Soft Computing, Part I
This is the first issue of a pair of two special issues on soft computing. The concept of soft computing was conceived by L. A. Zadeh in 1990. Soft computing refers to a coalition of methodologies, which are drawn together to deal with the pervasive imprecision that occurs often in the real world. The principal members of this coalition include fuzzy logic, neuro-computing, evolutionary computing, probabilistic computing, chaotic computing, and machine learning. These coalition members are synergistic in the sense that, in general, better results can be obtained when they are used in combination rather than in stand-alone mode. Therefore, in the future most likely many intelligent systems will be of hybrid type, employing a variety of soft computing methodologies in order to achieve superior performance.
Within the past few years, soft computing began to grow rapidly in both theoretical developments and practical applications in various fields. This Special Issue aims to examine such growth in the field of manufacturing engineering. The intended audience is primarily the practitioners of the manufacturing engineering profession who are responsible for the technical aspects of realizing a product. As stated earlier, this Special Issue is a companion to another Issue dedicated to the management aspects of running a production system. For those who are more interested in the theoretical developments of soft computing methodologies, please refer to the journals and technical conferences that are devoted to these subjects.
This Special Issue is comprised of a total of nine papers. The first three papers address engineering design related problems. The first paper is written by J. Wang and J. Terpenny. To deal with the uncertainty and imprecision inherent in the early design stages, they presented an iterative evolutionary approach to synthesize component-based preliminary engineering design problems. The second paper is written by B. C. Jiang and C.-H. Hsu. They developed a manufacturability evaluation model for the concurrent engineering environment based on fuzzy logic and multiple attribute decision making. The third paper is authored by C.-Y. Tsai and C. A. Chang. They proposed an intelligent design retrieval system that employs soft computing methodologies for both the feature and object association functions. Specifically, they employ the fuzzy relation and fuzzy composition concepts to realize the function of feature association whereas a fuzzy neural network implements the function of object association.
The next two papers address process-planning problems. The fourth paper is written by Li, et al. They presented a hybrid approach that combines the strengths of genetic algorithms and Tabu search to optimize an assembly process plan, in consideration of assembly guidelines as well as assembly constraints. It was shown that assembly plans obtained by the hybrid approach are superior to those derived by GA alone. The fifth paper, authored by G. C. Onwubolu and M. Mutingi, describes a genetic algorithm approach developed for solving the rectangular cutting stock problem. The objective is to minimize the waste. The simulation results of the proposed approach are encouraging when compared to the partial enumeration-based heuristic and the genetic neuro-nesting approach.
The last four papers address problems at the process level.
Konak et al. used a neural network approach to model a Hot
Isostatic Pressing process of nickel-based super-alloys for the estimation of
shrinkage. The neural network
approach was shown to outperform the regression approach.
The paper written by Su, et al.
deals with the process modeling and optimization problem. Their two-stage
approach first employs a back-propagation network to model the process and then
a genetic algorithm to find the optimal parameter settings. Better results were
obtained when compared to the Taguchi method.
Even thought the IC wire bonding process was studied, the approach can
definitely be generalized to other processes. The second last paper is written
by Hou, et al. They developed a methodology for the intelligent remote
monitoring and diagnosis of manufacturing processes. In an application to a manufacturing system that makes
conveyor belts, a back-propagation neural network accurately classified the
quality faults, and a rough set provided operating guidelines to the operators
on specific process settings in order to correct the detected quality problems.
Babuška, et al. wrote the last paper to address the control problem of
fermentation processes. To handle the diversity, non-linearity, and time-varying
nature of these processes, they proposed a supervised model-based self-tuning
control scheme. The supervisory
system is based on a combination of a state automaton with a rule-based fuzzy
The Guest Editors of this Special Issue are very thankful to all contributing authors. 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: http://www.csc.lsu.edu/trianta/Books/Special_Issue4/Special4.htm. Finally, the Guest Editors wish to express their gratitude to the Chief Editor of the Journal of Intelligent Manufacturing, Dr. Andrew Kusiak, for his support and guidance on this Special Issue.T. Warren Liao and Evangelos Triantaphyllou
Industrial and Manufacturing Systems Engineering Department (http://imse.lsu.edu)
Louisiana State University (http://www.lsu.edu)