Free vibration analysis of a Timoshenko beam carrying multiple spring-mass systems Using Artificial Neural Network
碩士 === 建國科技大學 === 自動化工程系暨機電光系統研究所 === 98 === This paper discusses a Timoshenko beam carrying multiple spring - mass system free vibration analysis of Timoshenko beam in the area but in addition I consider the shear deformation and rotary inertia, but also the shear deformation and rotational inertia...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2010
|
Online Access: | http://ndltd.ncl.edu.tw/handle/28531425394123085315 |
id |
ndltd-TW-098CTU05490046 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-098CTU054900462015-10-28T04:06:50Z http://ndltd.ncl.edu.tw/handle/28531425394123085315 Free vibration analysis of a Timoshenko beam carrying multiple spring-mass systems Using Artificial Neural Network 利用類神經網路分析Timoshenko樑附帶多個彈簧-質量系統自由振動 Cheng-Chung Chiu 邱政中 碩士 建國科技大學 自動化工程系暨機電光系統研究所 98 This paper discusses a Timoshenko beam carrying multiple spring - mass system free vibration analysis of Timoshenko beam in the area but in addition I consider the shear deformation and rotary inertia, but also the shear deformation and rotational inertia generated by a high-order items of common coupling and considering, re-use neural network (Artificial Neural Network, ANN) to find the best of the free vibration analysis model. First, using a Timoshenko beam carrying multiple spring-mass systems , the quality of the equation of motion to obtain the natural frequency coefficient values of exact solutions, exact solutions and then use this value as a neural network back propagation (Back Propagation, BP) training of the experimental data for neural network optimization model. Finally, training in the best of the free vibration analysis of neural network, the different parameters of free vibration of Timoshenko beam case, after training the numerical results obtained by scatter plot to represent, then the values obtained after training and the correct solution to do the average error and root mean square value of error, and then and so the error method to assess the performance of neural network state. By neural network training and simulation frequency coefficient error of ±2% range, enough to confirm that neural network model to establish the relationship between design parameters is feasible, the detection measurement data is also very correct, so can reduce the error rate and time the loss. Jee-Ray Wang 王紀瑞 2010 學位論文 ; thesis 0 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 建國科技大學 === 自動化工程系暨機電光系統研究所 === 98 === This paper discusses a Timoshenko beam carrying multiple spring - mass system free vibration analysis of Timoshenko beam in the area but in addition I consider the shear deformation and rotary inertia, but also the shear deformation and rotational inertia generated by a high-order items of common coupling and considering, re-use neural network (Artificial Neural Network, ANN) to find the best of the free vibration analysis model.
First, using a Timoshenko beam carrying multiple spring-mass systems , the quality of the equation of motion to obtain the natural frequency coefficient values of exact solutions, exact solutions and then use this value as a neural network back propagation (Back Propagation, BP) training of the experimental data for neural network optimization model.
Finally, training in the best of the free vibration analysis of neural network, the different parameters of free vibration of Timoshenko beam case, after training the numerical results obtained by scatter plot to represent, then the values obtained after training and the correct solution to do the average error and root mean square value of error, and then and so the error method to assess the performance of neural network state. By neural network training and simulation frequency coefficient error of ±2% range, enough to confirm that neural network model to establish the relationship between design parameters is feasible, the detection measurement data is also very correct, so can reduce the error rate and time the loss.
|
author2 |
Jee-Ray Wang |
author_facet |
Jee-Ray Wang Cheng-Chung Chiu 邱政中 |
author |
Cheng-Chung Chiu 邱政中 |
spellingShingle |
Cheng-Chung Chiu 邱政中 Free vibration analysis of a Timoshenko beam carrying multiple spring-mass systems Using Artificial Neural Network |
author_sort |
Cheng-Chung Chiu |
title |
Free vibration analysis of a Timoshenko beam carrying multiple spring-mass systems Using Artificial Neural Network |
title_short |
Free vibration analysis of a Timoshenko beam carrying multiple spring-mass systems Using Artificial Neural Network |
title_full |
Free vibration analysis of a Timoshenko beam carrying multiple spring-mass systems Using Artificial Neural Network |
title_fullStr |
Free vibration analysis of a Timoshenko beam carrying multiple spring-mass systems Using Artificial Neural Network |
title_full_unstemmed |
Free vibration analysis of a Timoshenko beam carrying multiple spring-mass systems Using Artificial Neural Network |
title_sort |
free vibration analysis of a timoshenko beam carrying multiple spring-mass systems using artificial neural network |
publishDate |
2010 |
url |
http://ndltd.ncl.edu.tw/handle/28531425394123085315 |
work_keys_str_mv |
AT chengchungchiu freevibrationanalysisofatimoshenkobeamcarryingmultiplespringmasssystemsusingartificialneuralnetwork AT qiūzhèngzhōng freevibrationanalysisofatimoshenkobeamcarryingmultiplespringmasssystemsusingartificialneuralnetwork AT chengchungchiu lìyònglèishénjīngwǎnglùfēnxītimoshenkoliángfùdàiduōgèdànhuángzhìliàngxìtǒngzìyóuzhèndòng AT qiūzhèngzhōng lìyònglèishénjīngwǎnglùfēnxītimoshenkoliángfùdàiduōgèdànhuángzhìliàngxìtǒngzìyóuzhèndòng |
_version_ |
1718112638766940160 |