DSpace

Now showing 1 - 10 of 26

ADAPTIVE FUZZY CONTROL OF UNSTABLE NONLINEAR-SYSTEMS
(1995-09-01)
LIN, CJ
;
LIN, CT
;
電控工程研究所
;
Institute of Electrical and Control Engineering
This paper addresses the structure and an associated on-line learning algorithm of a feedforward multilayer connectionist network for realizing the basic elements and functions of a traditional fuzzy logic controller. The proposed Fuzzy Adaptive Learning Control Network (FALCON) can be contrasted with the traditional fuzzy logic control systems in their network structure and learning ability. An on-line structure/parameter learning algorithm, called FALCON-ART, is proposed for constructing the FALCON dynamically. The FALCON-ART can partition the input/output space in a flexible way based on the distribution of the training data. Hence it can avoid the problem of combinatorial growing of partitioned grids in some complex systems. It combines the backpropagation learning scheme for parameter learning and the fuzzy ART algorithm for structure learning. More notably, the FALCON-ART can on-line partition the input/output spaces, tune membership functions, and find proper fuzzy logic rules dynamically without any a priori knowledge or even any initial information on these. The proposed learning scheme has been successfully used to control two unstable nonlinear systems. They are the seesaw system and the inverted wedge system.
NOVEL TECHNIQUE TO FORM PT-SILICIDED SHALLOW P(+)N JUNCTIONS USING LOW-TEMPERATURE PROCESSES
(1995-09-01)
MA, KP
;
LIN, CT
;
CHENG, HC
;
奈米中心
;
Nano Facility Center
By implanting BF2+ ions into thin polycrystalline Si films with subsequent low-temperature (as low as 500 degrees C) annealing, excellent Pt-silicided shallow p(+)n junctions have been formed. The samples implanted under the conditions of 100 keV/5 x 10(15) cm(-2) showed a leakage of 7 nA/cm(2) and a junction depth of about 0.05 mu m after 500 degrees C annealing, and the current leakages further decreased to a value at about 2 nA/cm(2) when the annealing temperature was raised to 550 degrees C. Various conditions of implant and annealing were examined to determine and characterize their effects on the resultant junctions.
AN EXAMPLE OF DISBENEFITS OF CENTRALIZED STOCKING
(1990-03-01)
CHEN, MS
;
LIN, CT
;
管理科學系
;
Department of Management Science
AN ART-BASED FUZZY ADAPTIVE LEARNING CONTROL NETWORK
(1994)
LIN, CJ
;
LIN, CT
;
電控工程研究所
;
Institute of Electrical and Control Engineering
Neural fuzzy control of unstable nonlinear systems
(1995)
LIN, CT
;
LIN, CJ
;
CHUNG, IF
;
電控工程研究所
;
Institute of Electrical and Control Engineering
REINFORCEMENT LEARNING FOR ART-BASED FUZZY ADAPTIVE LEARNING CONTROL NETWORKS
(1995)
LIN, CJ
;
LIN, CT
;
電控工程研究所
;
Institute of Electrical and Control Engineering
EFFECTS OF CENTRALIZATION ON EXPECTED COSTS IN A MULTI-LOCATION NEWSBOY PROBLEM
(1989-06-01)
CHEN, MS
;
LIN, CT
;
管理科學系
;
Department of Management Science
AN EXAMPLE OF DISBENEFITS OF CENTRALIZED STOCKING
(1990-03-01)
CHEN, MS
;
LIN, CT
;
管理科學系
;
Department of Management Science
CENTRALIZED EFFECT ON EXPECTED COSTS IN A MULTILOCATION NEWSBOY PROBLEM
(1991-03-01)
CHANG, PL
;
LIN, CT
;
管理科學系
;
Department of Management Science
This is a single-period single-product inventory model with several individual sources of demand. It is a multi-location problem with an opportunity for centralization. The holding and penalty cost functions, at each location, are assumed to be linear and identical. Two types of inventory system are considered in this paper: The decentralized system and the centralized system. The decentralized system is a system in which a separate inventory is kept to satisfy the demand at each source of demand and there is no reinforcement between locations; i.e., the surplus supplied location is not allowed to supply the deficient supplied location. Therefore, the total expected cost of the decentralized system is the sum of the expected cost of individual locations, as the holding cost or penalty cost of each location depends only on its own inventory level and is unrelated to any other location's inventory level. The centralized system is a system in which the surplus location is allowed to supplement the deficient one by transportation. Therefore, the holding cost or penalty cost is calculated by the net surplus or net deficient after the reinforcement. The total expected cost of the centralized system should therefore include the expected holding cost, the expected penalty cost and the expected transportation cost. Let hBAR > 0,pBAR > 0 and tBAR greater-than-or-equal-to 0 be the unit holding cost, the unit penalty cost and the unit transportation cost, respectively. This paper demonstrates that, for any probability distribution of a location's demand, the following two properties are always true: (1) tBAR < hBAR+pBAR if and only if the total expected cost in a decentralized system exceeds those in a centralized system. (2) For all i, j, i not-equal j, p(ij), the coefficient of correlation between the i-th location's demand and the j-th location's demand, is equal to 1, then for any tBAR, the total expected cost in a decentralized system is equal to those in a centralized system.
ON THE EFFECT OF CENTRALIZATION ON EXPECTED COSTS IN A MULTILOCATION NEWSBOY PROBLEM
(1991-11-01)
CHANG, PL
;
LIN, CT
;
管理科學系
;
Department of Management Science
This paper deals with a single-period, single-product inventory model with several individual sources of demand. It is a multi-location problem with an opportunity for centralization. Two types of inventory system are considered in this paper: the decentralized system and the centralized system. The aim of this paper is to extend Eppen's model by adding the consideration of transportation cost to constitute a new inventory model. With this new inventory model we prove three theorems that include the results of Eppen's model.

學術出版;;Publications

Browse

Filters

Settings

Sort By

Results per page

🏛️國立陽明交通大學機構典藏

Search Results