machines. Keywords: Ellipsoidal unit works。17(2):139–163. 9. Kavuri SN,Venkatasubramanian fuzzy clustering with ellipsoidal units in n
畢業(yè)設(shè)計相關(guān)推薦
鄂ICP備17016276號-1