Computational Intelligence in Industrial Engineering
A Special Issue of the Journal
Inter'l Journal of Industrial Engineering: Theory, Applications and Practice
Vol. 7, No. 1, 2003
(Published in March of 2003)
by T. Warren Liao, Evangelos Triantaphyllou and Jacob Chen
Computational intelligence is a term used to refer to a group of paradigms
developed to represent and process numeric and symbolic data/information in an
intelligent manner by computers. Well known computational intelligence paradigms
include neural networks, genetic algorithms, rule-based reasoning, case-based reasoning,
fuzzy sets/logics, and hybrid of the above. Theoretical developments of these
computational intelligence paradigms continue as we speak.
Over the years, computational intelligence paradigms have been shown effective
in solving real world problems in various domains, including industrial engineering
problems. This process of testing out new theoretical developments will not cease
because we are never satisfied with the status quo and constantly look out for new and
better ways to solve daily problems.
This special issue aims to give a glimpse of what specific computational
intelligence paradigms are popular among the industrial engineering community in
solving what specific types of industrial engineering problems at this point in time. The
intended audience is the practitioners. For those who are more interested in theoretical
developments, please refer to journals or technical conferences devoted to these subjects.
This Special Issue comprises of a total of nine papers. Among them, five papers
employ genetic algorithms. The other four include three neural network applications and
one case-based reasoning application. The first paper is written by H. Y. Fan and J.
Lampinen. They modified the original differential evolution algorithm by adding a
directed mutation operation with the objective to increase the convergence velocity of the
differential evolution and thereby to obtain an acceptable solution with a lower number of
objective function evaluations. The modified version of the differential evolution was
empirically examined with a suite of six well-known test problems and found to
statistically outperform the original one.
The second paper is written by H. Cao and D. Wang. They developed a
simulation based genetic algorithm approach to find the optimal solution for a partner
selection problem in new product developments. The partner selection problem was
formulated as a 0-1 integer programming one with non-linear objective function and
stochastic constraints. The third paper is authored by C. Moon and Y. H. Lee to address
an integrated process planning and scheduling problem with the objective to minimize the
makespan. They first formulated the problem as a mathematical model and then solved it
with a new genetic algorithm approach using topological sort. The fourth paper is written
by M. R. de Almeida et al. This paper presents a method, based on Genetic Algorithms,
to optimize the production scheduling of the fuel oil and asphalt area in a petroleum
refinery. They showed that the proposed method is able to correctly schedule the refinery
production with no delays and adequate quality, and in the meantime maintaining a
minimal stock in the product storage tanks. The fifth paper, authored by C. Smith,
considers a multiple-inventory loading problem involving a set of commodities that must
be transported from a distributor to a retailer. The vehicle carrying out this distribution is
divided into several compartments, in which only one type of commodity may be loaded.
Therefore, the problem becomes one of determining optimal assignments of vehicle
compartments to commodities in order to minimize a mix of transportation and inventory
costs. Instead of pursuing the development of an exact algorithm, the author instead
recommends the use of a genetic algorithm to quickly provide good quality solutions.
The sixth paper is written by P. C. Chang and J. C. Hsieh to deal with the due date
assignment problem in a simulated wafer production factory. The influential variables
related to the flowtime of each order are first identified through regression analysis. A
neural network model is then established to forecast the due-date of each order based on
the identified influential variables. The experimental results show that the proposed
approach convincingly outperforms with the traditional approaches. The seventh paper is
authored by C. S. Cheng and S. J. Chen. They studied the joint monitoring of process
mean and variance using the neural network technology. The important features that set
the current research apart from previous studies include the use of one single neural
network to monitor both mean and variance shifts and the invariance of the neural
network to sample size. The eighth paper is written by T.S. Li, C. Y. Chen and C. T. Su.
They compared several neural networks and statistical algorithms for classification
problems. The ninth paper is written by C. Chiu and N. S. Chiu. They applied a case-
based reasoning approach that uses nonlinear similarity functions and dynamic weighting
mechanisms for predicting airplane landing gravity.
The Guest Editors of this Special Issue are very thankful to all contributing
authors. Their patience and strive for excellence is highly appreciated. We hope that this
Special Issue will become a forum for the dissemination of the current developments and
also for initiating new partnerships among researchers and practitioners. To facilitate this
goal, we thus created a dedicated webpage, which can be accessed at URL:
Finally, the Guest Editors wish to express their gratitude to the Chief Editor of the
International Journal of Industrial Engineering, Dr. A. Mital, for his support and guidance
of this Special Issue and the Managing Editor for his administrative assistance.
T. Warren Liao
T. Warren Liao's Homepage
Dr. Triantaphyllou's Homepage
J. Chen's Homepage
Go back to the Special Issue's Homepage