National Changhua University of Education Institutional Repository : Item 987654321/18470
English  |  正體中文  |  简体中文  |  Items with full text/Total items : 6507/11669
Visitors : 30412185      Online Users : 454
RC Version 3.2 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Adv. Search
Login ‧ Upload ‧ Help ‧ About ‧ Administer
NCUEIR > College of Technology > vr > Proceedings >  Item 987654321/18470

Please use this identifier to cite or link to this item: http://ir.ncue.edu.tw/ir/handle/987654321/18470

Title: 引擎正時齒輪與汽門間隙之智慧型故障診斷
Intelligent Fault Diagnosis System of Engine Timing Gear and Valve Clearance
Authors: 陳建斌;鍾丞韋;吳建達
Contributors: 車輛科技研究所
Keywords: 離散小波;倒傳遞類神經;支援向量機;故障診斷
Discrete wavelet transforms;Back-propagation neural network;Support vector machine;Fault diagnosis system
Date: 2011-06
Issue Date: 2014-04-29T07:33:18Z
Publisher: 中華民國振動與噪音工程學會
Abstract: 傳統的汽車引擎故障檢測技術對於引擎內部機件所造成的異常聲訊與振動還是無法精確判斷，在以往都是依靠經驗豐富的老技師憑著維修經驗，甚至嘗試錯誤法的原則找出故障原因，以至於無法提升維修效率與速度。本文中提出一套智慧型專家系統，分別利用加速規與麥克風收錄實驗中所設定的故障聲音訊號與振動訊號，將擷取之訊號利用離散小波轉換技術作為特徵擷取的方法，從訊號中找出所隱含的特徵向量，在智慧型分類的步驟中，也分別採用監督式學習與非監督式學習的所代表的分類器，如倒傳遞類神經與支持向量基，在此作為相互的比較。實驗結果顯示本文所提出的智慧型診斷技術能得到較好的辨識速度與判別結果。
Traditional engine fault diagnosis technology is still unable precisely to detect fault problems. Mostly rely on the experience of technical staff to do to judge, but engine failure conditions usually complex cases, and then some failures because of technical personnel, subjective judgments and misjudgments. Therefore not increase maintenance efficiency and service quality. In this paper proposed the intelligent recognition system. It based on discrete wavelet transform (DWT), support vector machine (SVM), and back-propagation neural network (BPNN). DWT can find hidden information from the signals. In the classification stage, use supervised and unsupervised learning classifiers, such as BPNN and SVM. Compare the effectiveness of the two classifiers. Experimental results indicate that the internal combustion engine platform fault identification on the expert system, by engine vibration and sound signals are useful to identify the faults in the proposed study.
Relation: 第十九屆中華民國振動與噪音工程學會論文集, : 1-5
Appears in Collections:[vr] Proceedings

Files in This Item:

File SizeFormat
index.html0KbHTML508View/Open


All items in NCUEIR are protected by copyright, with all rights reserved.

 

DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback