Operational Research Commons^™

Right-Hand-Side Multidimensional Optimality Analysis Of A Large Scale Linear Program Using Metamodelling Techniques, Osman Iyde

Theses and Dissertations

A methodology for optimality analysis of linear programs was developed by Johnson, Bauer, Moore, and Grant to create metamodels using response surface methodology techniques such as experimental design and least squares regression, and a geostatistical estimation technique, namely kriging. Metamodels have the form of a simple polynomial, and they predict the optimal objective function value of an LP for various levels of the constraints. They eliminate the necessity of determining which critical region contains the right-hand-side (RHS) vector of interest since they are valid over multiple critical regions. The methodology of Johnson, et al. can be applied to large scale …

An Analytical Framework For Assessing Future Force Structure Requirements Under Uncertainty, Michael L. Fredley

Theses and Dissertations

The objective of this research was to develop an analytical framework to assess future force structure requirements under the major uncertainties inherent in the post-Cold War era. Among the uncertainties are the frequency and nature of future threats to U.S. interests and the cost of maintaining, building, and demobilizing forces. The centerpiece of the methodology is a computer model which simulates the development of threats to U.S. interests and the actions the U.S. takes to protect those interests. From this simulation, the costs and risks associated with different policy alternatives can be estimated. The simulation is set within a broader …

A Methodology For Comparing The Value Of Competing Afmc Manpower Allocation Strategies, Sandra K. Smith

Theses and Dissertations

This research effort develops a methodology for Air Force Materiel Command (AFMC) decision makers to use during mandated resource allocation exercises for comparing competing manpower allocation strategies. A value model is used to represent the hierarchical objectives of the command, with the primary objective being the attainment of maximum mission effectiveness in the face of constrained resources. Value model decomposition is patterned according to the command's organizational structure. Scoring functions derived using direct assessment survey techniques capture the relationship between manpower and mission effectiveness for lowest level organizations. An additive value function represents the model mathematically; the primary objective value …

Life-Cycle Cost Analysis For Radioactive Waste Remediation Alternatives, Thomas P. White, Ronald J. Toland, Dorian Y. Buitrago

Theses and Dissertations

This research has two primary objectives. The first is to develop a generic, interactive, spreadsheet-based life-cycle cost model that uses net present value and risk analysis techniques for cost comparison. The second is to apply the model specifically to the vitrification and cementation methods of waste remediation. By using spreadsheet analysis and graphics capabilities, the model will provide direct and objective comparisons of remediation alternatives. Since vitrification is a new technology, the plant design and operations are conceptual. Therefore, computer simulation and engineering judgement are integral to the vitrification LCC estimate.

Dynamic Maintenance Scheduling For A Stochastic Telecommunication Network: Determination Of Performance Factors, Todd S. Patterson

Theses and Dissertations

This research proposes an analytical approach to access the relationship between maintenance facility location and communication network performance measurement using a selected dynamic maintenance scheduling protocol. There were three objectives established for this effort. The first objective was the determination of an upper-bound upon the level of performance for a telecommunication network using dynamically scheduled maintenance to evaluate maintenance depot location. This was achieved by using a two-stage algorithm, first locate a maintenance depot by using stochastic algorithms, and then to measure the resulting impact upon performance with a multi-commodity network flow model. The second objective was to develop the …

Estimation Of The Captive-Carry Survival Function For The Advanced Medium Range Air-To-Air Missile (Amraam), David R. Denhard

Theses and Dissertations

This thesis considers the problem of estimating the survival function of an item (probability that the item functions for a time greater than a given time t) from sampling data subject to partial right censoring (a portion of the items in the sampling data have not yet been observed to fail). Specifically the thesis describes several parametric and non-parametric statistical models that can be used when the sampling data is subject to partial right censoring. These models are applied to the case of estimating the captive-carry survival function of the AIM-120A Advanced Medium Range Air-to-Air Missile (AMRAAM).

The Development Of A Metamodel For A Major Weapon System Cost Model, Paul W. Campbell

Theses and Dissertations

Cost estimation is an integral part of the procurement process of major weapon systems. Despite this essential role, the cost estimation process is able to provide the decision makers and analysts with a limited amount of insight. This is due to the complex nature of the cost models that typically contain 20-30 cost estimating relationships (CERs) and 50-100 variables. In an effort to provide the decision makers and analysts with additional insight to the cost estimate, this research demonstrates a methodology that will (1) identify the cost drivers of the cost model, ( 2) estimate the effects of these cost …

Selecting Optimal Experiments For Feedforward Multilayer Perceptrons, Lisa M. Belue

Theses and Dissertations

Where should a researcher conduct experiments to provide training data for a multilayer perceptron? This question is investigated and a statistically-based method for optimally selecting experimental design points for multilayer perceptrons is introduced. Specifically, a criterion is developed based on the size of an estimated confidence ellipsoid for the weights in the multilayer perceptron. This criterion is minimized over a set of exemplars to find optimal design points. Initially, single output networks are examined. An example is used to demonstrate the superiority of optimally selected design points over randomly chosen points and points chosen in a grid pattern. Also, two …

Issues In Developing An Undergraduate Simulation Course, Paul Savory

Department of Industrial and Management Systems Engineering: Faculty Publications

Experience in developing an undergraduate simulation course is described. The course introduces the philosophies, principles, and methodologies for discrete-event simulation modeling. Strategy in choosing the course simulation software is discussed, plus important areas of teaching emphasis are highlighted.

Simulation Project Characteristics In Industrial Settings, Paul Savory

Department of Industrial and Management Systems Engineering: Faculty Publications

In a survey of practitioners of discrete-event simulation from industry and research institutes who "build models for money," we asked about project goals, user backgrounds and training, organizational types and activities, software and hardware choices, modeling team composition, and effort allocation within a modeling project. We found that (1) only about half of the practitioners have three or more years experience, (2) many academics feel strongly affiliated with their industry clients rather than with their university employers, (3) shop-floor supervisors rarely lead simulation projects, even though their knowledge of the system may be unparalleled, (4)simulation models are generally described as …

An Improved Heuristic For Intercontinental Ballistic Missile Crew Scheduling, Michael D. Shirley Jr.

Theses and Dissertations

Creating monthly schedules for missile crews is a complex and time-consuming problem. Thousands of events must be scheduled for several hundred missile officers. The rules and regulations governing the problem are numerous, and there are currently no established measures for missile crew schedules. The scheduling software currently available only schedules a fraction of the events. The objectives of this research were to create a rule-based heuristic which could quickly produce feasible or near-feasible schedules, to make the scheduling process paperless, and to develop possible measures of effectiveness for missile crew schedules. The research was successful in each of these areas. …

A Multi-Attribute-Utility-Theory Model That Minimizes Interview-Data Requirements: A Consolidation Of Space Launch Decisions, Raymond W. Staats

Theses and Dissertations

This research uses multi-attribute utility theory (MAUT) to define a mathematical representation of a decision maker's utility associated with a satellite system. While developing the survey instrument, we focused on making it simpler to administer, primarily by eliminating the use of lottery questions. These simplifications enabled us to shorten our interview with the decision maker to under two hours for a rather complex model.

An Approach For Representation Of Organizational Mental Models Using System Dynamics, Jörg-Peter Theissen

Engineering Management & Systems Engineering Theses & Dissertations

The concept of mental models has received much attention within recent years, especially within the context of organizational learning. This research is based on and departs from the Organizational Learning Process as developed by Keating, Robinson, and Clemson (1994). That process, which is based on a verbal representation of mental models, does not call forth the kind of change that is desired in Organizational Learning. This research investigates if mental models can be represented in the form of system dynamics models and inquires if this representation is beneficial to the process of Organizational Learning.

The research was designed as a …

Analysis Of The Jplan Exercise As An Experimental Learning Tool, Mark J. Lynch, Michael E. Washington

Theses and Dissertations

The purpose of this study is to develop an effective educational tool for the Combat Logistics course offered at the Air Force Institute of Technology. The current tool being used, the JPLAN Exercise, was identified as outdated in several areas. The research focused upon four investigative questions what makes an effective educational tool, should the existing exercise be revised or replaced, which logistics principles are essential for incorporation into the educational tool, and is the updated tool significantly different from the original. To answer these questions, we conducted an extensive literature review that focused on two areas. The first area …

Dynamic Load Balancing For A Parallel Discrete-Event Battlefield Simulation, Seth R. Guanu

Theses and Dissertations

This thesis investigates issues involved in developing a dynamic load balancing model for a parallel discrete event battlefield simulation. The research covers issues in task management, discrete-event simulation, parallel simulation, and load balancing. There are four primary issues discussed concerning the design of a dynamic load balancing model. The first issue is processor load evaluation which deals with the calculation of the amount of work on a processor. The second issue is load balancing profitability determination which deals with the decision to load balance or not based on some cost-gain relationship. The third issue is task migration which deals with …

Embedded Chaotic Time Series: Applications In Prediction And Spatio-Temporal Classification, James R. Stright

Theses and Dissertations

The Deterministic Versus Stochastic algorithm developed by Martin Casdagli is modified to produce two new, methodologies, each of which selectively uses embedding space nearest neighbors. Neighbors which are considered prediction relevant are retained for local linear prediction, while those which are considered likely to represent noise are ignored. For many time series, it is shown possible to improve on local linear prediction with both of the new algorithms. Furthermore, the theory of embedology is applied to determine a length of test sequence sufficient for accurate classification of moving objects. Sequentially recorded feature vectors of a moving object form a training …

Application Of Sequential Quadratic Programming To Large-Scale Structural Design Problems, Mark A. Abramson

Theses and Dissertations

Large-scale structural optimization problems are often difficult to solve with reasonable efficiency and accuracy. Such problems are often characterized by constraint functions which are not explicitly defined. Constraint and gradient functions are usually expensive to evaluate. An optimization approach which uses the NLPQL sequential quadratic programming algorithm of Schittkowski, integrated with the Automated Structural Optimization System ASTROS is tested. The traditional solution approach involves the formulation and solution of an explicitly defined approximate problem during each iteration. This approach is replaced by a simpler approach in which the approximate problem is eliminated. In the simpler approach, each finite element analysis …

A Mean Value Analysis Heuristic For Analysis Of Aircraft Sortie Generation, Richard C. Jenkins

Theses and Dissertations

The primary objective of this study was to develop an analytical methodology based on the Mean Value Analysis algorithm that approximates the performance characteristics of a queueing network model QNM containing a fork- join queue with probabilistic branching. These performance characteristics are response time, throughput and queue length at each station. The QNM solved contains the essential features of the aircraft sortie generation process. The sensitivity of the methods accuracy to increases in server utilization was determined. The comparisons of the results of the MVA heuristic to the outputs of the Logistics Composite Model LCOM simulation indicate that the heuristics …

A Fortran Based Learning System Using Multilayer Back-Propagation Neural Network Techniques, Gregory L. Reinhart

Theses and Dissertations

An interactive computer system which allows the researcher to build an optimal neural network structure quickly, is developed and validated. This system assumes a single hidden layer perceptron structure and uses the back- propagation training technique. The software enables the researcher to quickly define a neural network structure, train the neural network, interrupt training at any point to analyze the status of the current network, re-start training at the interrupted point if desired, and analyze the final network using two- dimensional graphs, three-dimensional graphs, confusion matrices and saliency metrics. A technique for training, testing, and validating various network structures and …

Assessing The Vulnerability Of Multi-Commodity Networks With Failing Components, Alan R. Robinson

Theses and Dissertations

This research proposes an analytical approach for assessing flow disturbance, or compromise, based on limited sampling of arc flow information in multi-commodity, or multiple origin-destination O-D, networks with failing arcs. There were three objectives established for this research. The first objective was to bound the expected flow, given the arcs fail with certain probabilities, which was accomplished by reviewing current approaches for single-commodity networks and extending the results to the multi-commodity case. The second objective was to determine the best placement of flow monitors to obtain the most accurate estimates of O-D pair volumes. This was accomplished using a multi-criteria …

An Rsm Study Of The Effects Of Simulation Work And Metamodel Specification On The Statistical Quality Of Metamodel Estimates, Michael K. Taylor

Theses and Dissertations

This research investigated the combined influence of simulation work and metamodel specification on the statistical quality of the estimates obtained from the resulting metamodels of the simulation data. A 9 x 2 x 2 experiment consisting of 9 cases of simulation work, 2 levels of metamodel specification, and 2 levels of design fractionation were designed for 8 different configurations of MMk queues. The only observed statistic for this experiment was the average queue length. Simulation estimates for each configurations average queue length were calculated directly from the simulation data. In addition, the metamodels were fit to the simulation data and …

The Effective Use Of Animation In Simulation Model Validation, Christopher L. Swider

Theses and Dissertations

This study examined two animation displays moving icons, bar graphs at two presentation speeds to determine how each of these factors affected the animations ability to communicate violations of model assumptions. Subjects viewed animation displays individually and in combination at each presentation speed. Eight problem scenarios were presented to evaluate each animations ability to communicate violations of different assumptions. Each animations communication ability was measured subjectively and objectively. Subjective measures in the form of pairwise comparisons were used to calculate normalized preference ratings for each animation. objective measures included problem identification accuracy and problem time. Subjective results indicated that moving …

Proactive Monitoring Of Performance In Stochastic Communication Networks, John C. C. Van Hove

Theses and Dissertations

This research proposes several models for placing bounds on the expected values of some dynamic performance measures for computer communication networks with failing components. These models provide an understanding of expected network performance that is useful in the process of proactive performance monitoring and also in defining level of service agreements with network users. There were three objectives for this research. The first objective was to extend some existing models of steady-state stochastic network performance to a dynamic network flow representation in order to capture the dynamic nature of proactive monitoring. The second objective was to convert the extended absolute …

Analysis Of Thunder Combat Simulation Model, Timothy S. Webb

Theses and Dissertations

TAC THUNDER, or THUNDER, is a two-sided large scale computer simulation model that simulates air and ground combat, logistics, and limited airlift at the theater level. It is in use by several allied nations, major defense contractors, and various Department of Defense DoD analysis agencies. The objectives of this thesis effort were to examine the overall model variability, examine the model output for possible interrelationships, and examine the model sensitivity to input parameters. A univariate and multivariate analysis was performed to examine the first two objectives. The univariate analysis consisted of an analysis of the confidence intervals and replication requirements …

An Air Mission Planning Algorithm For A Theater Level Combat Model, Brian J. Griggs

Theses and Dissertations

This thesis describes the development of an air mission planning algorithm for the Joint Staffs Future Theater Level Model FTLM. The overall problem scope was to develop an algorithm to handle major factors bearing on the combat mission planning problem while providing hook-ups for the FTLM architecture. Other aspects of the problem included finding the appropriate level of detail, developing a fast solving technique, and attempting to use existing data. The problem was handled by using some ideas from existing aircraft allocation algorithms and by adding some new techniques. The proposed air mission planning algorithm supplies the optimum degree of …

An Analysis Of Stopping Criteria In Artificial Neural Networks, Bruce Kostal

Theses and Dissertations

The goal of this study was to decide when to terminate training of an artificial neural network ANN. In pursuit of this goal, several characteristics of the ANN were monitored throughout ANN training classification error rate of the training set, testing set, or a weighted average of the two moving average classification error rate measurements of the difference between ANN output and desired output error sum of squares, total absolute error. or largest absolute error or ANN weight changes absolute weight change, squared weight change, or relative weight change. Throughout this research, the learning rate was held constant at 0.35. …

An Investigation Of Simulated Annealing Applied To Structural Optimization Problems, Richard C. Mceachin

Theses and Dissertations

This thesis investigates the feasibility of using Simulated Annealing SA in structural optimization problems. The investigation involves solving benchmark structural optimization problems with an SA algorithm, and comparing its solutions to those found by four other optimizers. Overall, the analysis shows that SA has limited applicability in structural optimization. Two primary factors were found to adversely impact the performance of the SA algorithm in these problems. These factors are high dimensionality, and high levels of constraint. The difficulty involved in solving these problems with a random search increases exponentially with the number of dimensions. The number, and non-linearity, of the …

An Analysis Of Air Force Acquisition Engineering Officer's Perceptions Of The Adequacy Of Their Preparation For Management, Steven E. Woodruff

Theses and Dissertations

The purpose of this study was to determine how much time Air Force acquisition engineers spend in performing management functions, how those engineers spend in performing management functions, how those engineers perceive their management training, and which types of training contribute the most to managerial competency. The results from surveys of 215 acquisition engineers assigned to ASCEN, Wright-Patterson AFB, OH and their supervisors revealed that engineers do indeed spend substantial amounts of time performing management functions. Slightly more than half the engineers reported spending at least 50 of an average workday performing management functions. Over 53 of engineers responding to …

An Integer Solution Heuristic For The Arsenal Exchange Model (Aem), Daniel J. Green

Theses and Dissertations

The Air Force Studies and Analyses Agency sought a method for converting the continuous solution produced by the Arsenal Exchange Model into a feasible integer solution. The current integerization method leaves weapons unused and targets uncovered and could be improved. In the method developed, the noninteger valued variables in the continuous solution are rounded down to the nearest integer to produce a truncated solution. An integer goal program is then used to reallocate the weapons and targets made available in the rounding process. The truncated solution is then combined with the solution of the integer goal program to produce a …

A Simulation Approach To Granite Sentry System Analysis, Marilyn J. Bauer

Theses and Dissertations

This study demonstrated the use of simulation modelling to analyze Granite Sentry system performance. The availability simulation model constructed provides a number of system performance measures as a function of component MTBFs and MTTRs. Analysis of failure data prior to model construction supported the generally accepted use of exponentially distributed failure rates and lognormally distributed repair times.