Skip to Main Content
 

Global Search Box

 
 
 
 

Files

File List


case1056387721.pdf (3.84 MB)

ETD Abstract Container

Abstract Header

Solving adaptive multiple criteria problems by using artificial neural networks

Zhou, Yingqing
http://rave.ohiolink.edu/etdc/view?acc_num=case1056387721

Abstract Details

1992, Doctor of Philosophy, Case Western Reserve University, Systems and Control Engineering.
This dissertation addresses the application of Feedforward Artificial Neural Networks (FANNs) in solving Multiple Criteria Decision Making (MCDM) problems from the following aspects: (1) Designing the structure of FANNs; (2) Using FANNs in static MCDM; (3) Using FANNs in dynamic MCDM; and (4) Applying the method developed in this dissertation to machining Operations. In the structure design of a FANN, the capacity consideration of the FANN is important. In this dissertation, the capacity of a FANN with a given number of hidden nodes in approximating polynomial functions is given. The proofs and examples are presented. Secondly, an Adaptive Feedforward Artificial Neural Network (AF-ANN) is developed in solving static MCDM problems. The AF-ANN starts with an initial structure and increases its number of nodes until the desired structure is obtained. When training patterns change, the AF-ANN model can adapt itself to the changes by re-training or expanding the existing model. The static MCDM through AF-ANN consists of two steps: (a) Training an AF-ANN by the elicited information, and (b) Choosing the optimal alternative by using the trained AF-ANN. The theoretical basis for AF-ANN and examples are presented. The concept s of efficiency, concave, and convex in MCDM problems are discussed within the structure of AF-ANN. In dynamic MCDM problems, the Decision Maker (DM) may change his/her preferences. A FANN method is used to identify the changing preference function of the DM. To train a FANN efficiently in this dynamic environment, an adaptive algorithm is developed. This algorithm has two advantages: (a) The size of memory for training patterns does not increase as training patterns increase; and (b) the FANN is modified by using the algorithm such that, the new training pattern is always represented by the FANN while the total training error for the rest of training patterns is minimized. In terms of machining operations, a monitoring and supervising system is developed by using in-process regressions and FANNs. The system is designed for (a) in-process tool life measurement and prediction, (b) supervision of machining operations in terms of the best machining set-up, and (c) tool failure monitoring.
Behnam Malakooti (Advisor)
157 p.
Solving adaptive multiple criteria problems artificial neural networks

Recommended Citations

Citations

  • Zhou, Y. (1992). Solving adaptive multiple criteria problems by using artificial neural networks [Doctoral dissertation, Case Western Reserve University]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=case1056387721

    APA Style (7th edition)

  • Zhou, Yingqing. Solving adaptive multiple criteria problems by using artificial neural networks. 1992. Case Western Reserve University, Doctoral dissertation. OhioLINK Electronic Theses and Dissertations Center, http://rave.ohiolink.edu/etdc/view?acc_num=case1056387721.

    MLA Style (8th edition)

  • Zhou, Yingqing. "Solving adaptive multiple criteria problems by using artificial neural networks." Doctoral dissertation, Case Western Reserve University, 1992. http://rave.ohiolink.edu/etdc/view?acc_num=case1056387721

    Chicago Manual of Style (17th edition)

case1056387721
609
© 1992, all rights reserved.
This open access ETD is published by Case Western Reserve University School of Graduate Studies and OhioLINK.