Operations Research, Systems Engineering and Industrial Engineering Commons^™

A Comparison Of Fam And Cmac For Nonlinear Control, Arit Thammano, Cihan H. Dagli

Engineering Management and Systems Engineering Faculty Research & Creative Works

This article compares a neural network-based controller, both local and global networks, with fuzzy associative memories (FAM) on a nonlinear problem. CMAC and FAM are chosen as representatives of local generalization networks. CMAC controller is trained off-line, therefore, it can response to the incoming input immediately. CMAC can interpolate its memory and give a reasonable control signal even the input has not been trained on. Backpropagation is picked as a representative of global generalization networks. All three systems are studied on a simple simulated control problem. This preliminary research will be adapted later to control the laser cutting machine. A …

Ai-Based Generation Of Production Engineering Labor Standards, Hulya Yazici, Colin Othniel Benjamin, James Mcglaughlin

Engineering Management and Systems Engineering Faculty Research & Creative Works

Increased automation of manufacturing is necessary to compete in today's worldwide markets. The role of artificial intelligence (AI) techniques for incorporating the automation with changing manufacturing environments needs to be investigated. Al techniques can assist in meeting the challenge of transforming shop floor production engineering data into appropriate production engineering labor standards in a timely, consistent, and cost-effective manner. Production heuristics can be incorporated into an expert system that can learn from the changing manufacturing environment. This paper presents a prototype expert system which transfers the knowledge of experienced methods engineers into a rule-based system to develop the appropriate job …

The Application Of Markov State Probabilities In Developing Artificially Intelligent Managerial Strategies: A Case Study Based On Major League Baseball, Arnold Vincent Arconati

Doctoral Dissertations

"Baseball is a very large industry that influences the lives and financial assets of millions of people.

Many baseball analysts estimate that even the best Major League player can increase his team's expected number of yearly wins by only 3 or 4 games. In 1993 Bobby Bonilla, a New York Mets National League outfielder, earned $5,200,000 more than the average Major League player earned. The Mets apparently believed that expenditure of this money was worth his expected additional victories. If the strategy of an Artificially Intelligent baseball manager could produce 4 more team victories than the corresponding human baseball manager, …

Decision-Support Tools For Transferring Am/Fm/Gis To Small Communities, Steven W. Mccrary, Colin Othniel Benjamin, Peter J. Schmidt

Engineering Management and Systems Engineering Faculty Research & Creative Works

This paper examines several decision-support tools for transferring AM/FM/GIS technology to small communities. The term Computer-Assisted Spatial Information Systems (CASIS) provides a basis for a systematic categorization and definition of AM/FM/GIS systems that will serve to enhance small communities' understanding of these technologies for future decisions. The acronym CASIS includes such areas as database-management systems, automated mapping/facilities management/geographic information systems (AM/FM/GIS), and computer-aided drafting (CAD). Further, this paper reports the highlights of a survey that assesses the theory-practice gap in AM/FM/GIS usage among very small local government agencies. The survey uncovered an existing theory-practice gap: A, slow rate of system …

A Model Of Electronic Warfare Systems Acquisition And Engineering For Saudi Arabia, Negaa M. Albegami

Doctoral Dissertations

"A major activity within the systems engineering process is the requirements definition and analysis phase. In technical systems, planning this phase looks too technical for top management and too broad for the engineers specialized in narrow technical fields. This categorization (too technical/too broad) represents a gap between top management and specialized engineering. In Saudi Arabia, such a gap is believed to be very wide.

The main objective of this research is to find a way to narrow this gap between management and engineering when planning government systems, especially in electronic warfare (EW) systems. A solution in this effort is to …

Hands-On Structural Engineering Experiences With The "Anex" Mini-Laboratory, Richard A. Behr, Colin Othniel Benjamin, Azam A. Mirza

Civil, Architectural and Environmental Engineering Faculty Research & Creative Works

The ANEX facility has been developed to allow nearly real-time comparisons of analysis results with experimental data gathered on small-scale structural models. ANEX has been used successfully for in-class demonstrations, student-designed experiments, and comprehensive design/build competitions in an introductory structural analysis course at the University of Missouri-Rolla. An expert system is now being developed to guide ANEX users and to act as a trouble-shooter and advisor in the event that analytical and experimental results do not correlate acceptably well. ANEX, using only simple, small-scale model structures, is able to enrich structural engineering instruction by introducing students to the sophisticated capabilities …

The Management Of Replicated Data, Hsueh-Chi Shih, C. Y. Ho, S. Alptekin

Computer Science Technical Reports

Data replication, which has the benefits of improving system availability and read performance, proved to be indispensable to many database applications. In a replicated database, the one-copy serializability of transaction executions can be ensured by employing a replica control mechanism on top of the traditional concurrency control mechanism. This work contains two replica control algorithms and a read-only transaction processing algorithm. Both replica control algorithms handle multiple site, communication and partitioning failures. The replica control algorithms achieve read operation efficiency by always translating a logical read operation into one local physical read operation and by taking advantage of the locality …

Application Of Total Quality Management To Research And Development: An Historical Perspective, Scott A. Dellana, Henry Allen Wiebe

Engineering Management and Systems Engineering Faculty Research & Creative Works

This paper discusses the historical applications of Total Quality Management (TQM) to Research and Development (R&D). Research aimed at establishing an effective model for the application of TQM philosophies and tools to the R&D environment must start from this historical perspective. The emphasis of this paper is on the relationship of quality tools and techniques to the application of TQM in R&D, providing the foundation for further model development. The scope and definition of R&D is presented and is followed by an overview of the TQM philosophy and its associated tools and techniques. Special attention is given to defining performance …

Computer Networking For Operation Management And Optimization In Power Utility Industry, Ali K. Kamrani, Kamran K. Kamrani

Engineering Management and Systems Engineering Faculty Research & Creative Works

The connectivity, flexibility, and real time control capability of computer systems have led electric utility companies to consider the use of computers and telecommunication networks. The application of such an environment includes data acquisition, supervisory control, operation optimization, and data management. This paper presents the layout of a computer system network for an electric power utility.

Educating Engineers To Manage Technology: An International Comparison, Daniel L. Babcock, Brian E. Lloyd

Engineering Management and Systems Engineering Faculty Research & Creative Works

Two countries, the United States and Australia, are compared in terms of: (1) the historical growth of their engineering professions; (2) the structure of their engineering professional organizations; (3) the prevalence of engineers in management positions; and (4 the education of their engineers for management responsibilities.

The Management Of Change: A Case Study, Stephen A. Raper, Richard Neal Callahan

Engineering Management and Systems Engineering Faculty Research & Creative Works

A literature review was conducted to identify some of the requirements for competitiveness and change that are being promoted by leaders in the manufacturing field. A survey was developed based on the literature review and was subsequently administered, via the case study method, at a midwestern US agricultural chemicals firm to determine the company's degree of compliance with the literature''s recommendations. To a large degree, the company complied with the requirements.

A Methodology For Customer Requirements Generation In Communication Systems Planning, Negaa Albegami, Yildirim Omurtag

Engineering Management and Systems Engineering Faculty Research & Creative Works

In electronic communication systems it is nearly impossible to keep up with changing technology. This problem is further aggregated in the developing countries where the contractor (probably a western company) is expected to develop the system from the ground up. A basic problem which confronts this approach is either: 1) The customer will start adding or rejecting some of the capabilities, or 2) The local operation will never use some of the capabilities. Both of these outcomes are costly in terms of time and resources available to a developing country. This paper describes a new methodology for requirements generation to …

Moving Object Recognition And Guidance Of Robots Using Neural Networks, Abhijit Neogy, S. N. Balakrishnan, Cihan H. Dagli

Mechanical and Aerospace Engineering Faculty Research & Creative Works

The design of a robust guidance system for a robot is discussed. The two major tasks for this guidance system are the online recognition of a moving object invariant to rotation and translation, and tracking the moving object using a neural-network-driven vision system. This system included computer software ported to the IBM PC and interfaced with an IBM 7535 robot. The operation of this guidance system involved recognition of a moving object and the ability to track it till the robot and effector was in close proximity of the object. It was found that the robot was able to track …

Composite Stock Cutting Through Simulated Annealing, Hanan Lutfiyya, Bruce M. Mcmillin, Pipatpong Poshyanonda, Cihan H. Dagli

Computer Science Faculty Research & Creative Works

This paper explores the use of Simulated Annealing as an optimization technique for the problem of Composite Material Stock Cutting. The shapes are not constrained to be convex polygons or even regular shapes. However, due to the composite nature of the material, the orientation of the shapes on the stock is restricted. For placements of various shapes, we show how to determine a cost function, annealing parameters and performance. © 1992.

Composite Stock Cutting Through Simulated Annealing, Pipatpong Poshyanonda, Cihan H. Dagli

Computer Science Technical Reports

This paper explores the use of Simulated Annealing as an optimization technique for the problem Composite Material Stock Cutting. The shapes are not constrained to be convex polygons or even regular shapes. However, due to the composite nature of the material, the orientation of the shapes on the stock is restricted. For placements of various shapes, we show how to determine a cost function, annealing parameters, and performance.

Composite Stock Cutting Through Simulated Annealing, Pipatpong Poshyanonda, Cihan H. Dagli

Computer Science Technical Reports

This paper explores the use of Simulated Annealing as an optimization technique for the problem Composite Material Stock Cutting. The shapes are not constrained to be convex polygons or even regular shapes. However, due to the composite nature of the material, the orientation of the shapes on the stock is restricted. For placements of various shapes, we show how to determine a cost function, annealing parameters, and performance.

Integrated Neural Network And Machine Vision Approach For Intelligent State Identification, Cihan H. Dagli, Timothy Andrew Bauer

Engineering Management and Systems Engineering Faculty Research & Creative Works

An interfacing of neural networks (NNs) and machine vision to provide the next state of a system given an image of the present state of the system is presented. This interfacing is applied to a loading operation. First, a NN is trained for part recognition under conditions of rotation, location, object distortion, and background noise given an image of the part. Then, a second NN, given the output of the first NN and an image of a pallet being loaded, is trained for optimal part loading onto the pallet under conditions of noise in the image. The paradigm used is …

An Empirical Analysis Of Backpropagation Error Surface Initiation For Injection Molding Process Control, Alice E. Smith, Elaine R. Raterman, Cihan H. Dagli

Engineering Management and Systems Engineering Faculty Research & Creative Works

Backpropagation neural networks are trained by adjusting initially random interconnecting weights according to the steepest local error surface gradient. The authors examine the practical implications of the arbitrary starting point on the error landscape of the ensuing trained network. The effects on network convergence and performance are tested empirically, varying parameters such as network size, training rate, transfer function and data representation. The data used are live process control data from an injection molding plant

A Technological Development Model For Strategy Formation, Halvard E. Nystrom

Engineering Management and Systems Engineering Faculty Research & Creative Works

Summary form only given, as follows. The author presents a technological development model for product and company development based on a distinction between explicit and implicit technologies. Implicit technologies are evolving technologies while explicit technologies are established technologies. Based on empirical data from Swedish companies, a number of strategic dimensions are discussed such as network interaction and combining knowledge from various sources. These concepts are then used to present an integrated model of strategy formation and product and company development. It is argued that this view of technological development facilitates the understanding and analysis of innovation and entrepreneurship in highly …

Coordinated Strategic Planning Of Hydroelectric Energy Usage Using Stochastic Dynamic Programming With Decoupled Production Cost Simulation, Duane David Highley

Masters Theses

"The method of Stochastic Dynamic Programming is applied to the problem of Long-term hydrothermal coordination for a five-reservoir system in the Midwest. The model that has been developed will optimize the monthly reservoir elevations to produce the lowest expected energy production cost. The production cost calculations are decoupled from the Dynamic Programming loop, resulting in shorter execution times. Constraints are included for maximum and minimum reservoir elevations, maximum monthly reservoir rise and drop, and maximum and minimum monthly energy production. These constraints help to reduce the state space and shorten execution time. An additional constraint is modeled to control the …

Toward The Development Of Decision Support Tools To Manage The Catis Project Life Cycle, Steven Wayne Mccrary

Doctoral Dissertations

"The American Public Works Administration (1987) states that communities' infrastructures are in need of repair and better management and recommends CATIS (Computer-Assisted Terraspatial Information Systems) as an excellent tool to assist in that endeavor. Small communities have several voids that CATIS technology can fill. This research reports on a life-cycle approach to CATIS adoption that will help small communities to better manage their infrastructure.

It is important for small communities to become aware of the types of systems available and what each system can do. This study presents a straightforward, understandable discussion of CATIS technologies, features, and applications. Justifying the …

Simulated Annealing Approach For Solving Stock Cutting Problem, Cihan H. Dagli, Alireza Hajakbari

Engineering Management and Systems Engineering Faculty Research & Creative Works

The simulated annealing approach is applied to stock cutting. The conceptual approach proposed uses an energy function that measures the area of the rectangular enclosure of all the patterns to be nested, the level of similarity between pattern pairs, and the amount of overlap among patterns in evaluating various pattern configurations to be generated by the simulated annealing algorithm. Three methods for pattern configuration generation are considered. The first method uses heuristics to generate the initial configuration. The second and third methods use random selection and random placement of patterns

A Parallel Architecture For Stock Cutting Problem, Cihan H. Dagli, Alireza Hajakbari

Engineering Management and Systems Engineering Faculty Research & Creative Works

The problem of allocating irregular patterns arises frequently in applications where it has to be determined how a set of two-dimensional shapes will fit onto a stock sheet of finite dimensions with minimum waste. The use of the simulated annealing approach for the solution of this problem is described

Neural Networks In Manufacturing: Possible Impacts On Cutting Stock Problems, Cihan H. Dagli

Engineering Management and Systems Engineering Faculty Research & Creative Works

The potential of neural networks is examined, and the effect of parallel processing on the solution of the stock-cutting problem is assessed. The conceptual model proposed integrates a feature-recognition network and a simulated annealing approach. The model uses a neocognitron neural network paradigm to generate data for assessing the degree of match between two irregular patterns. The information generated through the feature recognition network is passed to an energy function, and the optimal configuration of patterns is computed using a simulated annealing algorithm. Basics of the approach are demonstrated with an example.

Cost Justification Of An Expert System, Alice E. Smith, Cihan H. Dagli

Engineering Management and Systems Engineering Faculty Research & Creative Works

It is pointed out that, like other projects which spend corporate dollars, an expert system must be analyzed for its economic and strategic worth to the organization. Both traditional engineering economy project analysis and multivariate holistic methods can be applicable. The fundamental strategy of the analyst is to decide upon the evaluation methodologies, gather cost and benefit data, study the project from various perspectives, and present the results and recommendations.

Knowledge-Based Prototype For Improving Scheduling Productivity, Colin Othniel Benjamin, Daniel L. Babcock, N. B. Yunus, John B. Kincaid

Engineering Management and Systems Engineering Faculty Research & Creative Works

The development of efficient construction plans and schedules presents continuing challenges to construction schedulers. Knowledge-based systems offer considerable potential as computer-based planning tools to aid the development of realistic project plans and schedules. This paper outlines the development of a knowledge-based prototype system for construction planning and scheduling and evaluates its effectiveness as a tool for improving the productivity of inexperienced construction project schedulers. The prototype, developed using the M.1 knowledge engineering shell, incorporates data bases, algorithm, and heuristics that mimic the decision process of expert construction project schedulers and identifies a work breakdown structure and precedence relationships. Inexperienced schedulers …

Possible Applications Of Neural Networks In Manufacturing, S. Lammers, Cihan H. Dagli

Engineering Management and Systems Engineering Faculty Research & Creative Works

Summary form only given. An examination is made of the potential of neural networks and the impact of parallel processing in the design and operations of manufacturing systems. After an initial discussion on possible areas of application, an approach that integrates artificial intelligence, operations research, and neural networks for the solution of a scheduling problem is examined

Application Of Distributed Knowledge Bases In Intelligent Manufacturing, Cihan H. Dagli, Gerald E. Hoffman

Engineering Management and Systems Engineering Faculty Research & Creative Works

The authors consider independent knowledge bases operating on separate work stations networked together within the domain of knowledge-based scheduling. The scheduling problem is addressed through distributed knowledge bases that have an ability to pass information back and forth between small knowledge bases functioning at different decision-making levels. A small manufacturing plant is conceptualized in order to experiment with this process. The general outline and areas of the manufacturing shop are shown. The domain specific area for the knowledge bases is to optimize the scheduling of work at each work station in order to meet a weekly quota. Automatic guided vehicle, …

Packaging Engineering Education Qualitative Need Assessment, M. Douglas Sachs

Masters Theses

"Packaging engineering is an interdisciplinary field which has no formal degree program to support it. While there arc packaging engineers in industry, there are no packaging engineering degrees presently being offered by our nation's colleges and universities. In order to lay a foundation upon which a degree program could be based, this thesis has investigated the needs of packaging engineering education by seeking the input of the packaging industry. This qualitative comparison has been quantified, resulting in a list of prioritized classes and topics upon which a degree program could be based"--Abstract, page ii.

Toward The Development Of A Knowledge-Based Construction Schedule Planning System, Nordin Bin Yunus

Doctoral Dissertations

"This research attempts to model and prototype a knowledge-based system for use in the construction industry to accomplish the automatic generation of initial construction schedules. The schedule can be transformed into a logical network that provides a physical representation of the construction operations plan. The prototype system, which requires symbolic processing and reasoning, is developed based on an intensive modeling that rationally examines industry practice.

The model identifies work breakdown and precedence relationship as the two major concepts in schedule planning. Work breakdown is concerned with the identification of construction activities that result in the completion of project elements. Precedence …