The VLSI implementation of an artificial neural network scheme embedded in an automated inspection quality management system

2003 ◽  
Author(s):  
Chih-hsien Kung ◽  
M.J. Devaney ◽  
Chih-ming Kung ◽  
Chung-ming Huang ◽  
Yi-jen Wang ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Quality Management ◽  
Management System ◽  
Quality Management System ◽  
Vlsi Implementation ◽  
Automated Inspection ◽  
Artificial Neural

scholarly journals Design and Analog VLSI Implementation of Artificial Neural Network

2011 ◽  
Vol 2 (3) ◽  
pp. 96-109 ◽  
Author(s):  
Bapuray.D Yammenavar ◽  
Vadiraj.R Gurunaik ◽  
Rakesh.N Bevinagidad ◽  
Vinayak.U Gandage
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Analog Vlsi ◽  
Vlsi Implementation ◽  
Artificial Neural

Expert Project Recommendation Procedure for Arizona Department of Transportation’s Pavement Management System

1997 ◽  
Vol 1592 (1) ◽  
pp. 26-34 ◽  
Author(s):  
Gerardo W. Flintsch ◽  
John P. Zaniewski
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Management System ◽  
Trigger Points ◽  
Pavement Management ◽  
Network Simulator ◽  
Pavement Management System ◽  
Remaining Service Life ◽  
Artificial Neural ◽  
Condition Indicator

The Arizona Department of Transportation (ADOT) uses a network-level pavement management system to determine budget requirements for its annual pavement preservation program. Although this is a valuable tool for preservation programming, it does not assist the engineers with the selection of projects and rehabilitation treatments. The documented research was designed to enhance the capability of ADOT’s pavement management system to include project selection. An automatic project recommendation procedure was developed and implemented in a user-friendly, modular computer program. This automatic system is expected to reduce considerably the effort required to develop the preservation programs. It should improve the consistency of the decision process. The analysis starts with a section delineation procedure that delineates uniform roadway sections. It then computes the remaining service life of each uniform section by using linear performance equations and trigger points defined for each condition indicator. An artificial neural network simulator is used to screen and recommend roadway sections for the preservation program. The trained artificial neural network prepares a list of candidate sections, using the criteria learned from past selections and the current condition of all pavement sections. This preliminary list of candidate sections is further analyzed by a project recommendation procedure. This procedure recommends a preservation treatment, assigns a priority rating to each section in the list, and sorts the projects by priority. Funding is assigned to the highest-priority sections within each roadway group until the budget recommendation provided by the network optimization process is reached.

Sign in / Sign up

Export Citation Format

Share Document