Open Access. Powered by Scholars. Published by Universities.®

Engineering Commons

Open Access. Powered by Scholars. Published by Universities.®

Articles 1 - 23 of 23

Full-Text Articles in Engineering

A Study Of The Accuracy, Completeness, And Efficiency Of Artificial Neural Networks And Related Inductive Learning Techniques , Craig Garlin Carmichael Jan 2001

A Study Of The Accuracy, Completeness, And Efficiency Of Artificial Neural Networks And Related Inductive Learning Techniques , Craig Garlin Carmichael

Retrospective Theses and Dissertations

Artificial Neural Networks (ANNs) have been an intense topic of research in the last decade. They have been viewed as black boxes, where the inputs were known and the outputs were computed, but the underlying statistics and thus reliability of the networks were not fully understood. Because of this, there has been hesitation in utilizing ANNs in automated systems such as intelligent flight control. This hesitation is diminishing, however. Individual elements of a neural network can be probed and their decision-making power assessed. In this study, a neural network is trained and then various ranking methods are used to assess ...


Algorithms For Enhancing Pattern Separability, Feature Selection And Incremental Learning With Applications To Gas Sensing Electronic Nose Systems , Robi Polikar Jan 2000

Algorithms For Enhancing Pattern Separability, Feature Selection And Incremental Learning With Applications To Gas Sensing Electronic Nose Systems , Robi Polikar

Retrospective Theses and Dissertations

Three major issues in pattern recognition and data analysis have been addressed in this study and applied to the problem of identification of volatile organic compounds (VOC) for gas sensing applications. Various approaches have been proposed and discussed. These approaches are not only applicable to the VOC identification, but also to a variety of pattern recognition and data analysis problems. In particular, (1) enhancing pattern separability for challenging classification problems, (2) optimum feature selection problem, and (3) incremental learning for neural networks have been investigated;Three different approaches are proposed for enhancing pattern separability for classification of closely spaced, or ...


Knowledge Based Expert System Pavement Management Optimization , Omar Ghaleb Smadi Jan 2000

Knowledge Based Expert System Pavement Management Optimization , Omar Ghaleb Smadi

Retrospective Theses and Dissertations

Knowledge-based expert systems and dynamic programming are used for development of a comprehensive pavement management system tool to help engineers and planners to make objective, consistent, and cost effective decisions regarding pavement maintenance, rehabilitation, and reconstruction;Knowledge-based expert system provide a flexible tool to allow for acquisition of knowledge from experts in the field and incorporate that knowledge in building an efficient pavement management decision support tool. Knowledge-based expert systems are used to develop a pavement condition forecasting model and a treatment strategy selection model. The forecasting model is capable of predicting pavement condition in the future based on both ...


Power System Security Boundary Visualization Using Intelligent Techniques , Guozhong Zhou Jan 1998

Power System Security Boundary Visualization Using Intelligent Techniques , Guozhong Zhou

Retrospective Theses and Dissertations

In the open access environment, one of the challenges for utilities is that typical operating conditions tend to be much closer to security boundaries. Consequently, security levels for the transmission network must be accurately assessed and easily identified on-line by system operators;Security assessment through boundary visualization provides the operator with knowledge of system security levels in terms of easily monitorable pre-contingency operating parameters. The traditional boundary visualization approach results in a two-dimensional graph called a nomogram. However, an intensive labor involvement, inaccurate boundary representation, and little flexibility in integrating with the energy management system greatly restrict use of nomograms ...


Profiting From Competition: Financial Tools For Electric Generation Companies , Charles William Richter Jr. Jan 1998

Profiting From Competition: Financial Tools For Electric Generation Companies , Charles William Richter Jr.

Retrospective Theses and Dissertations

Regulations governing the operation of electric power systems in North America and many other areas of the world are undergoing major changes designed to promote competition. This process of change is often referred to as deregulation. Participants in deregulated electricity systems may find that their profits will greatly benefit from the implementation of successful bidding strategies. While the goal of the regulators may be to create rules which balance reliable power system operation with maximization of the total benefit to society, the goal of generation companies is to maximize their profit, i.e., return to their shareholders. The majority of ...


Pns Algorithm For Solving Supersonic Flows With Upstream Influences , James Hale Miller Jan 1997

Pns Algorithm For Solving Supersonic Flows With Upstream Influences , James Hale Miller

Retrospective Theses and Dissertations

The goal of this research is to produce a robust, parabolized Navier-Stokes (PNS) code that will significantly reduce the computer time required to calculate flows about complex vehicles with embedded subsonic/separated regions. The major drawback of "current day" PNS codes is that they cannot be used to compute separated regions which occur near canopies, wing-body junctures, etc. As a result, Navier-Stokes (NS) codes are often used to compute the entire flowfield despite the fact that a PNS code requires at least one order of magnitude less computer time and storage;An innovative approach has been developed to permit a ...


Development Of Four In-Process Surface Recognition Systems To Predict Surface Roughness In End Milling , Shi-Jer Lou Jan 1997

Development Of Four In-Process Surface Recognition Systems To Predict Surface Roughness In End Milling , Shi-Jer Lou

Retrospective Theses and Dissertations

Surface roughness is one of the important factors in tribology and in evaluating the quality of machining operations. To realize full automation and achieve zero defect production, an effective technique is needed for on-line, real-time monitoring of surface roughness during machining. An in-process surface recognition system (ISRS), was developed for predicting real-time surface roughness, Ra, in end-milling operations. The parameters are spindle speed, feed rate, depth of cut, and the cutting, vibration between tool and workpiece. The cutting vibration is measured by an accelerometer and a proximity sensor;The analyses of the data and the ISRS building model are carried ...


The Fuzzy-Nets Based Approach In Predicting The Cutting Power Of End Milling Operations , Chuan-Teh Chang Jan 1997

The Fuzzy-Nets Based Approach In Predicting The Cutting Power Of End Milling Operations , Chuan-Teh Chang

Retrospective Theses and Dissertations

Process planning is a major determinant of manufacturing cost. The selection of machining parameters is an important element of process planning. The development of a utility to show the cutting power on-line would be helpful to programmers and process planners in selecting machining parameters. The relationship between the cutting power and the machining parameters is nonlinear. Presently there is no accurate or simple algorithm to calculate the required cutting power for a selected set of parameters. Although machining data handbooks, machinability data systems, and machining databases have been developed to recommend machining parameters for efficient machining, they are basically for ...


Three-Dimensional Object Recognition , Kehang Chen Jan 1997

Three-Dimensional Object Recognition , Kehang Chen

Retrospective Theses and Dissertations

In the development of an object pattern recognition system, feature construction is always the problem issue. Due to the large amount of information contained in three dimensional (3D) objects, features extracted to efficiently and sufficiently represent 3D objects are difficult to obtain. Thus, current commercially available object recognition systems mostly emphasize the classification of two dimensional objects or patterns. This work presents a paradigm to develop a complete 3D object recognition system that uses simple and efficient features, and supports the integration of CAD/CAM models;In this research, several proposed algorithm for extracting features representing 3D objects are constructed ...


Invariance Transformations For Processing Nde Signals , Shreekanth Ammanji Mandayam Jan 1996

Invariance Transformations For Processing Nde Signals , Shreekanth Ammanji Mandayam

Retrospective Theses and Dissertations

The ultimate objective in nondestructive evaluation (NDE) is the characterization of materials, on the basis of information in the response from energy/material interactions. This is commonly referred to as the "inverse problem." Inverse problems are in general ill-posed and full analytical solutions to these problems are seldom tractable. Pragmatic approaches for solving them employ a constrained search technique by limiting the space of all possible solutions. A more modest goal is therefore to use the received signal for characterizing defects in objects in terms of the location, size and shape. However, the NDE signal received by the sensors is ...


Propagation Of Uncertainty In A Knowledge-Based System To Assess Energy Management Strategies For New Technologies , Chun-Yen Hsu Jan 1995

Propagation Of Uncertainty In A Knowledge-Based System To Assess Energy Management Strategies For New Technologies , Chun-Yen Hsu

Retrospective Theses and Dissertations

The goal of this project is to investigate the propagation of uncertainty in a knowledge-based system that assesses energy management strategies for new gas and electric technologies that can help reduce energy consumption and demand. The new technologies that have been investigated include lighting, electric heat pumps, motors, refrigerators, microwave clothes dryers, freeze concentration, electric vehicles, gas furnaces, gas heat pumps, engine-driven chillers, absorption chillers, and natural gas vehicles distributed throughout the residential, commercial, industrial, and transportation sectors;The description of a complex assessment system may be simplified by allowing some degree of uncertainty. A number of uncertainty-representing mechanisms, such ...


Automated Image Inspection Using Wavelet Decomposition And Fuzzy Rule-Based Classifier , Zhong Zhang Jan 1995

Automated Image Inspection Using Wavelet Decomposition And Fuzzy Rule-Based Classifier , Zhong Zhang

Retrospective Theses and Dissertations

A general purpose image inspecting system has been developed for automatic flaw detection in industrial applications. The system has a general purpose image understanding architecture that performs local feature extraction and supervised classification. Local features of an image are extracted from the compactly supported wavelet transform of the image. The features extracted from the wavelet transform provide local harmonic analysis and multi-resolution representation of the image. Image segmentation is achieved by classifying image pixels based on features extracted within a local area near each pixel. The supervised classifier used in the segmentation process is a fuzzy rule-based classifier which is ...


Nuclear Plant Diagnostics Using Neural Networks With Dynamic Input Selection , Anujit Basu Jan 1995

Nuclear Plant Diagnostics Using Neural Networks With Dynamic Input Selection , Anujit Basu

Retrospective Theses and Dissertations

The work presented in this dissertation explores the design and development of a large scale nuclear power plant (NPP) fault diagnostic system based on artificial neural networks (ANNs). The viability of detecting a large number of transients in a NPP using ANNs is demonstrated. A new adviser design is subsequently presented where the diagnostic task is divided into component parts, and each part is solved by an individual ANN. This new design allows the expansion of the diagnostic capabilities of an existing adviser by modifying the existing ANNs and adding new ANNs to the adviser;This dissertation also presents an ...


Medical Image Tomography: A Statistically Tailored Neural Network Approach , John Patrick Kerr Jan 1994

Medical Image Tomography: A Statistically Tailored Neural Network Approach , John Patrick Kerr

Retrospective Theses and Dissertations

In medical computed tomography (CT) the tomographic images are reconstructed from planar information collected 180∘ to 360∘ around the patient. In clinical applications, the reconstructions are typically produced using a filtered backprojection algorithm. Filtered backprojection methods have limitations that create a high percentage of statistical uncertainty in the reconstructed images. Many techniques have been developed which produce better reconstructions, but they tend to be computationally expensive, and thus, impractical for clinical use;Artificial neural networks (ANN) have been shown to be adept at learning and then simulating complex functional relationships. For medical tomography, a neural network can be trained to ...


Advanced Fuzzy Logic Controllers And Self-Tuning Strategy , Shou-Heng Huang Jan 1994

Advanced Fuzzy Logic Controllers And Self-Tuning Strategy , Shou-Heng Huang

Retrospective Theses and Dissertations

This study has concentrated on fuzzy logic controllers from the basic aspects to an advanced self-tuning strategy. Fuzzy logic provides a very good technique for knowledge representation which makes it possible to incorporate the experience of human operators in the design of controllers;The basic concepts of fuzzy set theory, fundamental definitions of fuzzy logic, and basic structure of fuzzy logic controllers are introduced and a guideline for building the fuzzy rule-based system is developed. The rule development and adjustment strategies for fuzzy logic controllers are presented and experimentally identified. The fuzzy logic control system is analyzed on a linguistic ...


Spline Network Modeling And Fault Classification Of A Heating Ventilation And Air-Conditioning System , Mathew Scaria Chackalackal Jan 1994

Spline Network Modeling And Fault Classification Of A Heating Ventilation And Air-Conditioning System , Mathew Scaria Chackalackal

Retrospective Theses and Dissertations

A spline network, that is an alternative to artificial neural networks, is introduced in this dissertation. This network has an input layer, a single hidden layer, and an output layer. Spline basis functions, with small support, are used as the activation functions. The network is used to model the steady state operation of a complex Heating Ventilation and Air-conditioning (HVAC) system. Real data was used to train the spline network. A neural network was also trained on the same set of data. Based on the training process, it is possible to conclude that when compared to artificial neural networks, the ...


Color Computer Vision For Characterization Of Corn Germplasm , Suranjan Panigrahi Jan 1992

Color Computer Vision For Characterization Of Corn Germplasm , Suranjan Panigrahi

Retrospective Theses and Dissertations

A color computer vision system was developed at Iowa State University, Ames, Iowa for morphological characterization of corn germplasm. The system consists of a color camera, a PC-AT host computer, a color frame digitizer, a video display monitor, a color video decoder and encoder, and a specially designed lighting chamber. The lighting chamber was specially designed and fabricated to provide uniform lighting for acquiring images of ear corn. The components of the system were matched and interfaced to configure the entire system. A study was conducted to calibrate each component and the entire system to ensure proper functioning of the ...


An Expert Fuzzy Logic Controller Employing Adaptive Learning For Servo Systems , Zong-Mu Yeh Jan 1992

An Expert Fuzzy Logic Controller Employing Adaptive Learning For Servo Systems , Zong-Mu Yeh

Retrospective Theses and Dissertations

An expert fuzzy logic controller with adaptive learning is proposed as an intelligent controller for servo systems. A key component of this controller is an adaptive learning mechanism which is used to self-regulate the scaling factors and the control action based on the error between the desired value and the plant output. The inference engine of this controller is based on the principle of approximate reasoning and the learning strategy is based on reinforcement learning. A novel approach of model reference adaptive control is also proposed for servo systems. The comparison of the performance between the proposed controller and PID ...


Knowledge Base Expert System Control Of Spatial Xenon Oscillations In Pressurized Water Reactors , Serhat Alten Jan 1992

Knowledge Base Expert System Control Of Spatial Xenon Oscillations In Pressurized Water Reactors , Serhat Alten

Retrospective Theses and Dissertations

Nuclear reactor operators are required to pay special attention to spatial xenon oscillations during the load-follow operation of pressurized water reactors. They are expected to observe the axial offset of the core, and to estimate the correct time and amount of necessary control action based on heuristic rules given in axial offset control strategies;Current control methods of axial xenon oscillations are knowledge intensive, and heuristic in nature. An expert system, ACES (Axial offset Control using Expert Systems) is developed to implement a heuristic constant axial offset control procedure to aid reactor operators in increasing the plant reliability by reducing ...


Neural Network Approach For Solving Inverse Problems, Ibrahim Mohamed Elshafiey Jan 1991

Neural Network Approach For Solving Inverse Problems, Ibrahim Mohamed Elshafiey

Retrospective Theses and Dissertations

No abstract provided.


A Microcomputer Based Combined Machine Vision And Expert System For Irregular Object Classification , Syed Azhar Saeed Zaidi Jan 1990

A Microcomputer Based Combined Machine Vision And Expert System For Irregular Object Classification , Syed Azhar Saeed Zaidi

Retrospective Theses and Dissertations

In recent years, much work has been reported on the development of microcomputer based machine vision systems. A substantial portion of this research assumes most of the items subjected for machine vision inspection, can be categorized by a regular geometrical shape. Most of the vision systems, and microcomputer-based vision systems in particular, are designed to perform singular tasks. They are niche oriented and designed to be used in an inflexible environment, and are designed to process regular objects. These systems are prohibitively expensive for small industrial concerns;The objective of the research was to develop and design a low cost ...


Design Of An Expert System For Failed Fuel Identification And Surveillance In Ebr-Ii , Ramin Mikaili Jan 1990

Design Of An Expert System For Failed Fuel Identification And Surveillance In Ebr-Ii , Ramin Mikaili

Retrospective Theses and Dissertations

Since 1977, a program has been underway at experimental breeder reactor-II (EBR-II) to evaluate the performance of metal and mixed-oxide liquid metal reactor (LMR) fuel elements after clad failure (breach). The motivation for this activity, called run beyond cladding breach (RBCB) testing, is to continue safe operation of EBR-II after occurrence of a single or multiple clad failures. Principal safety concerns are excessive release of fission gas (FG) and mixed-oxide fuel/sodium interaction, which result in release of by-products to the sodium and may result in blockage of coolant flow. Excessive release of FG is controlled by the cover gas ...


Expert Systems For Security Trend Analysis Of Transient-Voltage-Limited Power Systems , S. Venkataraman Jan 1990

Expert Systems For Security Trend Analysis Of Transient-Voltage-Limited Power Systems , S. Venkataraman

Retrospective Theses and Dissertations

In this dissertation, we apply expert system techniques and Transient Energy Function (TEF) method results for dynamic system security assessment (DSSA). The concept of power system vulnerability combines the effect of contingencies on the security level and its rate of change with the changing system conditions and/or parameters. Vulnerability of a power system can be computed using the results of the sensitivity analysis program of the TEF method. The computation of vulnerability requires a large amount of data obtained from the results of stability analysis programs and this data needs to be organized into a structured knowledge base for ...