A Study of Using Artificial Neural Network in a Non-linear Centrifugal Compressor System
Journal Title: International Journal on Computer Science and Engineering - Year 2012, Vol 4, Issue 12
Abstract
This study adopts the centrifugal compressor system which produces the nitric acid equipment in China Petrochemical Development Corporation’s Plant. The system is non-linear and its manufacturing process is changeable, which the traditional PID (Proportional-Integral-Differential) control method is difficult to apply. This study is intended to apply the artificial neural network method to test and forecast the compressor performance. By means of collecting the PLC (Programmable Logic Controller) on-line data, the proposed method is applied to simulate the control system. According to the result of this study, the proposed method can reach the high accuracy, and make concrete contributions in promoting the safety of the centrifugal compressor system.
Authors and Affiliations
Prof. Pin-Chang Chen , Prof. Hung-Teng Chang , Mr. Armada Hsu
HIERARCHICAL DOCUMENT ORGANIZATION AND RETRIEVAL BASED ON THEMES FOR NEWS TRACKS
Organizing text documents is an important task and there are also numbers of strategies available in it. A good document clustering approach can assist computers in organizing the document corpus automatically into a mea...
Road Recognition for Vision Navigation of Robot by Using Computer Vision
This paper presents a method for vision navigation of robot by road recognition based on image processing. By taking advantages of the unique structure in road images, the square images on road can be scanned while the r...
Ambient Intelligence: The Next Generation Technology
Configuration of the computing and communications systems found at home and in the workplace is a complex system design that currently requires the attention of the user. Recently, researchers have begun to explore compu...
AN EFFICIENT SUPER RESOLUTION TECHNIQUE FOR LOSS LESS COMPRESSED BAYER COLOUR FILTER ARRAY IMAGES
In digital cameras, Bayer color filter array(CFA) images are captured and demosaicing is carried out before compression. Recently, it was found that compression-first schemes outperform the conventional demosaicing-first...
USER INTEREST LEVEL BASED PREPROCESSING ALGORITHMS USING WEB USAGE MINING
Web logs take an important role to know about user behavior. Several pattern mining techniques were developed to understand the user behavior. A specific kind of preprocessing technique improves the quality and accuracy...