【溫馨提示】====【1】設(shè)計(jì)包含CAD圖紙 和 DOC文檔，均可以在線預(yù)覽，所見即所得，，dwg后綴的文件為CAD圖，超高清，可編輯，無(wú)任何水印，，充值下載得到【資源目錄】里展示的所有文件======【2】若題目上備注三維，則表示文件里包含三維源文件，由于三維組成零件數(shù)量較多，為保證預(yù)覽的簡(jiǎn)潔性，店家將三維文件夾進(jìn)行了打包。三維預(yù)覽圖，均為店主電腦打開軟件進(jìn)行截圖的，保證能夠打開，下載后解壓即可。======【3】特價(jià)促銷，，拼團(tuán)購(gòu)買，，均有不同程度的打折優(yōu)惠，，詳情可咨詢QQ：1304139763 或者 414951605======【4】 題目最后的備注【YC系列】為店主整理分類的代號(hào)，與課題內(nèi)容無(wú)關(guān)，請(qǐng)忽視
無(wú)級(jí)變速自行車設(shè)計(jì)
1 前言
自行車的誕生與發(fā)展已有幾百年了，在自行車的發(fā)展歷程中自行車的結(jié)構(gòu)有過(guò)幾次重大的變化，這些變化使自行車的設(shè)計(jì)發(fā)展中出現(xiàn)過(guò)“山窮水復(fù)疑無(wú)路，柳暗花明又一村”。每一次重大的變化都是自行車的設(shè)計(jì)思想上的一個(gè)大的突破，每一次大的變化都使自行車的發(fā)展進(jìn)入了一個(gè)新時(shí)代。
1791年，法國(guó)人西弗拉克發(fā)明了最原始的自行車。它只有兩個(gè)輪子而沒(méi)有傳動(dòng)裝置，人騎在上面，需用兩腳蹬地驅(qū)車向前滾動(dòng)。近些年來(lái)，我國(guó)機(jī)械工業(yè)有了很大的發(fā)展，這給今后機(jī)床夾具的發(fā)展提出了更高的要求。
2 機(jī)械無(wú)級(jí)變速器的發(fā)展概況
無(wú)級(jí)變速器分為機(jī)械無(wú)級(jí)變速器，液壓傳動(dòng)無(wú)級(jí)變速器，電力傳動(dòng)無(wú)級(jí)變速器三種，但本設(shè)計(jì)任務(wù)要求把無(wú)級(jí)變速器安裝在自行車上，所以一般只能用機(jī)械無(wú)級(jí)變速器，所以以下重點(diǎn)介紹機(jī)械無(wú)級(jí)變速器。
機(jī)械無(wú)級(jí)變速器最初是在19世紀(jì)90年代出現(xiàn)的，至20世紀(jì)30年代以后才開始發(fā)展，但當(dāng)時(shí)由于受材質(zhì)與工藝方面的條件限制，進(jìn)展緩慢。直到20世紀(jì)50年代，尤其是70年代以后，一方面隨著先進(jìn)的冶煉和熱處理技術(shù)，精密加工和數(shù)控機(jī)床以及牽引傳動(dòng)理論與油品的出現(xiàn)和發(fā)展，解決了研制和生產(chǎn)無(wú)級(jí)變速器的限制因素；另一方面，隨著生產(chǎn)工藝流程實(shí)現(xiàn)機(jī)械化、自動(dòng)化以及機(jī)械要改進(jìn)工作性能，都需要大量采用無(wú)級(jí)變速器。因此在這種形式下，機(jī)械無(wú)級(jí)變速器獲得迅速和廣泛的發(fā)展。主要研制和生產(chǎn)的國(guó)家有美國(guó)、日本、德國(guó)、意大利和俄國(guó)等。產(chǎn)品有摩擦式、鏈?zhǔn)?、帶式和脈動(dòng)式四大類約三十多種結(jié)構(gòu)形式。
國(guó)內(nèi)無(wú)級(jí)變速器是在20世紀(jì)60年代前后起步的，當(dāng)時(shí)主要是作為專業(yè)機(jī)械配套零部件，由于專業(yè)機(jī)械廠進(jìn)行仿制和生產(chǎn)，例如用于紡織機(jī)械的齒鏈?zhǔn)?，化工機(jī)械的多盤式以及切削機(jī)床的Kopp型無(wú)級(jí)變速器等，但品種規(guī)格不多，產(chǎn)量不大，年產(chǎn)量?jī)H數(shù)千臺(tái)。直到80年代中期以后，隨著國(guó)外先進(jìn)設(shè)備的大量引進(jìn)，工業(yè)生產(chǎn)現(xiàn)代化及自動(dòng)流水線的迅速發(fā)展，對(duì)各種類型機(jī)械無(wú)級(jí)變速器的需求大幅度增加，專業(yè)廠才開始建立并進(jìn)行規(guī)?；a(chǎn)，一些高等院校也開展了該領(lǐng)域的研究工作。經(jīng)過(guò)十幾年的發(fā)展，國(guó)外現(xiàn)有的幾種主要類型結(jié)構(gòu)的無(wú)級(jí)變速器，在國(guó)內(nèi)皆有相應(yīng)的專業(yè)生產(chǎn)廠及系列產(chǎn)品，年產(chǎn)量約10萬(wàn)臺(tái)左右，初步滿足了生產(chǎn)發(fā)展的需要。與此同時(shí)，無(wú)級(jí)變速器專業(yè)協(xié)會(huì)、行業(yè)協(xié)會(huì)及情報(bào)網(wǎng)等組織相繼建立。定期出版網(wǎng)訊及召開學(xué)術(shù)信息會(huì)議進(jìn)行交流。
3 無(wú)級(jí)變速自行車研究現(xiàn)狀
自行車發(fā)展到現(xiàn)在已經(jīng)有傳統(tǒng)的自行車演變成無(wú)級(jí)變速自行車，現(xiàn)代的無(wú)級(jí)變速自行車可謂是形式多樣，五花八門，以下是當(dāng)今社會(huì)上存在的部分無(wú)級(jí)變速自行車。
1、低座無(wú)級(jí)變速自行車
由低矮形車架把一個(gè)作驅(qū)動(dòng)的前輪和一個(gè)作導(dǎo)向的后輪連接在一塊的自行車，帶靠背的座椅安裝在車架中部，騎行者可斜躺著坐在座椅上，兩腿放在前輪二側(cè)。杠桿式曲柄無(wú)級(jí)傳動(dòng)裝置固定在前輪的前上方，通過(guò)左右曲柄桿上的滑塊鉸接鏈條交替?zhèn)鲃?dòng)前輪。操縱把手裝于前輪的正上方，由鋼絲繩牽引后輪轉(zhuǎn)向。這樣就不會(huì)干擾車子的方向操縱。
2、人力腳踏式無(wú)級(jí)變速自行車
一種人力腳踏式無(wú)級(jí)變速自行車，在自行車車架兩側(cè)面的中軸上，安裝有錐面相對(duì)的變速輪盤組成的主動(dòng)輪，主動(dòng)輪兩側(cè)安裝有腳蹬兩變速輪盤輪沿掛有三角皮帶，兩盤面間安裝有壓縮彈簧；在車架的前斜梁上，安裝有由變速桿操縱可前后移動(dòng)的挺桿，挺桿的近變速輪盤端安裝有可使兩變速輪盤靠近或分離的插件；在自行車后軸上的后輪輪輻兩側(cè)面支承有附輪；車架后斜梁上在三角皮帶上方安裝有可推壓三角皮帶張緊的張緊輪。自行車的行走和變速不用成組鏈輪和鏈條傳動(dòng)，成本低、重量輕，可實(shí)現(xiàn)無(wú)級(jí)變速，速度轉(zhuǎn)換快，速比大。
3、帶傳動(dòng)無(wú)級(jí)變速自行車
一種無(wú)級(jí)變速自行車，改進(jìn)了現(xiàn)有自行車的動(dòng)力傳動(dòng)機(jī)構(gòu)。該自行車的動(dòng)力傳動(dòng)機(jī)構(gòu)包括以下部件：小動(dòng)輪、小定輪等構(gòu)成。其特征在于自行車的動(dòng)力傳動(dòng)機(jī)構(gòu)包括以下部件：小動(dòng)輪、小定輪等，與自行車后軸上的飛輪軸套固定連接，小動(dòng)輪在撥叉控制下沿軸滑動(dòng)；大動(dòng)輪、大定輪、大動(dòng)輪撥叉，大動(dòng)輪、大定輪也呈錐形，兩輪大小形狀一致，錐面相對(duì)，組成帶有Ｖ形溝槽的大傳動(dòng)輪，固定在自行車中軸上，大動(dòng)輪在撥叉控制下沿軸滑動(dòng)；Ｖ型傳動(dòng)帶鑲在大小輪的溝槽中；Ｖ型帶張緊裝置裝在后軸上，其支承輪支撐傳動(dòng)帶；調(diào)速器裝在車把附近，與閘線連接，閘線帶動(dòng)調(diào)節(jié)大小動(dòng)輪位置的撥叉。 這種無(wú)級(jí)變速自行車通過(guò)帶傳動(dòng)來(lái)實(shí)現(xiàn)自行車的無(wú)級(jí)變速，傳動(dòng)平穩(wěn)、噪音低、調(diào)速操作方便、變速范圍大；同時(shí)該無(wú)級(jí)變速自行車的結(jié)構(gòu)簡(jiǎn)單、易于加工，可以實(shí)現(xiàn)大規(guī)模成批生產(chǎn)。
4、前置往復(fù)式無(wú)級(jí)變速自行車
針對(duì)自行車的驅(qū)動(dòng)、乘座和避震進(jìn)行改進(jìn)。包括：乘騎者坐靠休閑式椅，兩腳蹬踏前置的兩個(gè)懸搖桿曲柄，可進(jìn)行弧形的曲線往復(fù)運(yùn)動(dòng)，用腳掌面的蹬踏角度或用手直接調(diào)動(dòng)搖桿上力臂的長(zhǎng)短實(shí)現(xiàn)無(wú)級(jí)變速，高效能的帶動(dòng)撓性件驅(qū)動(dòng)后輪；還包括裝卸方便且不互換的休閑式座椅和防落物防盜的可帶走座椅；簡(jiǎn)化的全避震使乘坐舒適并使貨架攜帶的物品減小了顛簸
5、純滾動(dòng)式四個(gè)檔位無(wú)級(jí)變速自行車
一種純滾動(dòng)式四個(gè)檔位無(wú)級(jí)變速自行車，其中在中軸上的中心齒輪嚙合連接有一級(jí)行星輪和二級(jí)行星輪，中心齒輪的兩側(cè)分別套裝有推動(dòng)盤，一側(cè)固定在腳蹬輪軸上，另一側(cè)固定在鏈輪上；二級(jí)行星輪和中心齒輪為棘輪總成與鏈輪嚙合連接，在中軸和后軸的車架體上固定有座盤，座盤上固定有升降檔位彈簧。隨時(shí)變?cè)鰷p速檔位，對(duì)自行車零部件無(wú)影響，制造簡(jiǎn)單，性能可靠，操作簡(jiǎn)單，使用方便。
6、無(wú)鏈無(wú)級(jí)變速自行車
一種無(wú)鏈條傳動(dòng)，可隨意變換車速的自行車。該自行車包括車輪、把手、三角架和踏拐等，橫梁左端設(shè)有后齒輪、大齒輪和正反齒輪，橫梁右端設(shè)有中軸齒輪，齒輪與拐軸齒輪嚙合，偏心連桿的上端和杠桿的右端同軸裝在定位槽板的滑槽中，杠桿的左端與齒條連接，齒條與正反齒輪嚙合，橫梁上方設(shè)有拉簧、活動(dòng)支架和鋼絲拉索。該自行車結(jié)構(gòu)簡(jiǎn)單，調(diào)速方便靈活，經(jīng)久耐用，適合各種型號(hào)。
7、蓄能型-全自動(dòng)無(wú)級(jí)變速自行車
一種蓄能型一全自動(dòng)無(wú)級(jí)變速自行車，屬于交通工具技術(shù)領(lǐng)域。本實(shí)用新型的目的通過(guò)如下技術(shù)方案實(shí)現(xiàn)：主要由設(shè)置每側(cè)腳蹬上的長(zhǎng)型齒盤交替工作，通過(guò)同側(cè)的鏈條傳動(dòng)同側(cè)的飛輪，飛輪連同帶動(dòng)設(shè)置在輪骨內(nèi)的發(fā)條內(nèi)端發(fā)條外端同輪骨固定。騎行時(shí)由于每側(cè)長(zhǎng)型齒盤的作用，通過(guò)鏈條對(duì)同側(cè)的發(fā)條交替蓄能，從而實(shí)現(xiàn)全自動(dòng)無(wú)級(jí)變速。本實(shí)用新型是現(xiàn)代變速自行車的換代產(chǎn)品。
8、便攜式高安全型無(wú)級(jí)變速自行車
一種新式樣的自行車。其特征是由行走機(jī)構(gòu)，車椅式直立車龍頭轉(zhuǎn)向機(jī)構(gòu)，杠桿式無(wú)級(jí)變速驅(qū)動(dòng)機(jī)構(gòu)。本裝置是由足踏杠桿式無(wú)級(jí)變速機(jī)構(gòu)，車架可橫向折疊，驅(qū)動(dòng)大車輪在前面，導(dǎo)向小車輪在后邊的行走機(jī)構(gòu)與帶靠背車坐椅式的直立車龍頭轉(zhuǎn)向機(jī)構(gòu)組成的自行車裝置。該裝置形體式樣，較為奇特但騎行舒適，更安全，并能折疊便攜帶。
4 無(wú)級(jí)變速自行車的研究意義及實(shí)用價(jià)值
改進(jìn)現(xiàn)有齒輪式有級(jí)變速自行車不足。
1、換擋問(wèn)題。一般變速自行車為前后輪雙齒輪組，以滿足更多種變速比。這種方式需要車主熟悉掌握變速的檔位數(shù)以搭配獲得最佳效果。無(wú)級(jí)變速自行車能夠?qū)崿F(xiàn)傳動(dòng)比的連續(xù)改變，免去記憶復(fù)雜的前后輪檔位搭配，增加了易用性。
2、重心問(wèn)題。普通變速自行車的變速齒輪集中在一側(cè)，造成重心偏移。易倒。無(wú)級(jí)變速采用后輪2個(gè)并排，中間放置變速器，重心居中，便于轉(zhuǎn)彎操控。
3、鏈條問(wèn)題。傳統(tǒng)變速自行車存在鏈條在齒輪組空隙中調(diào)整時(shí)易掉鏈的問(wèn)題。無(wú)級(jí)變速自行車采取金屬帶式無(wú)級(jí)變速方式，錐形金屬帶夾在兩個(gè)錐形輪之間，不易掉鏈。而且金屬帶以及錐形輪盤較普通齒輪鏈條性能更加優(yōu)異。減小了保養(yǎng)難度。
4、維修問(wèn)題。普通變速自行車因構(gòu)建過(guò)多，增加了維修難度，而無(wú)級(jí)變速自行車零件簡(jiǎn)單，維修難度低，
5、舒適度問(wèn)題?，F(xiàn)有變速自行車最多擁有前7后9共63種檔位，但其跳躍性檔位設(shè)置有可能仍然使某些人找不到適于自己的傳動(dòng)比。無(wú)級(jí)變速自行車可以滿足各種人的不同需要。
6、轉(zhuǎn)彎問(wèn)題。采取前輪小后輪大的設(shè)計(jì)方式，增加了轉(zhuǎn)彎的靈活性。由于主要構(gòu)件集中于后輪，重心靠后，可以減小前輪小容易前翻的問(wèn)題。
7、上坡問(wèn)題。普通變速自行車由于前后輪同時(shí)放置變速器，重心較無(wú)級(jí)變速自行車靠前。上坡難度比后置無(wú)級(jí)變速自行車大。
8、使用價(jià)值?？梢杂行Ы档统杀荆b配難度，維修難度，生產(chǎn)難度都有所降低，適于普通家居生活。
9、操作難度降低，適用于中國(guó)最早一代使用自行車卻正在慢慢老去的群體。只需轉(zhuǎn)動(dòng)旋鈕即可實(shí)現(xiàn)變速。
10、外觀新穎時(shí)尚
3 結(jié)束語(yǔ)
綜上，機(jī)械工業(yè)是國(guó)民經(jīng)濟(jì)的支柱產(chǎn)業(yè)，現(xiàn)代機(jī)械制造技術(shù)是機(jī)械工業(yè)賴以生存和發(fā)展的重要保證。自行車隨著科技的發(fā)展使計(jì)算機(jī)技術(shù)、數(shù)控技術(shù)、控制論及系統(tǒng)工程與制造技術(shù)結(jié)合為制造系統(tǒng)，形成現(xiàn)代制造工程學(xué)。在機(jī)械制造中，可能會(huì)使用很多先進(jìn)的鑄造技術(shù)，這些制造技術(shù)可以提高勞動(dòng)生產(chǎn)率，提高加工精度，減少?gòu)U品，可以擴(kuò)大工藝范圍，改善操作者的勞動(dòng)條件。因此，機(jī)械制造的一項(xiàng)重要工藝設(shè)備，這也給今后無(wú)極變速技術(shù)的發(fā)展提出了更高的要求。
參考文獻(xiàn)
[1]濮良貴,紀(jì)名剛、機(jī)械設(shè)計(jì)[M]、第八版、西安:高等教育出版社, 2005、
[2]孫恒,陳作模、機(jī)械原理[M]、第六版、西安:高等教育出版社, 2000、
[3]徐灝、機(jī)械設(shè)計(jì)手冊(cè)[M]、第三卷、北京:機(jī)械工業(yè)出版社, 1991、
[4]吳宗澤,羅圣國(guó)、機(jī)械設(shè)計(jì)課程設(shè)計(jì)手冊(cè)[M]、第三版、北京:高等教育出版社, 2006、
[5]周良德,朱泗芳、現(xiàn)代工程圖學(xué)[M]、湘潭:湖南科學(xué)技術(shù)出版社, 2000、
[6]周有強(qiáng)、機(jī)械無(wú)級(jí)變速器[M]、成都:機(jī)械工業(yè)出版社, 2001、
[7]李新,洪泉,王艷梅、國(guó)內(nèi)外通用標(biāo)準(zhǔn)件手冊(cè)[M]、南京:江蘇科技出版,鳳凰出版?zhèn)髅郊瘓F(tuán), 2006、
[8]葛志淇、機(jī)械零件設(shè)計(jì)手冊(cè)[M]、天津:冶金工業(yè)出版社,1980
5
附錄1 翻譯原文及譯文
Doc No: P0193-GP-01-1
Doc Name: Analysis of Manufacturing
Process Data Using
QUICK TechnologyTM
Issue： 1
Data： 20 April ，2006
Name(Print)
Signature
Author：
D.Clifton
Reviewer：
S.Turner
22
Table of Contents
1 Executive Summary 4
1.1 Introdution 4
1.2 Techniques Employed 4
1.3 Summary of Results 4
1.4 Observations 4
2 Introdution 6
2.1 Oxford BioSignals Limited 6
3 External References 7
4 Glossary 7
5 Data Description 8
5.1 Data types 8
5.2 Prior Experiment Knowledge 8
5.3 Test Description 8
6 Pre-processing 10
6.1 Removal of Start/Stop Transients 10
6.2 Removal of Power Supply Signal 10
6.3 Frequency Transformation 10
7 Analysis I-Visualisation 13
7.1 Visualisation of High-Dimensional Data 13
7.2 Visualising 5-D Manufacturing Process Data 13
7.3 Automatic Novelty Detection 15
7.4 Conclusion of Analysis I-Visualisation 16
8 Analysis II-Signature Analysis 17
8.1 Constructing Signatures 17
8.2 Visualising Signatures 19
8.3 Conclusion of Analysis II-Signature Analysis 23
9 Analysis III-Template Analysis 24
9.1 Constructing a Template of Normality 24
9.2 Results of Novelty Detection Using Template Analysis 25
9.3 Conclusion of Analysis III-Template Analysis 26
10 Analysis IV-None-linear Prediction 27
10.1 Neural Networks for On-Line Prediction 27
10.2 Results of Novelty Detection using Non-linear Prediction 27
10.3 Conclusion of Analysis IV-Non-linear Prediction 28
11 Overall Conclusion 29
11.1 Methodology 29
11.2 Summary of Tesults 29
11.3 Future Work 29
12 Appendix A-NeuroScale Visualisations 31
Table of Figures
Figure 1- Test 90. From top to bottom: Ax, Ay, Az, AE, SP against time t(s)
Figure 2- Power spectra for Test 19 after removal of 50Hz power supply contribution. The top plot shows a 3-D “l(fā)andspace” plot of each spectrum. The bottom plot shows a “contour” plot of the same information, with increasing signal power shown as increasing colour from black to red
Figure 3- Power spectra for Test 19 after removal of all spectral components beneath power threshold
Figure 4- Az against time (in seconds) for Test 19,before removal of low-power frequency components
Figure 5- Az against time (in seconds) for Test 19, after removal of low-power frequency components
Figure 6- SP for an example test, showing three automatically-detecrmined states:S1-drilling in (shown in green); S2-drill-bit break-through and removal (shown in red); S3-retraction (shown in blue)
Figure 7- Example signature of variable plotted against operating-point
Figure 8- Power spectra for test 51, frequency (Hz) on the x-axis between [0 fs/2]
Figure 9- Average significant frequency
Figure 10- Visualisation of AE signatures for all tests
Figure 11- Visualisation of Ax broadband signatures for all tests
Figure 12- Visualisation of Ax average-frequency signatures for all tests
Figure 13- Novelty detection using a template signature
Figure 14-
1 Executive Summary
1.1 Introduction
The purpose of this investigation conducted by Oxford BioSignals was to examine and determine the suitability of its techniques in analyzing data from an example manufacturing process. This report has been submitted to Rolls-Royce for the expressed of assessing Oxford BioSignals’ techniques with respect to monitoring the example process.
The analysis conducted by Oxford BioSignals (OBS) was limited to a fixed timescale, a fixed set of challenge data for a single process (as provided by Rolls-Royce and Aachen university of Technology), with no prior domain knowledge, nor information of system failure .
1.2 Techniques Employed
OBS used a number of analysis techniques given the limited timescales:
I-Visualisation, and Cluster Analysis
This powerful method allowed the evolution of the system state (fusing all available data types) to be visualised throughout the series of tests. This showed several distinct modes of operation during the series, highlighting major events observed within the data, later correlated with actual changes to the system’s operation by domain experts.
Cluster analysis automatically detects which of these events may be considered to be “abnormal”, with respect to previously observed system behavior .
II-Signature represents each test as a single point on a plot, allowing changes between tests to be easily identified. Abnormal tests are shown as outlying points, with normal tests forming a cluster.
Modeling the normal behavior of several features selected from the provided data, this method showed that advance warning of system failure could be automatically detected using these features, as well as highlighting significant events within the life of the system.
III-Template Analysis
This method allows instantaneous sample-by –sample novelty detection, suitable for on-line implementation.
Using a complementary approach to Signature Analysis, this method also models normal system behavior. Results confirmed the observation made using previous methods.
IV-Neural network Predictor
Similarly useful for on-line analysis, this method uses an automated predictor of system behaviour(a neural network predictor), in which previously identified events were confirmed, and further significant episodes were detected.
1.3 Summary of Results
Early warning of system failure was independently identified by the various analysis methods employed.
Several significant events during the life of the process were correlated with actual known events later revealed by system experts.
Changes in sensor configurations are identified, and periods of system stability (in which tests are similar to one another) are highlighted.
This report shall be used as the basis for further correlation of detected events against actual occurrences within the life of the system, to be performed by Aachen University of Technology.
1.4 Observations
Based on this limited study, OBS are confident that their techniques are applicable to condition monitoring of the example manufacturing process as follows:
Evidence shows that automated detection of system novelty is possible, compared to its “normal” operation.
Early warning of system distress may be provided, giving adequate time to take preventative maintenance actions such that system failure may be avoided.
Provision “fleet-wide” analysis is possible using the techniques considered within this investigation.
The involvement of domain knowledge from system experts alongside OBS engineers will be crucial in developing future implementations. While this “blind” analysis showed that OBS modelling techniques are appropriate for process monitoring, it is the coupling of domain knowledge with OBS modelling techniques that may provide optimal diagnostic and prognostic analysis.
2 Introduction
2.1 Oxford BioSignals Limited
This document reports on the initial analysis conducted by Oxford BioSignals of manufacturing process challenge data provided by Rolls-Royce, in conjunction with Aachen University of Technology(AUT).
Oxford BioSignals Limited(OBS) is a world-class provider of Acquisition, Data Fusion, Neural Networks and other Advanced Signal Processing techniques and solutions branded under the collective name QUICK Technology. This technology not only provides for health and quality assurance monitoring of the operational performance of equipment and plant.
QUICK Technology has been extensively proven in the field of gas turbine monitoring with both on-line and off-line implementations at multiple levels: as a research tool, a test bed system, a ground support tool, an on-board monitoring system, an off-line analysis tool and a “fleet” manager.
Many of the techniques employed by OBS may be described as novelty detection methods. This approach has a significant advantage over many traditional classification techniques in that it is not necessary to provide fault data to the system during development. Instead, providing a sufficiently comprehensive model of the condition can be identified automatically. As information is discovered regarding the causes of these deviations it is then possible to move from novelty detection to diagnosis, but the ability to identify previously unseen abnormalities is retained at all stages.
3 External References
Accompanying documentation providing further information on the data sets is available in unnumbered documents.
4 Glossary
AUT- Aachen University of Technology
GMM- Gaussian Mixture Model
MLP- Multi-Layer Perception
OBS- Oxford BioSignals Ltd.
5 Data Description
The following sections give a brief overview of the data set obtained by visual inspection of the data.
4.1 Data types
The data provided were recorded over a number of tests. Each test consisted of a similar procedure, in which an automated drill unit moved towards a static metallic disk at a fixed velocity (“feed”), a hole was drilled in the disk at that same feed-rate.
The following data streams were recorded during each test, each sampled at a rate of 20 KHz:
Ax – acceleration of the disk-mounting unit in the x-plane1 ,
Ay- acceleration of the disk-mounting unit in the y-plane1 ,
Az- acceleration of the disk-mounting unit in the z-plane1 ,
AE-RMS acoustic emission, 50-400 KHz2,
SP-power delivered to the drill spindle3.
Tests considered in this investigation used three drill-prices (of identical product specification) as shown in Table 1.
Table 1-Experiment Parameters by Test
Drill Number
Test Numbers
Drill Rotation Rate
Feed Rate
1
[12]
1700RPM
80 mm/min
2
[3127]
1700RPM
80 mm/min
3
[130194]
1700RPM
120mm/min
Note that tests 16,54,128,129 were not provided, thus a series of 190 tests are analysed in this investigation. These 190 tests are labeled as shown in Table 2.
Table 2 –Test indices used in this report against actual test numbers
Test Indices
Actual Test Number
[115]
[115]
[1652]
[1753]
[53125]
[55127]
[126190]
[130194]
4.2 Prior Experiment Knowledge
4.2.1 Normal Tests
AUT indicated that tests [10110] could be considered “normal processes”.
4.2.2 AE Sensor Placement
AUT noted that the position of the acoustic emission sensor was altered prior to test 77, and was adjusted prior to subsequent tests. From inspection of AE data, it appears that AE measurements are consistent after test 84, and so:
·AE is assumed to be unusable for tests [176] –the sensor records only white noise;
·AE is assumed to be usable, but possibly abnormal, for tests [7783] –the sensor position is being adjusted, resulting in extreme variation in measurements;
·AE is assumed to be usable for tests [94190] –the sensor position is held constant during these tests.
Thus, the range of tests assumed to be normal [10110] should be reduced to [84110] when AE is considered.
4.3 Test Description
Data recorded for during a typical test are shown in Figure 1. The duration of this test is approximately t=51 seconds. This section uses this test to illustrate a typical process, as described by AUT.
Drill power-on and power-off events may be seen at the start and end of the test as transient spikes in SP.
The drill unit is then moved towards the static disk at the constant feed rata specified in Table 1, between t=12 and 27 seconds. This corresponds to approximately constant values of SP during that period, approximately zero AE, and very lowamplitude acceleration in x-,y-,and z- planes.
At t=27 seconds, the drill makes contact with the static disk and begins to drill into the metal. This corresponds to a step-change in SP to a higher lever, staying approximately constant until t=38 seconds. During this time, AE increases significantly to a largely constant but non-zero value. The values Ax and Az increase throughout this drilling operation, while the value of Ay remains approximately zero (as it does throughout the test).
At t=38 seconds, the tip of the drill-bit passes through the rear face of the disk. The value of SP increases until t=44 seconds. During this period, AE reaches correspondingly high values, while Ax and Az decrease in amplitude.
At t=44 seconds, the direction of the drill unit is reversed, and the drill is retracted from the metal disk. Until t=46 seconds, the value of SP and AE decrease rapidly. A transient is observed in Ax and Az at t =44 seconds, with vibration amplitude decreasing until t=46 seconds.
At t=46 seconds, the drill-bit has been completely retracted from the metal disk, and the unit continues to be withdrawn at the feed rate until the end of the test. The value of SP decreases during this period(noting the power-off transient at the very end of the test), while the values of all three acceleration channels and AE are approximately zero.
6 .Pre-processing
4.4 Removal of Start/Stop Transients
Assuming that normal and abnormal system behaviour will be evident from data acquired during the drilling process, prior to analysis, each test was shortened by retaining only data between the start and stop events, shown as transients in SP. For example, for the test shown in Figure 1, this corresponds to retaining the period [1350] seconds.
4.5 Removal of Power Supply Signal
The 50 Hz power supply appears with in each channel, and was removed prior to analysis by application of a band-stop filter with stop-band [4951] Hz.
4.6 Frequency Transformation
Data for each test were divided into windows of 4096 points. A 4096-point FFT for was performed using data within each window, for Ax,Ay and Az channels. This corresponds to approximately 5 FFTs per second of data，similar to the QUICK system used in aerospace analysis， shown to provide sufficient resolution for identifying frequency-based events indicative of system abnormality.
For the analyses performed in this investigation, all spectral components of Ax, Ay, and Ay occurring at frequency f with power Pf below some threshold Pf
收藏