下載電子全文宣告This thesis is authorized to indicate in-campus access only
You can not download at the moment.
Your IP address is 184.108.40.206
The defense date of the thesis is 2012-08-21
The current date is 2019-07-19
This thesis will be accessible at off-campus not accessible
URN etd-0817112-192301 Statistics This thesis had been viewed 1367 times. Download 3 times. Author Tien-Yuan Chen Author's Email Address No Public. Department Mechanical Engineering Year 2011 Semester 2 Degree Master Type of Document Master's Thesis Language zh-TW.Big5 Chinese Page Count 118 Title Analysis and Optimization of Rectangular Expansion Chamber with Multiple Extended tubes Keyword Neural NetworkS SYSNOISE Extended thin baffle Extended thin baffle SYSNOISE Neural NetworkS Abstract Abstract
A software (SYSNOISE), one kind of the boundary element method (BEM) used in acoustic analysis, has been adopted in this paper. The main purpose for this paper is to study the acoustical-performance of the plenums equipped with multiple thin extended baffles.
First, the model and testing set of the plenum will be planned. Thereafter, the outline model of the plenum is established t using the I-DEAS software and then imported to the SYSNOISE. The related acoustical performance（Transmission Loss） of the plenums equipped with multiple thin extended baffles and internally lined with sound absorbing material will be proceeded.
Two primary issues presented in this paper include (1) To explore the influences of the acoustical performance by varying the lengths of extended baffles and tubes for the plenums equipped with open, extended baffles, and extended tubes; (2) To search for optimally shaped plenum by using the SYSNOISE, Neural Network, and Genetic Algorithm.
Here, the accuracy of mathematical model has been verified using the experimental data and found to be in good agreement. Consequently, the optimization applied in industry can effectively shorten the design time, lower the manufacturing cost, and enhance the product competitiveness.
Keywords: SYSNOISE、Extended thin baffle、Neural Network System
Advisor Committee Ying-Chun Chang - advisor
Files Date of Defense 2012-07-19 Date of Submission 2012-08-21