The Analysis and Application of Industrial Signals by Using Neural Network
碩士 === 義守大學 === 電機工程學系 === 102 === The aim of this thesis is about the applications of the data mining. The powerful learning and nonlinear mapping abilities of neural network are used to employed into the different and real industrial signals. The influencing degree of each input variable could be...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2014
|
Online Access: | http://ndltd.ncl.edu.tw/handle/80467833588409710226 |
Summary: | 碩士 === 義守大學 === 電機工程學系 === 102 === The aim of this thesis is about the applications of the data mining. The powerful learning and nonlinear mapping abilities of neural network are used to employed into the different and real industrial signals. The influencing degree of each input variable could be calculated based on the weights of the well trained neural network. According to the influencing degree of each variable, the importance of each input variable to the output could be clearly distinguished. The nonlinear relationship between input and output variables could also be obtained. This study could be employed into the real application of the manufacturing process of industry. The useful and important manufacturing parameters could be found and obtained. It can not only decrease the complexity of the industrial signal process, but also reduce the cost of the company. Thus, this research has promoted the practicability of the neural network in the real applications of data mining and signal process.
|
---|